79 accepted papers
While reasoning technology like Chain-of-Thought (CoT) has been widely adopted in Vision-Language-Action (VLA) models, it demonstrates promising capabilities in end-to-end autonomous driving. However, recent efforts to integrate CoT reasoning often fall short in simple scenarios, introducing unneces…
Event cameras capture asynchronous pixel-level brightness changes with microsecond temporal resolution, offering unique advantages for high-speed vision tasks. Existing methods often convert event streams into intermediate representations such as frames, voxel grids, or point clouds, which inevitabl…
Accurate feature matching between image pairs is fundamental for various computer vision applications. In detector-base process, the feature matcher aims to find the optimal feature correspondences, and the match filter is used for further removing mismatches. However, their connection is rarely exp
Autonomous driving needs fast, scalable 4D reconstruction and re-simulation for training and evaluation, yet most methods for dynamic driving scenes still rely on per-scene optimization, known camera calibration, or short frame windows, making them slow and impractical. We revisit this problem from
Recently, the prominent performance of large language models (LLMs) has been largely driven by multi-task instruct-tuning. Unfortunately, this training paradigm suffers from a key issue, named cross-task interference, due to conflicting gradients over shared parameters among different tasks. Some pr…
World models have become crucial for autonomous driving, as they learn how scenarios evolve over time to address the long-tail challenges of the real world. However, current approaches relegate world models to limited roles: they operate within ostensibly unified architectures that still keep world
Text-to-image diffusion models have achieved remarkable progress, generating visually realistic and semantically coherent images from textual prompts. However, natural language alone lacks the precision required for design-centric applications that demand strict spatial and structural fidelity--part
Multimodal Misinformation Detection (MMD) refers to the task of detecting social media posts involving misinformation, where the post often contains text and image modalities. However, by observing the MMD posts, we hold that the text modality may be much more informative than the image modality bec
Keypoint-based matching is a fundamental component of modern 3D vision systems, such as Structure-from-Motion (SfM) and SLAM. Most existing learning-based methods are trained on image pairs, a paradigm that fails to explicitly optimize for the long-term trackability of keypoints across sequences und
Parking is a critical task for autonomous driving systems (ADS), with unique challenges in crowded parking slots and GPS-denied environments. However, existing works focus on 2D parking slot perception, mapping, and localization, 3D reconstruction remains underexplored, which is crucial for capturin
Time series forecasting (TSF) refers to a fundamental task of predicting future sequential data based on historical observations. One representative category of TSF methods is transformer-based approaches, which translate time series into token sequences (i.e., as raw texts) before applying well-est
We present PhysInOne, a large-scale synthetic dataset addressing the critical scarcity of physically-grounded training data for AI systems. Unlike existing datasets limited to merely hundreds or thousands of examples, PhysInOne provides 2 million videos across 153,810 dynamic 3D scenes, covering 71
The increasing demand for real-time interaction in online video scenarios necessitates a new class of efficient streaming video understanding models. However, existing approaches often rely on a flawed, query-agnostic ``change-is-important'' principle, which conflates visual dynamics with semantic r…
Relative spatial relations provide a compact description of spatial structure, serving as a key component of relative spatial reasoning in 3D layout generation. Recent works leverage Multimodal Large Language Models (MLLMs) to infer these relations, but the inferred relations are often unreliable an…
Recent studies have explored leveraging the world knowledge and cognitive capabilities of Vision-Language Models (VLMs) to address the long-tail problem in end-to-end autonomous driving. However, existing methods typically formulate trajectory planning as a language modeling task, where physical act…
Recent advancements in driving world models enable controllable generation of high-quality RGB videos or multimodal videos. Existing methods primarily focus on metrics related to generation quality and controllability. However, they often overlook the evaluation of downstream perception tasks, whi…
Self-attention with separate pre- and post-projections can be a universal approximator (on compact domains) under mild conditions. Yet we observe a striking gap: an attention-only Transformer (w/o FFN layers) exhibits a marked accuracy drop relative to its standard interleaved attention--FFN baselin
Neural networks necessitate nonlinearities to achieve universal approximability. Traditional activation functions introduce nonlinearities through rigid feature rectifications. Recent self-gated variants improve traditional methods in fitting flexibility by incorporating learnable content-aware fact…
Dynamic driving scene modeling is critical for autonomous driving simulation and closed-loop learning. While recent feed-forward methods offer fast inference through data-driven priors, they struggle with long-range driving sequences due to quadratic complexity in sequence length and restrictive ass
Large reasoning models (LRMs) achieve remarkable reasoning performance by generating long chains-of-thought (CoT). However, standard supervised fine-tuning (SFT) treats all tokens uniformly, indiscriminately minimizing loss across both essential reasoning steps and those that are noisy, redundant, o…
Learning discriminative point-wise representations remains the central challenge in scene-level, correspondence-based point cloud registration. Most existing methods process two frames independently during the early stage and introduce cross-frame interaction only at coarsest stages. Such delayed in
The safe deployment of autonomous driving (AD) systems is fundamentally hindered by the long-tail problem, where rare yet critical driving scenarios are severely underrepresented in real-world data. Existing solutions including safety-critical scenario generation and closed-loop learning often rely
Reasoning distillation, a cost-effective approach for enhancing student model performance, has attracted increasing attention. It typically leverages a large teacher model to generate reasoning paths, which are then used to fine-tune a student model so that it mimics the teacher's behavior in traini…
Recent advances in driving-scene generation and reconstruction have demonstrated significant potential for enhancing autonomous driving systems by producing scalable and controllable training data. Existing generation methods primarily focus on synthesizing diverse and high-fidelity driving videos;…
Underwater localization is a crucial capability for ensuring robust and accurate vehicle navigation. Although various well-developed localization systems exist, their primary focus is on ground and aerial applications. The challenges posed by underwater environments, such as sparse textures and dyna
Positive and Unlabeled (PU) learning is a special case of binary classification with weak supervision, where only positive labeled and unlabeled data are available. Previous studies suggest several specific risk estimators of PU learning such as non-negative PU (nnPU), which are unbiased and consist…
We present Genesis, a unified world model for joint generation of multi-view driving videos and LiDAR sequences with spatio-temporal and cross-modal consistency. Genesis employs a two-stage architecture that integrates a DiT-based video diffusion model with 3D-VAE encoding, and a BEV-represented LiD…
Despite significant progress in Video Large Language Models (Video-LLMs) for offline video understanding, existing online Video-LLMs typically struggle to simultaneously process continuous frame-by-frame inputs and determine optimal response timing, often compromising real-time responsiveness and na…
Recent LLM-based Text-to-SQL methods usually suffer from significant performance degradation on “huge” databases and complex user questions that require multi-step reasoning. Moreover, most existing methods neglect the crucial significance of LLMs utilizing external tools and model collaboration. To…
Humans perceive the world through multimodal cues to understand and interact with the environment. Learning a scene representation for multiple modalities enhances comprehension of the physical world. However, modality conflicts, arising from inherent distinctions among different modalities, present…
Despite significant advances in 3D human pose estimation from a single-view video, existing methods often struggle to produce reasonable human poses when the human is heavily occluded or blurred. To address this issue, we propose a Mixed Spectral and Attention Network (MSANet) that stacks spectral a…
Mamba, a selective state-space model, has recently seen widespread application across various visual tasks due to its exceptional ability to capture long-range dependencies. While promising results have been demonstrated in image classification, its potential in multi-label image classification rema…
Code large language models (LLMs) have shown remarkable advances in code understanding, completion, and generation tasks. Programming benchmarks, comprised of a selection of code challenges and corresponding test cases, serve as a standard to evaluate the capability of different LLMs in such tasks.…
Due to the interference of background noise, existing video anomaly detection methods are prone to detect some normal events in complex scenes as anomalies. Meanwhile, we note that the diversity of normal patterns has not been adequately considered, i.e., the normal events that are worthy of referen…
Surface normal estimation serves as a cornerstone for a spectrum of computer vision applications. While numerous efforts have been devoted to static image scenarios, ensuring temporal coherence in video-based normal estimation remains a formidable challenge. Instead of merely augmenting existing met…
End-to-end (E2E) autonomous driving methods still struggle to make correct decisions in interactive closed-loop evaluation due to limited causal reasoning capability. Current methods attempt to leverage the powerful understanding and reasoning abilities of Vision-Language Models (VLMs) to resolve th…
This paper presents **Pixel-Perfect Depth**, a monocular depth estimation model based on pixel-space diffusion generation that produces high-quality, flying-pixel-free point clouds from estimated depth maps. Current generative depth estimation models fine-tune Stable Diffusion and achieve impressive…
The development of Internet technology has led to an increased prevalence of misinformation, causing severe negative effects across diverse domains. To mitigate this challenge, Misinformation Detection (MD), aiming to detect online misinformation automatically, emerges as a rapidly growing research
Cross-Domain Recommendation (CDR) leverages additional knowledge from auxiliary domains to address the long-standing data sparsity issue. However, existing methods typically acquire this knowledge by minimizing the average loss over all domains, overlooking the fact that different domains possess di…
With the rapid advancement of large language models (LLMs), recent researchers have increasingly focused on the superior capabilities of LLMs in text/code understanding and generation to tackle text-to-SQL tasks. Traditional approaches adopt schema linking to first eliminate redundant tables and col…
Chain-of-thought (CoT) has emerged as a powerful technique to elicit reasoning in large language models and improve a variety of downstream tasks. CoT mainly demonstrates excellent performance in English, but its usage in low-resource languages is constrained due to poor language generalization. To…
Aspect-based sentiment analysis (ABSA), a fine-grained sentiment classification task, has received much attention recently. Many works investigate sentiment information through opinion words, such as "good'' and "bad''. However, implicit sentiment data widely exists in the ABSA dataset, whose sentim…
Matching cross-modality features between images and point clouds is a fundamental problem for image-to-point cloud registration. However, due to the modality difference between images and points, it is difficult to learn robust and discriminative cross-modality features by existing metric learning m…
Tracking and catching moving objects is an important ability for robots in a dynamic world. Whilst some objects have highly predictable state evolution e.g., the ballistic trajectory of a tennis ball, reactive targets alter their behavior in response to motion of the manipulator. Reactive applicatio…
Projection-free online learning has drawn increasing interest due to its efficiency in solving high-dimensional problems with complicated constraints. However, most existing projection-free online methods focus on minimizing the static regret, which unfortunately fails to capture the challenge of ch…
The relationship between various objects in real life is very important and universal. However, existing object detection models, especially Two-stage models, mostly rely solely on instance learning of individual objects, which use limited global information to extract regions of interest and neglec…
Positive and Unlabeled (PU) learning refers to a special case of binary classification, and technically, it aims to induce a binary classifier from a few labeled positive training instances and loads of unlabeled instances. In this paper, we derive a theorem indicating that the probability boundary…
3D occupancy prediction holds significant promise in the fields of robot perception and autonomous driving, which quantifies 3D scenes into grid cells with semantic labels. Recent works mainly utilize complete occupancy labels in 3D voxel space for supervision. However, the expensive annotation proc…
Vision-centric 3D environment understanding is both vital and challenging for autonomous driving systems. Recently object-free methods have attracted considerable attention. Such methods perceive the world by predicting the semantics of discrete voxel grids but fail to construct continuous and accur…
Intermediate reasoning or acting steps have successfully improved large language models (LLMs) for handling various downstream natural language processing (NLP) tasks.When applying LLMs for code generation, recent works mainly focus on directing the models to articulate intermediate natural-language…
Partial multi-label learning (PMLL) refers to a weakly-supervised classification problem, where each instance is associated with a set of candidate labels, covering its ground-truth labels but also with irrelevant ones. The current methodology of PMLL is to estimate the ground-truth confidences of c…
Multilingual translation supports multiple translation directions by projecting all languages in a shared space, but the translation quality is undermined by the difference between languages in the text-only modality, especially when the number of languages is large. To bridge this gap, we introduce…
Naked eye recognition of age is usually based on comparison with the age of others. However, this idea is ignored by computer tasks because it is difficult to obtain representative contrast images of each age. Inspired by the transfer learning, we designed the Delta Age AdaIN (DAA) operation to obta…
In this paper, we study the problem of 3D scene geometry decomposition and manipulation from 2D views. By leveraging the recent implicit neural representation techniques, particularly the appealing neural radiance fields, we introduce an object field component to learn unique codes for all individua…
Recent works in robotic manipulation through reinforcement learning (RL) or imitation learning (IL) have shown potential for tackling a range of tasks e.g., opening a drawer or a cupboard. However, these techniques generalize poorly to unseen objects. We conjecture that this is due to the high-dimen…
We study the problem of 3D semantic segmentation from raw point clouds. Unlike existing methods which primarily rely on a large amount of human annotations for training neural networks, we propose the first purely unsupervised method, called GrowSP, to successfully identify complex semantic classes…
The task of text-to-SQL aims to convert a natural language question into its corresponding SQL query within the context of relational tables. Existing text-to-SQL parsers generate a plausible SQL query for an arbitrary user question, thereby failing to correctly handle problematic user questions. To…
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task, which focuses on detecting the sentiment polarity towards the aspect in a sentence. However, it is always sensitive to the multi-aspect challenge, where features of multiple aspects in a sentence will affect each other…
This paper presents a novel place recognition approach to autonomous vehicles by using low-cost, single-chip automotive radar. Aimed at improving recognition robustness and fully exploiting the rich information provided by this emerging automotive radar, our approach follows a principled pipeline th…
Fusing the camera and LiDAR information has become a de-facto standard for 3D object detection tasks. Current methods rely on point clouds from the LiDAR sensor as queries to leverage the feature from the image space. However, people discovered that this underlying assumption makes the current fusio…
The vision-language navigation (VLN) task requires an agent to reach a target with the guidance of natural language instruction. Previous works learn to navigate step-by-step following an instruction. However, these works may fail to discriminate the similarities and discrepancies across instruction…
Corner-guided detector enjoys potential ability to yield precise bounding boxes. However, unreliable corner pairs, generated by heuristic grouping guidance, hinder the development of this detector. In this paper, we propose a novel corner grouping algorithm, termed as Corner Affinity, to significan…
Knowledge distillation becomes a de facto standard to improve the performance of small neural networks. Most of the previous works propose to regress the representational features from the teacher to the student in a one-to-one spatial matching fashion. However, people tend to overlook the fact that…
Scene flow is a powerful tool for capturing the motion field of 3D point clouds. However, it is difficult to directly apply flow-based models to dynamic point cloud classification since the unstructured points make it hard or even impossible to efficiently and effectively trace point-wise correspond…
The robustness of Text-to-SQL parsers against adversarial perturbations plays a crucial role in delivering highly reliable applications. Previous studies along this line primarily focused on perturbations in the natural language question side, neglecting the variability of tables. Motivated by this,…
Accurate motion capture of aerial robots in 3D is a key enabler for autonomous operation in indoor environments such as warehouses or factories, as well as driving forward research in these areas. The most commonly used solutions at present are optical motion capture (e.g. VICON) and Ultrawide-band…
A myriad of recent breakthroughs in hand-crafted neural architectures for visual recognition have highlighted the urgent need to explore hybrid architectures consisting of diversified building blocks. Meanwhile, neural architecture search methods are surging with an expectation to reduce human effor…
Current dynamic networks and dynamic pruning methods have shown their promising capability in reducing theoretical computation complexity. However, dynamic sparse patterns on convolutional filters fail to achieve actual acceleration in real-world implementation, due to the extra burden of indexing,…
Knowledge Distillation has shown very promising ability in transferring learned representation from the larger model (teacher) to the smaller one (student). Despite many efforts, prior methods ignore the important role of retaining inter-channel correlation of features, leading to the lack of captur…
Accurately describing and detecting 2D and 3D keypoints is crucial to establishing correspondences across images and point clouds. Despite a plethora of learning-based 2D or 3D local feature descriptors and detectors having been proposed, the derivation of a shared descriptor and joint keypoint dete…
Lidar odometry (LO) is a key technology in numerous reliable and accurate localization and mapping systems of autonomous driving. The state-of-the-art LO methods generally leverage geometric information to perform point cloud registration. Furthermore, obtaining the point cloud semantic information…
Recent learning-based approaches have achieved impressive results in the field of single-shot camera localization. However, how best to fuse multiple modalities (e.g., image and depth) and to deal with degraded or missing input are less well studied. In particular, we note that previous approaches t…
Heart rate monitoring at home is a useful metric for assessing health e.g. of the elderly or patients in post-operative recovery. Although non-contact heart rate monitoring has been widely explored, typically using a static, wall-mounted device, measurements are limited to a single room and sensitiv…
We present a novel key region extraction method of point cloud, ROI-cloud, for LiDAR odometry and localization with autonomous robots. Traditional methods process massive point cloud data in every region within the field of view. In dense urban environments, however, processing redundant and dynamic…
This paper proposes a hierarchical depthwise graph convolutional neural network (HDGCN) for point cloud semantic segmentation. The main chanllenge for learning on point clouds is to capture local structures or relationships. Graph convolution has the strong ability to extract local shape information…
Pedestrian detection in fish-eye images is always an important problem in advanced driver assistance systems (ADAS). In conventional methods, pedestrian detectors will be trained using fish-eye images. But it is hard to collect and label enough fish-eye images manually. Therefore, a new strategy for…
Point set registration is a long addressed problem in lots of pattern recognition tasks. This paper presents a robust point set registration algorithm based on optimization of distance between two probability distributions. A major problem encountered in the point to point algorithms is the definiti…
In image labeling, local representations for image units (pixels, patches or superpixels) are usually generated from their surrounding image patches, thus long-range contextual information is not effectively encoded. In this paper, we introduce recurrent neural networks (RNNs) to address this issue.…
We adopt Convolutional Neural Networks (CNN) as our parametric model to learn discriminative features and classifiers for local patch classification. As visually similar pixels are indistinguishable from local context, we alleviate such ambiguity by putting a global scene constraint. We estimate the…