192 accepted papers
High-resolution visual encoders in multimodal large language models (MLLMs) substantially improve fine-grained perception, yet incur prohibitive computational costs.Existing token pruning methods are effective on natural images but struggle with spatially sparse structured inputs (e.g., charts), whe…
Large Language Model (LLM)-based multi-agent systems often suffer from high communication cost due to redundant interactions, as existing methods optimize communication structures without explicitly measuring whether exchanged messages contribute to the final decision. To better utilize the semantic…
As Large Language Models (LLMs) are increasingly popularized in the multilingual world, ensuring hallucination-free factuality becomes markedly crucial. However, existing benchmarks for evaluating the reliability of Multimodal Large Language Models (MLLMs) predominantly focus on textual or visual m
Large Language Models (LLMs) are increasingly used for question answering over scientific research papers. Existing retrieval augmentation methods often rely on isolated text chunks or concepts, but overlook deeper semantic connections between papers. This impairs the LLM's comprehension of scientif…
Large-scale video-language pretraining enables strong generalization across multimodal tasks but often incurs prohibitive computational costs. Although recent advances in masked visual modeling help mitigate this issue, they still suffer from two fundamental limitations: severe visual information lo
Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of tasks, yet they generally lack self-awareness, often displaying overconfidence when confronted with questions beyond their knowledge boundaries. This limitation severely hinders their trustworthiness in high
Vision-Language Models (VLMs) have achieved success in tasks such as visual question answering, yet their resilience to distractions remains underexplored. Understanding how distractions affect VLMs
Personalized image preference assessment aims to evaluate an individual user's image preferences by relying only on a small set of reference images as prior information. Existing methods mainly focus on general preference assessment, training models with large-scale data to tackle well-defined task…
Introducing high-quality references can largely alleviate the uncertainty in blind face image restoration tasks, yet the equivocal utilization of reference priors makes it still a struggle to well preserve the human identity. We attribute the identity inconsistency to two deficiencies of existing re
Multimodal Large Language Models (MLLMs) have achieved notable success in enhancing translation performance by integrating multimodal information. However, existing research primarily focuses on image-guided methods, whose applicability is constrained by the scarcity of multilingual image-text pairs…
Reliable, drift-free global localization presents significant challenges yet remains crucial for autonomous navigation in large-scale dynamic environments. In this paper, we introduce a tightly-coupled Semantic-LiDAR-Inertial-Wheel Odometry fusion framework, which is specifically designed to provide…
Large reasoning models (LRMs) have shown strong performance in complex mathematical reasoning when optimized via reinforcement learning (RL). However, conventional outcome-only reward provides sparse feedback, leading to inefficient optimization. In this work, we investigate whether generative proce…
Temporal Knowledge Graphs (TKGs) are vital for event prediction, yet current methods face limitations. Graph neural networks mainly depend on structural information, often overlooking semantic understanding and requiring high computational costs. Meanwhile, Large Language Models (LLMs) support zero-…
Road curbs are considered as one of the crucial and ubiquitous traffic features, which are essential for ensuring the safety of autonomous vehicles. Current methods for detecting curbs primarily rely on camera imagery or LiDAR point clouds. Image-based methods are vulnerable to fluctuations in light
The release of OpenAI’s O1 and subsequent projects like DeepSeek R1 has significantly advanced research on complex reasoning in LLMs. This paper systematically analyzes existing reasoning studies from the perspective of self-evolution, structured into three components: data evolution, model evolutio…
The colossal parameters and computational overhead of Large Language Models (LLMs) challenge their real-world applications. Network pruning, which targets unstructured or structured sparsity by removing redundant parameters, has recently been explored for LLM acceleration. Existing LLM pruning works…
With the popularity of large language models and their high-quality text generation capabilities, researchers are using them as auxiliary tools for text summary writing. Although summaries generated by these large language models are smooth and capture key information sufficiently, the quality of th…
LiDAR-based localization serves as a critical component in autonomous systems, yet existing approaches face persistent challenges in balancing repeatability, accuracy, and environmental adaptability. Traditional point cloud registration methods relying solely on offline maps often exhibit limited ro
The increasing size of deep neural networks (DNNs) necessitates effective model compression to reduce their computational and memory footprints. Sparsity and quantization are two prominent compression methods that have been shown to reduce DNNs' computational and memory footprints significantly whil…
Large Vision-Language Models (LVLMs) have achieved remarkable success, yet their significant computational demands hinder practicaldeployment. While efforts to improve LVLM efficiency are growing, existing methods lack comprehensive evaluation across diverse backbones, benchmarks, and metrics. In th…
Self-disclosure can provide psychological comfort and social support, but it also carries the risk of unintentionally revealing sensitive information, leading to serious privacy concerns. Research on self-disclosure in Chinese multimodal contexts remains limited, lacking high-quality corpora, analys
Layout-to-image (L2I) generation has exhibited promising results in natural domains, but suffers from limited generative fidelity and weak alignment with user-provided layouts when applied to degraded scenes (i.e., low-light, underwater). We primarily attribute these limitations to the "contextual i…
Accurate depth estimation is crucial for 3D scene comprehension in robotics and autonomous vehicles. Fisheye cameras, known for their wide field of view, have inherent geometric benefits. However, their use in depth estimation is restricted by a scarcity of ground truth data and image distortions. W
To tackle complex tasks in real-world scenarios, more researchers are focusing on Omni-MLLMs, which aim to achieve omni-modal understanding and generation. Beyond the constraints of any specific non-linguistic modality, Omni-MLLMs map various non-linguistic modalities into the embedding space of LLM…
Accurate prediction of pedestrian trajectories is crucial for improving the safety of autonomous driving. However, this task is generally nontrivial due to the inherent stochasticity of human motion, which naturally requires the predictor to generate multi-modal prediction. Previous works leverage v
Evaluating the graph comprehension and reasoning abilities of Large Language Models (LLMs) is challenging and often incomplete. Existing benchmarks focus primarily on pure graph understanding, lacking a comprehensive evaluation across all graph types and detailed capability definitions. This paper p…
Entity alignment (EA), critical for knowledge graph (KG) integration, identifies equivalent entities across different KGs. Traditional methods often face challenges in semantic understanding and scalability. The rise of language models (LMs), particularly large language models (LLMs), has provided p
Diffusion Probabilistic Models (DPMs) have achieved significant success in generative tasks. However, their training and sampling processes suffer from the issue of distribution mismatch. During the denoising process, the input data distributions differ between the training and inference stages, pot…
Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified process. Well alignment needs high-quality pre-training data and…
Large Multimodal Models (LMMs) have recently demonstrated impressive performance on general video comprehension benchmarks. Nevertheless, for broader applications, the robustness of their temporal analysis capability needs to be thoroughly investigated yet predominantly ignored. Motivated by this, w…
As video language models (VLMs) gain more applications in various scenarios, the need for robust and scalable evaluation of their performance becomes increasingly critical. The traditional human expert-based evaluation of VLMs has limitations in consistency and scalability, which sparked interest in…
Graph-theoretic problems arise in real-world applications like logistics, communication networks, and traffic optimization. These problems are often complex, noisy, and irregular, posing challenges for traditional algorithms. Large language models offer potential solutions but face several challenge
Multimodal Large Language Models (MLLMs) have achieved significant success in Speech-to-Text Translation (S2TT) tasks. While most existing research has focused on English-centric translation directions, the exploration of many-to-many translation is still limited by the scarcity of parallel data. To…
Unified multimodal large language models (U-MLLMs) have demonstrated impressive performance in end-to-end visual understanding and generation tasks. However, compared to generation-only systems (e.g., Stable Diffusion), the unified architecture of U-MLLMs introduces new risks of propagating demograp…
Large language models (LLMs) have shown remarkable capabilities in natural language processing. However, in knowledge graph question answering tasks (KGQA), there remains the issue of answering questions that require multi-hop reasoning. Existing methods rely on entity vector matching, but the purpo…
Large Language Models (LLMs) have demonstrated impressive capabilities in text generation but raise concerns regarding potential copyright infringement. While prior research has explored mitigation strategies like content filtering and alignment, the impact of adversarial persuasion techniques in el
Although large language models (LLMs) have demonstrated remarkable reasoning capabilities, they still face challenges in knowledge-intensive multi-hop reasoning. Recent work explores iterative retrieval to address complex problems. However, the absence of intermediate guidance often leads to inaccur…
Traditional knowledge distillation techniques are aimed at compressing models and speeding up inference, but they often fail to maintain the superior capabilities of complex models in simpler ones. To address this issue, this paper focus on the deraining task and introduces the Sequential Knowledge-…
Recent advancements in proactive dialogues have garnered significant attention, particularly for more complex objectives (e.g. emotion support and persuasion). Unlike traditional task-oriented dialogues, proactive dialogues demand advanced policy planning and adaptability, requiring rich scenarios a…
Traffic sign is a critical map feature for navigation and traffic control. Nevertheless, current methods for traffic sign recognition rely on traditional deep learning models, which typically suffer from significant performance degradation considering the variations in data distribution across diffe
Pre-training techniques play a crucial role in deep learning, enhancing models' performance across a variety of tasks. By initially training on large datasets and subsequently fine-tuning on task-specific data, pre-training provides a solid foundation for models, improving generalization abilities a
Two-step approaches combining pre-trained large language model embeddings and anomaly detectors demonstrate strong performance in text anomaly detection by leveraging rich semantic representations. However, high-dimensional dense embeddings extracted by large language models pose challenges due to s
Despite the remarkable reasoning capabilities demonstrated by large language models (LLM), the substantial computational overhead limits their practices. Some efforts have been directed toward distilling multi-step reasoning capabilities into smaller models through chain-of-thought (CoT). While CoT…
Although recent methods have tried to introduce large multimodal models (LMMs) into industrial anomaly detection (IAD), their generalization in the IAD field is far inferior to that for general purposes. We summarize the main reasons for this gap into two aspects. On one hand, general-purpose LMMs l…
Crack segmentation is pivotal for structural health monitoring, enabling the timely maintenance of critical infrastructure such as bridges and roads. However, existing deep learning models are often too computationally intensive for deployment on resource-constrained devices. To address this limitat
This paper presents a generic trajectory planning method for wheeled robots with fixed steering axes while the steering angle of each wheel is constrained. In the existing literatures, All-Wheel-Steering (AWS) robots, incorporating modes such as rotation-free translation maneuvers, in-situ rotationa…
Unmanned vehicles usually rely on Global Positioning System (GPS) and Light Detection and Ranging (LiDAR) sensors to achieve high-precision localization results for navigation purpose. However, this combination with their associated costs and infrastructure demands, poses challenges for widespread a…
Visual odometry (VO) system is challenged by complex illumination environments. Image quality and its consistency in the time domain directly determine feature detection and tracking performance, which further affect the robustness and accuracy of the entire system. In this paper, an image acquisiti…
In this paper, we present our exploration of annotating Chinese word senses using English WordNet synsets, with examples extracted from OntoNotes Chinese sense inventories. Given a target word along with the example that contains it, the annotators select a WordNet synset that best describes the mea…
Large language models (LLMs) have demonstrated strong reasoning capabilities.Nevertheless, they still suffer from factual errors when tackling knowledge-intensive tasks.Retrieval-augmented reasoning represents a promising approach.However, significant challenges still persist, including inaccurate a…
Global point clouds that correctly represent the static environment features can facilitate accurate localization and robust path planning. However, dynamic objects introduce undesired <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">‘ghost’</i> track
Compositional neural scene graph studies have shown that radiance fields can be an efficient tool in an editable autonomous driving simulator. However, previous studies learned within a sequence of autonomous driving datasets, resulting in unsatisfactory blurring when rotating the car in the simulat
Collaborative state estimation using different heterogeneous sensors is a fundamental prerequisite for robotic swarms operating in GPS-denied environments, posing a significant research challenge. In this paper, we introduce a centralized system to facilitate collaborative LiDAR-ranging-inertial sta…
Cognitive dynamics, which refer to the evolution in human cognitive processes, are pivotal to advance human understanding of the world. Recent advancements in large language models (LLMs) highlight their potential for cognitive simulation. However, these LLM-based cognitive studies primarily focus o…
Maps provide robots with crucial environmental knowledge, thereby enabling them to perform interactive tasks effectively. Easily accessing accurate abstract-to-detailed geometric and semantic concepts from maps is crucial for robots to make informed and efficient decisions. To comprehensively model…
Multi-modal Named Entity Recognition, a fundamental task for multi-modal knowledge graph construction, requires integrating multi-modal information to extract named entities from text. Previous research has explored the integration of multi-modal representations at different granularities. However,…
Despite recent progress made by large language models in code generation, they still struggle with programs that meet complex requirements. Recent work utilizes plan-and-solve decomposition to decrease the complexity and leverage self-tests to refine the generated program. Yet, planning deep-inside…
Monocular 3D object detection is essential for autonomous driving. However, current monocular 3D detection algorithms rely on expensive 3D labels from LiDAR scans, making it difficult to use in new datasets and unfamiliar environments. This study explores training a monocular 3D object detection mod…
There are substantial instructional videos on the Internet, which provide us tutorials for completing various tasks. Existing instructional video datasets only focus on specific steps at the video level, lacking experiential guidelines at the task level, which can lead to beginners struggling to lea…
Accurate trajectory prediction is crucial for safe and efficient autonomous driving, but handling partial observations presents significant challenges. To address this, we propose a novel trajectory prediction framework called Partial Observations Prediction (POP) for congested urban road scenarios.…
Expanding the understanding capabilities of multi-modal large language models (MLLMs) for infrared modality is a challenge due to the single-modality nature and limited amount of training data. Existing methods typically construct a uniform embedding space for cross-modal alignment and leverage abun…
With the expansion of the scale of robotics applications, the multi-goal multi-agent pathfinding (MG-MAPF) problem began to gain widespread attention. This problem requires each agent to visit pre-assigned multiple goal points at least once without conflict. Some previous methods have been proposed…
Reasoning, a fundamental cognitive process integral to human intelligence, has garnered substantial interest within artificial intelligence.Notably, recent studies have revealed that chain-of-thought prompting significantly enhances LLM’s reasoning capabilities, which attracts widespread attention f…
A Colored point cloud, as a simple and efficient 3D representation, has many advantages in various fields, including robotic navigation and scene reconstruction. This representation is now commonly used in 3D reconstruction tasks relying on cameras and LiDARs. However, fusing data from these two typ…
In proactive dialogue, the challenge lies not just in generating responses but in steering conversations toward predetermined goals, a task where Large Language Models (LLMs) typically struggle due to their reactive nature. Traditional approaches to enhance dialogue planning in LLMs, ranging from el…
LiDAR-based localization is valuable for applications like mining surveys and underground facility maintenance. However, existing methods can struggle when dealing with uninformative geometric structures in challenging scenarios. This paper presents RELEAD, a LiDAR-centric solution designed to addre…
Multi-modal relation extraction (MRE) requires the integration of multi-modal information to identify relationships between entities. Although fine-grained correlations between visual objects and textual words have the potential to improve cross-modal interaction, they are typically modeled implicit…
In recent years, imitation-based driving planners have reported considerable success. However, due to the absence of a standardized benchmark, the effectiveness of various designs remains unclear. The newly released nuPlan addresses this issue by offering a large-scale real-world dataset and a stand…
Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications. Moreover, the degree of redundancy in token representations…
With the popularity of large language models (LLMs) and their ability to handle longer input documents, there is a growing need for high-quality long document summarization datasets. Although many models already support 16k input, current lengths of summarization datasets are inadequate, and salient…
Grasping the concept of time is a fundamental facet of human cognition, indispensable for truly comprehending the intricacies of the world.Previous studies typically focus on specific aspects of time, lacking a comprehensive temporal reasoning benchmark.To address this, we propose TimeBench, a compr…
Situational awareness refers to the capacity to perceive and comprehend the present context and anticipate forthcoming events, which plays a critical role in aiding decision-making, anticipating potential issues, and adapting to dynamic circumstances. Nevertheless, the situational awareness capabili…
Adversarial robustness, domain generalization and dataset biases are three active lines of research contributing to out-of-distribution (OOD) evaluation on neural NLP models. However, a comprehensive, integrated discussion of the three research lines is still lacking in the literature. This surve…
For improving image composition and aesthetic quality, most existing methods modulate the captured images by striking out redundant content near the image borders. However, such image cropping methods are limited in the range of image views. Some methods have been suggested to extrapolate the images…
Parameter-efficient fine-tuning (PEFT) methods have provided an effective way for adapting large vision-language models to specific tasks or scenarios. Typically, they learn a very small scale of parameters for pre-trained models in a white-box formulation, which assumes model architectures to be kn…
With the fast development of autonomous driving technologies, there is an increasing demand for high-definition (HD) maps, which provide reliable and robust prior information about the static part of the traffic environments. As one of the important elements in HD maps, road lane centerline is criti…
Maintaining balance during gait in the mediolateral direction requires more active motor control than in the anteroposterior direction. Step width modulation is a key strategy used by healthy individuals to achieve mediolateral walking balance, but it can be disrupted in populations with poor sensor…
The rotation orthonormalization on the special orthogonal group \text{SO}(n)\text{SO}(n), also known as the high dimensional nearest rotation problem, has been revisited. A new generalized simple iterative formula has been proposed that solves this problem in a completely rational manner. Rational o…
Surface normal holds significant importance in visual environmental perception, serving as a source of rich geometric information. However, the state-of-the-art (SoTA) surface normal estimators (SNEs) generally suffer from an unsatisfactory trade-off between efficiency and accuracy. To resolve this…
Robotic prosthetic legs have the potential to significantly improve the quality of life for lower limb amputees to perform locomotion in various environments and task conditions. However, these devices lack the capability to recover from internal intrinsic control faults, which can lead to harmful c…
Understanding the relationships between items can improve the accuracy and interpretability of recommender systems. Among these relationships, the substitute and complement relationships attract the most attention in e-commerce platforms. The substitutable items are interchangeable and might be comp…
This paper proposes a novel real-time semantic segmentation network via frequency domain learning, called FDLNet, which revisits the segmentation task from two critical perspectives: spatial structure description and multilevel feature fusion. We first devise an image-size convolution (IS-Conv) as a…
This study explores the application of self-supervised learning (SSL) to the task of motion forecasting, an area that has not yet been extensively investigated despite the widespread success of SSL in computer vision and natural language processing. To address this gap, we introduce Forecast-MAE, an…
Dynamic scene graph generation aims to identify visual relationships (subject-predicate-object) in frames based on spatio-temporal contextual information in the video. Previous work implicitly models the spatio-temporal interaction simultaneously, which leads to entanglement of spatio-temporal conte…
How to generate the ground-truth (GT) image is a critical issue for training realistic image super-resolution (Real-ISR) models. Existing methods mostly take a set of high-resolution (HR) images as GTs and apply various degradations to simulate their low-resolution (LR) counterparts. Though great pr…
The facts and time in the document are intricately intertwined, making temporal reasoning over documents challenging. Previous work models time implicitly, making it difficult to handle such complex relationships. To address this issue, we propose MTGER, a novel Multi-view Temporal Graph Enhanced Re…
Due to their highly structured characteristics, faces are easier to recover than natural scenes for blind image super-resolution. Therefore, we can extract the degradation representation of an image from the low-quality and recovered face pairs. Using the degradation representation, realistic low-qu…
Although deep neural networks have achieved astonishing performance in many vision tasks, existing learning-based methods are far inferior to the physical model-based solutions in extreme low-light sensor noise modeling. To tap the potential of learning-based sensor noise modeling, we investigate th…
The road network graph is a critical component for downstream tasks in autonomous driving, such as global route planning and navigation. In the past years, road network graphs are usually annotated by human experts manually, which is time-consuming and labor-intensive. To annotate road network graph
Having good knowledge of terrain information is essential for improving the performance of various downstream tasks on complex terrains, especially for the locomotion and navigation of legged robots. We present a novel framework for neural urban terrain reconstruction with uncertainty estimations. I
Drivable area segmentation is an essential component of the visual perception system for autonomous driving vehicles. Recent efforts in deep neural networks have sig-nificantly improved semantic segmentation performance for autonomous driving. However, most DNN-based methods need a large amount of d…
As an abstract representation of the environment structure, a topological map has advantageous properties for path-planning and navigation. Here we proposed an online topological mapping method, 360ST-Mapping, using omnidirectional vision. The 360° field-of-view allows the agent to obtain consistent…
Robot navigation in human crowds remains the challenge of understanding human behaviors in different scenarios. We present an approach for interactive and human-friendly crowd navigation in complex static environments. The planner models the online interactions among the robot, humans, and the stati…
The physical interactions between wearable lower limb robots and humans have been investigated to inform effective robot design for walking augmentation. However, human-robot interactions when internal faults occur within robots have not been systematically reported, but it is essential to improve t
The corresponding author of this letter [1] is Lujia Wang, not Sukai Wang.
Generative Adversarial Networks(GANs) are powerful generative models on numerous tasks and datasets but are also known for their training instability and mode collapse. The latter is because the optimal transportation map is discontinuous, but DNNs can only approximate continuous ones. One way to so…
Existing robotic lower-limb prostheses use autonomous control to address cyclic, locomotive tasks, but are inadequate in adapting to variations in non-cyclic and unpredictable tasks. This study aims to address this challenge by designing a novel electromyography (EMG)-driven musculoskeletal model fo…
On vision-language understanding (VLU) tasks, fusion-encoder vision-language models achieve superior results but sacrifice efficiency because of the simultaneous encoding of images and text. On the contrary, the dual encoder model that separately encodes images and text has the advantage in efficien…
Safely interacting with other traffic participants is one of the core requirements for autonomous driving, especially in intersections and occlusions. Most existing approaches are designed for particular scenarios and require significant human labor in parameter tuning to be applied to different sit
Combining multiple sensors enables a robot to maximize its perceptual awareness of environments and enhance its robustness to external disturbance, crucial to robotic navigation. This paper proposes the FusionPortable benchmark, a complete multi-sensor dataset with a diverse set of sequences for mob…
Pedestrian trajectory prediction is of great importance for downstream tasks, such as autonomous driving and mobile robot navigation. Realistic models of the social interactions within the crowd is crucial for accurate pedestrian trajectory prediction. However, most existing methods do not capture g…
Real-time semantic segmentation is a crucial but challenging dense prediction task for scene parsing. However, the existing CNN-based methods commonly bias the model in favor of speed-boosting compromising spatial resolution due to business requirements and hardware constrains, which impedes the hig…
Abstractive summarization has made tremendous progress in recent years. In this work, we perform fine-grained human annotations to evaluate long document abstractive summarization systems (i.e., models and metrics) with the aim of implementing them to generate reliable summaries. For long document a…
Understanding the uncertainty of predictions is a desirable feature for perceptual modules in critical robotic applications. 3D object detectors are neural networks with high-dimensional output space. It suffers from poor calibration in classification and lacks reliable uncertainty estimation in reg…
Our goal is to train a neural planner that can capture diverse driving behaviors in complex urban scenarios. We observe that even state-of-the-art neural planners are struggling to perform common maneuvers such as lane change, which is rather natural for human drivers. We propose to explore the mult…
"Classical LIDAR semantic segmentation is not robust for real-world applications, e.g., autonomous driving, since it is closed-set and static. The closed-set network is only able to output labels of trained classes, even for objects never seen before, while a static network cannot update its knowled…
"For autonomous driving systems, the storage cost and transmission speed of the large-scale point clouds become an important bottleneck because of their large volume. In this paper, we propose a range image-based three-stage framework to compress the scanning LiDAR’s point clouds using the entropy m…
Real-time kinodynamic trajectory planning in dy-namic environments is critical yet challenging for autonomous driving. In this paper, we propose an efficient trajectory plan-ning system for autonomous driving in complex dynamic sce-narios through iterative and incremental path-speed optimization. Ex…
When taking photos under an environment with insufficient light, the exposure time and the sensor gain usually require to be carefully chosen to obtain images with satisfying visual quality. For example, the images with high ISO usually have inescapable noise, while the long-exposure ones may be blu…
3D object detection with only image inputs is an interesting and important problem in computer vision and autonomous driving. Nowadays, most existing monocular 3D object detection algorithms rely solely on the approximation power of convolutional neural networks to learn a mapping from pixels to 3D…
Disparity and optical flow estimation are respectively 1D and 2D dense correspondence matching (DCM) tasks in nature. Unsupervised domain adaptation (UDA) is crucial for their success in new and unseen scenarios, enabling networks to draw inferences across different domains without manually-labeled…
Deep learning-based image retrieval techniques for the loop closure detection demonstrate satisfactory performance. However, it is still challenging to achieve high-level performance based on previously trained models in different geographical regions. This letter addresses the problem of their depl
High-Definition (HD) maps can provide precise geometric and semantic information of static traffic environments for autonomous driving. Road-boundary is one important information presented in HD maps since it distinguishes between road areas and off-road areas, which can guide vehicles to drive with
In this paper, we introduce a method for visual relocalization using the geometric information from a 3D surfel map. A visual database is first built by global indices from the 3D surfel map rendering, which provides associations between image points and 3D surfels. Surfel reprojection constraints a…
Robotic exoskeletons are exciting technologies for augmenting human mobility. However, designing such a device for seamless integration with the human user and to assist human movement still is a major challenge. This paper aims at developing a novel data-driven solution framework based on reinforce…
Ankle joints play key roles in everyday locomotion, such as walking, stair climbing, and sit-to-stand. Despite the achievement in designing powered prosthetic ankles, engineers still face challenges to duplicate the full mechanics of ankle joints, including high torque, large range of motion (ROM),…
Pedestrian trajectory prediction is a critical yet challenging task especially for crowded scenes. We suggest that introducing an attention mechanism to infer the importance of different neighbors is critical for accurate trajectory prediction in scenes with varying crowd size. In this work, we prop…
We present a simple, effective, and general activation function we term ACON which learns to activate the neurons or not. Interestingly, we find Swish, the recent popular NAS-searched activation, can be interpreted as a smooth approximation to ReLU. Intuitively, in the same way, we approximate the m…
Road curb detection is important for autonomous driving. It can be used to determine road boundaries to constrain vehicles on roads, so that potential accidents could be avoided. Most of the current methods detect road curbs online using vehicle-mounted sensors, such as cameras or 3-D Lidars. Howeve…
Classical close-set semantic segmentation networks have limited ability to detect out-of-distribution (OOD) objects, which is important for safety-critical applications such as autonomous driving. Incrementally learning these OOD objects with few annotations is an ideal way to enlarge the knowledge…
Traditional decision and planning frameworks for self-driving vehicles (SDVs) scale poorly in new scenarios, thus they require tedious hand-tuning of rules and parameters to maintain acceptable performance in all foreseeable cases. Recently, self-driving methods based on deep learning have shown pro…
End-to-end 3D object detection and tracking based on point clouds is receiving more and more attention in many robotics applications, such as autonomous driving. Compared with 2D images, 3D point clouds do not have enough texture information for data association. Thus, we propose an end-to-end point
A novel 3-dimensional (3-D) alignment method for point-cloud registration is proposed where the time-differential information of the measured points is employed. The new problem turns out to be a novel multi-dimensional optimization. Analytical solution to this optimization is then obtained, which s…
Modern LiDAR-SLAM (L-SLAM) systems have shown excellent results in large-scale, real-world scenarios. However, they commonly have a high latency due to the expensive data association and nonlinear optimization. This paper demonstrates that actively selecting a subset of features significantly improv…
Estimating the 3D position and orientation of objects in the environment with a single RGB camera is a critical and challenging task for low-cost urban autonomous driving and mobile robots. Most of the existing algorithms are based on the geometric constraints in 2D-3D correspondence, which stems fr
Making robots learn skills incrementally is an efficient way to design real intelligent agents. To achieve this, researchers adopt knowledge distillation to transfer old-task knowledge from old models to new ones. However, when the length of the task sequence increases, the effectiveness of knowledg
Recently, deep-learning based approaches have achieved impressive performance for autonomous driving. However, end-to-end vision-based methods typically have limited interpretability, making the behaviors of the deep networks difficult to explain. Hence, their potential applications could be limited…
Learning RAW-to-sRGB mapping has drawn increasing attention in recent years, wherein an input raw image is trained to imitate the target sRGB image captured by another camera. However, the severe color inconsistency makes it very challenging to generate well-aligned training pairs of input raw and t…
In this paper, we propose a simple few-shot domain adaptation paradigm for reading comprehension. We first identify the lottery subnetwork structure within the Transformer-based source domain model via gradual magnitude pruning. Then, we only fine-tune the lottery subnetwork, a small fraction of the…
This paper presents an unsupervised extractive approach to summarize scientific long documents based on the Information Bottleneck principle. Inspired by previous work which uses the Information Bottleneck principle for sentence compression, we extend it to document level summarization with two sepa…
Neural topic models (NTMs) apply deep neural networks to topic modelling. Despite their success, NTMs generally ignore two important aspects: (1) only document-level word count information is utilized for the training, while more fine-grained sentence-level information is ignored, and (2) external s…
Multiview registration is used to estimate Rigid Body Transformations (RBTs) from multiple frames and reconstruct a scene with corresponding scans. Despite the success of pairwise registration and pose synchronization, the concept of Bundle Adjustment (BA) has been proven to better maintain global c
Supervised learning with deep convolutional neural networks (DCNNs) has seen huge adoption in stereo matching. However, the acquisition of large-scale datasets with well-labeled ground truth is cumbersome and labor-intensive, making supervised learning-based approaches often hard to implement in pra
Moving-obstacle segmentation is an essential capability for autonomous driving. For example, it can serve as a fundamental component for motion planning in dynamic traffic environments. Most of the current 3-D Lidar-based methods use road segmentation to find obstacles, and then employ ego-motion co
Navigation on challenging terrain topographies requires the understanding of robots’ locomotion capabilities to produce optimal solutions. We present an integrated framework for real-time autonomous navigation of mobile robots based on elevation maps. The framework performs rapid global path plannin…
Path planning is a fundamental capability for autonomous navigation of robotic wheelchairs. With the impressive development of deep-learning technologies, imitation learning-based path planning approaches have achieved effective results in recent years. However, the disadvantages of these approaches…
Freespace detection is a fundamental component of autonomous driving perception. Recently, deep convolutional neural networks (DCNNs) have achieved impressive performance for this task. In particular, SNE-RoadSeg, our previously proposed method based on a surface normal estimator (SNE) and a data-fu…
This letter proposes three-filters-to-normal (3F2N), an accurate and ultrafast surface normal estimator (SNE), which is designed for structured range sensor data, e.g., depth/disparity images. 3F2N SNE computes surface normals by simply performing three filtering operations (two image gradient filte
Road-boundary detection is important for autonomous driving. It can be used to constrain autonomous vehicles running on road areas to ensure driving safety. Compared with online road-boundary detection using on-vehicle cameras/Lidars, offline detection using aerial images could alleviate the severe
This paper proposes a transformer over transformer framework, called Transformerˆ2, to perform neural text segmentation. It consists of two components: bottom-level sentence encoders using pre-trained transformers, and an upper-level transformer-based segmentation model based on the sentence embeddi…
The tuning process for a robotic prosthesis is a challenging and time-consuming task both for users and clinicians. An automatic tuning approach using reinforcement learning (RL) has been developed for a knee prosthesis to address the challenges of manual tuning methods. The algorithm tunes the opti…
Autonomous car racing is a challenging task in the robotic control area. Traditional modular methods require accurate mapping, localization and planning, which makes them computationally inefficient and sensitive to environmental changes. Recently, deep-learning-based end-to-end systems have shown p
Object detection in 3D with stereo cameras is an important problem in computer vision, and is particularly crucial in low-cost autonomous mobile robots without LiDARs. Nowadays, most of the best-performing frameworks for stereo 3D object detection are based on dense depth reconstruction from dispari…
Detection of road curbs is an essential capability for autonomous driving. It can be used for autonomous vehicles to determine drivable areas on roads. Usually, road curbs are detected on-line using vehicle-mounted sensors, such as video cameras and 3-D Lidars. However, on-line detection using video
In this letter, we propose a novel coding architecture for LiDAR point cloud sequences based on clustering and prediction neural networks. LiDAR point clouds are structured, which provides an opportunity to convert the 3D data to a 2D array, represented as range images. Thus, we cast the LiDAR point
Lightweight global localization is favorable by many resource-constrained platforms working in GPS-denied indoor environments, such as service robots and mobile devices. In recent years, visible light communication (VLC) has emerged as a promising technology that can support global positioning in bu
Online knowledge distillation has attracted increasing interest recently, which jointly learns teacher and student models or an ensemble of student models simultaneously and collaboratively. On the other hand, existing works focus more on outcome-driven learning according to knowledge like classific…
The joint detection of drivable areas and road anomalies is a crucial task for ground mobile robots. In recent years, many impressive semantic segmentation networks, which can be used for pixel-level drivable area and road anomaly detection, have been developed. However, the detection accuracy still…
The interpretation of ego motion and scene change is a fundamental task for mobile robots. Optical flow information can be employed to estimate motion in the surroundings. Recently, unsupervised optical flow estimation has become a research hotspot. However, unsupervised approaches are often easy to
Cable-driven robotic manipulators are desirable for medical applications, for their form factor flexibility after separating actuation from the distal end. However, intended to work under high spatial constraints such as dental or other surgical applications, severe cable elongations will raise cont
Humans are capable of learning a new behavior by observing others to perform the skill. Similarly, robots can also implement this by imitation learning. Furthermore, if with external guidance, humans can master the new behavior more efficiently. So, how can robots achieve this? To address the issue,
Incorporating prior structure information into the visual state estimation could generally improve the localization performance. In this letter, we aim to address the paradox between accuracy and efficiency in coupling visual factors with structure constraints. To this end, we present a cross-modali
Drifting is a complicated task for autonomous vehicle control. Most traditional methods in this area are based on motion equations derived by the understanding of vehicle dynamics, which is difficult to be modeled precisely. We propose a robust drift controller without explicit motion equations, whi
We present LINS, a lightweight lidar-inertial state estimator, for real-time ego-motion estimation. The proposed method enables robust and efficient navigation for ground vehicles in challenging environments, such as feature-less scenes, via fusing a 6-axis IMU and a 3D lidar in a tightly-coupled sc…
Despite recent advances in deep learning-based face frontalization methods, photo-realistic and illumination preserving frontal face synthesis is still challenging due to large pose and illumination discrepancy during training. We propose a novel Flow-based Feature Warping Model (FFWM) which can lea…
Extrinsic perturbation always exists in multiple sensors. In this paper, we focus on the extrinsic uncertainty in multi-LiDAR systems for 3D object detection. We first analyze the influence of extrinsic perturbation on geometric tasks with two basic examples. To minimize the detrimental effect of ex…
Research into the area of multiparty dialog has grown considerably over recent years. We present the Molweni dataset, a machine reading comprehension (MRC) dataset with discourse structure built over multiparty dialog. Molweni’s source samples from the Ubuntu Chat Corpus, including 10,000 dialogs co…
In this paper, we introduce an approach to tracking the pose of a monocular camera in a prior surfel map. By rendering vertex and normal maps from the prior surfel map, the global planar information for the sparse tracked points in the image frame is obtained. The tracked points with and without the…
Robustness and accuracy for monocular visual odometry (VO) under challenging environments are widely concerned. In this paper, we present a monocular VO system leveraging learned repeatability and description. In a hybrid scheme, the camera pose is initially tracked on the predicted repeatability ma…
Recent machine learning-based multi-object tracking (MOT) frameworks are becoming popular for 3-D point clouds. Most traditional tracking approaches use filters (e.g., Kalman filter or particle filter) to predict object locations in a time sequence, however, they are vulnerable to extreme motion con
All-day and all-weather navigation is a critical capability for autonomous driving, which requires proper reaction to varied environmental conditions and complex agent behaviors. Recently, with the rise of deep learning, end-to-end control for autonomous vehicles has been well studied. However, most
In this paper, we explore the limits of Microsoft Floating Point (MSFP), a new class of datatypes developed for production cloud-scale inferencing on custom hardware. Through the co-evolution of hardware design and algorithms, MSFP achieves accuracy comparable to or better than industry standards Bf…
Safe and efficient crowd navigation for mobile robot is a crucial yet challenging task. Previous work has shown the power of deep reinforcement learning frameworks to train efficient policies. However, their performance deteriorates when the crowd size grows. We suggest that this can be addressed by
In this paper, we address the issue of pedestrian tracking in crowd scenarios. People in close social relationships tend to act as a group which is a great challenge to individually discriminate and track pedestrians on a LiDAR system. In this paper, we integrally model groups of people and track th…
Freespace detection is an essential component of visual perception for self-driving cars. The recent efforts made in data-fusion convolutional neural networks (CNNs) have significantly improved semantic driving scene segmentation. Freespace can be hypothesized as a ground plane, on which the points…
Ego-vehicle trajectory prediction is important for autonomous vehicles to detect collisions and accordingly avoid accidents. Recent approaches employ prior-known or on-line acquired road topology or geometries as motion constraints for their predictive models. However, the prior-known information (e
The presence of any type of defect on the glass screen of smart devices has a great impact on their quality. We present a robust semi-supervised learning framework for intelligent micro-scaled localization and classification of defects on a 16K pixel image of smartphone glass. Our model features the…
We investigate the task of learning blind image denoising networks from an unpaired set of clean and noisy images. Such problem setting generally is practical and valuable considering that it is feasible to collect unpaired noisy and clean images in most real-world applications. And we further assum…
The visual-inertial navigation system (VINS) has been a practical approach for state estimation in recent years. In this paper, we propose a general GPS-aided omnidirectional visual-inertial state estimator capable of operating in ubiquitous environments and platforms. Our system consists of two par…
Due to the enormous volume of point cloud data, transmitting and storing the data requires large bandwidth and storage space. It could be a critical bottleneck, especially in tasks such as autonomous driving. In this letter, we propose a novel point cloud compression algorithm based on clustering. T
Multiple LiDARs have progressively emerged on autonomous vehicles for rendering a rich view and dense measurements. However, the lack of precise calibration negatively affects their potential applications. In this paper, we propose a novel system that enables automatic multi-LiDAR calibration method…
3D object detection is still an open problem in autonomous driving scenes. When recognizing and localizing key objects from sparse 3D inputs, autonomous vehicles suffer from a larger continuous searching space and higher fore-background imbalance compared to image-based object detection. In this let
Imitation learning by behavioral cloning is a prevalent method that has achieved some success in vision-based autonomous driving. The basic idea behind behavioral cloning is to have the neural network learn from observing a human expert's behavior. Typically, a convolutional neural network learns to…
This paper was motivated by the problem of how to make robots fuse and transfer their experience so that they can effectively use prior knowledge and quickly adapt to new environments. To address the problem, we present a learning architecture for navigation in cloud robotic systems: Lifelong Federa…
This letter was motivated by the problem of how to make robots fuse and transfer their experience so that they can effectively use prior knowledge and quickly adapt to new environments. To address the problem, we present a learning architecture for navigation in cloud robotic systems: Lifelong Feder
Metric localization plays a critical role in vision-based navigation. For overcoming the degradation of matching photometry under appearance changes, recent research resorted to introducing geometry constraints of the prior scene structure. In this paper, we present a metric localization method for…
Semantic segmentation is a fundamental capability for autonomous vehicles. With the advancements of deep learning technologies, many effective semantic segmentation networks have been proposed in recent years. However, most of them are designed using RGB images from visible cameras. The quality of R
Arbitrary attribute editing generally can be tackled by incorporating encoder-decoder and generative adversarial networks. However, the bottleneck layer in encoder-decoder usually gives rise to blurry and low quality editing result. And adding skip connections improves image quality at the cost of w…
The segmentation of drivable areas and road anomalies are critical capabilities to achieve autonomous navigation for robotic wheelchairs. The recent progress of semantic segmentation using deep learning techniques has presented effective results. However, the acquisition of large-scale datasets with
Ego-motion estimation is a fundamental requirement for most mobile robotic applications. By sensor fusion, we can compensate the deficiencies of stand-alone sensors and provide more reliable estimations. We introduce a tightly coupled lidar-IMU fusion method in this paper. By jointly minimizing the…
The detection of curved lanes is still challenging for autonomous driving systems. Although current cutting-edge approaches have performed well in real applications, most of them are based on strict model assumptions. Similar to other visual recognition tasks, lane detection can be formulated as a t…
In this letter, we deal with the reality gap from a novel perspective, targeting transferring deep reinforcement learning (DRL) policies learned in simulated environments to the real-world domain for visual control tasks. Instead of adopting the common solutions to the problem by increasing the visu
End-to-end visual-based imitation learning has been widely applied in autonomous driving. When deploying the trained visual-based driving policy, a deterministic command is usually directly applied without considering the uncertainty of the input data. Such kind of policies may bring dramatical dama…
Indoor localization for pedestrians has gained increasing popularity among the rich body of literature for the last decade. In this paper, a low-cost indoor mapping and localization solution is proposed using the opportunistic signals from ambient indoor environments with a smartphone. It is compose…
This paper studies the problem of blind face restoration from an unconstrained blurry, noisy, low-resolution, or compressed image (i.e., degraded observation). For better recovery of fine facial details, we modify the problem setting by taking both the degraded observation and a high-quality guided…
Indoor localization is critical to many location-aware applications, however, a low-cost solution with guaranteed accuracies has not yet come. Visible Light Communication (VLC-) based localization techniques are very promising to fill this gap. In this paper, we propose Plugo, a novel VLC system wit…
We present an approach for mobile robots to learn to navigate in dynamic environments with pedestrians via raw depth inputs, in a socially compliant manner. To achieve this, we adopt a generative adversarial imitation learning (GAIL) strategy, which improves upon a pre-trained behavior cloning polic…
This paper studies the problem of image-based leader-follower formation control for mobile robots, where the controller is designed independently of the leader's motion. An adaptive control scheme, which is suitable for both omnidirectional and perspective cameras, is proposed. The proposed approach…
We present a learning-based mapless motion planner by taking the sparse 10-dimensional range findings and the target position with respect to the mobile robot coordinate frame as input and the continuous steering commands as output. Traditional motion planners for mobile ground robots with a laser r…
Obstacle avoidance is the core problem for mobile robots. Its objective is to allow mobile robots to explore an unknown environment without colliding into other objects. It is the basis for various tasks, e.g. surveillance and rescue, etc. Previous approaches mainly focused on geometric models (such…
Indoor localization is a fundamental capability for service robots and indoor applications on mobile devices. To realize that, the cost and performance are of great concern. In this paper, we introduce a lightweight signal encoding and decomposition method for a low-cost and low-power Visible Light…
For mobile robots and position-based services, such as healthcare service, precise localization is the most fundamental capability while low-cost localization solutions are with increasing need and potentially have a wide market. A low-cost localization solution based on a novel Visible Light Commun…