176 accepted papers
Endoscopic surgery demands continuous real-time visual decision-making under severe constraints, including a limited field of view, motion blur, and dynamically deforming anatomy. These factors impose substantial cognitive load on surgeons and motivate the integration of artificial intelligence (AI)
Diffusion-based video editing has emerged as an important paradigm for high-quality and flexible content generation. However, despite their generality and strong modeling capacity, Diffusion Transformers (DiT) remain computationally expensive due to the iterative denoising process, posing challenges
Parameter-efficient Mixture-of-Experts (MoE) architectures, such as LoRA-MoE, enable strong and generalizable fine-tuning. However, a critical problem arises when fine-tuning these architectures with advanced reinforcement learning algorithms such as Group Relative Policy Optimization (GRPO). Tradit…
Self-supervised contrastive learning has emerged as a powerful paradigm for skeleton-based action recognition by enforcing consistency in the embedding space. However, existing methods rely on binary contrastive objectives that overlook the intrinsic continuity of human motion, resulting in fragment
Underwater instance segmentation is essential for fine-grained scene understanding. However, underwater imagery exhibits a strong domain gap from in-air vision due to severe degradation (e.g., turbidity). Consequently, despite its general segmentation ability, SAM degrades sharply underwater. In thi
Federated multi-view clustering (FedMVC) has been widely used to discover latent structures in distributed multi-view data, but most methods assume independent and identically distributed (IID) data. In practice, non-IID distributions with partial and imbalanced categories cause clients to learn bia
While previous multimodal slow-thinking methods have demonstrated remarkable success in single-image understanding scenarios, their effectiveness becomes fundamentally constrained when extended to more complex multi-image comprehension tasks. This limitation stems from their predominant reliance on
Ensuring safety in power grid construction remains a critical yet challenging task, as existing monitoring approaches often lack scalability, timeliness, and adaptability to diverse on-site conditions. To address these limitations, we present ConstructAI, a deployed AI-driven safety management syste
Diffusion models have recently demonstrated significant robustness in medical image segmentation, effectively accommodating variations across different imaging styles. However, their applications remain limited due to: (i) current successes being primarily confined to 2D segmentation tasks—we observ…
Existing core-set selection methods predominantly rely on heuristic scoring signals such as training dynamics or model uncertainty, lacking explicit modeling of data likelihood. This omission may hinder the constructed subset from capturing subtle yet critical distributional structures that underpin
A precise and comprehensive understanding of human-environment interactions in egocentric vision is essential for next-generation intelligent agents, such as assistive robotics. While existing multimodal large language models (MLLMs) support unified reasoning from scene-level analysis to instance-sp…
Time-series clustering remains challenging due to the inherent trade-off between clustering effectiveness and computational efficiency. Similarity-based methods often suffer from quadratic complexity caused by pairwise distance computations, while deep learning–based approaches typically rely on cos
Out-of-distribution (OOD) detection is critical for the safe deployment of machine learning systems in safety-sensitive domains. Diffusion models have recently emerged as powerful generative models, capable of capturing complex data distributions through iterative denoising. Building on this progres…
Multimodal Large Language Models (MLLMs) hold promise for accelerating scientific discovery by interpreting complex experimental procedures. However, their true capabilities are poorly understood, as existing benchmarks neglect the fine-grained and long-horizon nature of authentic laboratory work, e…
Text-to-Video (T2V) generation has advanced greatly, yet maintaining consistency remains challenging, especially for tuning-free long video generation. We attribute the consistency problem to cumulative deviations for long video generation at three levels: the random noise lacking correlation resu
Multimodal large language models (MLLMs) are emerging as versatile foundations for mixed-modality retrieval. Yet, they often require heavy post-hoc training to convert them into contrastive encoders for retrieval. This work asks: \textit{Can off-the-shelf MLLMs serve as powerful retrievers without a…
We present GRL-SNAM, a geometric reinforcement learning framework for Simultaneous Navigation and Mapping in unknown environments. GRL-SNAM differs from traditional SLAM and other reinforcement learning methods by relying exclusively on local sensory observations without constructing a global map. O…
Humans commonly reason about object affordance through observed interactions in images or videos, and once formed, such knowledge can be generically generalized to novel objects. Inspired by this principle, we advocate for a novel framework that leverages emerging multimodal large language models (M
Fine-tuning large models on edge devices is severely hindered by the memory-intensive backpropagation (BP) in standard frameworks like federated learning and split learning. While substituting BP with zeroth-order optimization can significantly reduce memory footprints, it typically suffers from pro…
Recent methods have made notable progress in the visual quality of hand-object interaction video synthesis. However, most approaches rely on 2D control signals that lack spatial expressiveness and limit the utilization of synthetic 3D conditional data. To address these limitations, we propose HVG-3D
This paper aims to interactively generate and edit disentangled 3D characters based on precise user instructions. Existing methods generate and edit 3D characters via rough and simple editing guidance and entangled representations, making it difficult to achieve precise and comprehensive control ove
A fine-grained understanding of egocentric human-environment interactions is crucial for developing next-generation embodied agents. One fundamental challenge in this area involves accurately parsing hands and active objects. While transformer-based architectures have demonstrated considerable poten…
Recent benchmarks and datasets have been proposed to improve spatial reasoning in vision-language models (VLMs), yet existing open resources remain limited in scale, visual diversity, and instruction expressiveness. In this work, we introduce InternSpatial, the largest open-source dataset for spatia…
Large-scale video-text pretraining achieves strong performance but depends on noisy, synthetic captions with limited semantic coverage, often overlooking implicit world knowledge such as object motion, 3D geometry, and physical cues. In contrast, masked video modeling (MVM) directly exploits spatiot
Offline Multi-Agent Reinforcement Learning (MARL) is critical for coordinating multiple agents in costly and unsafe environments, yet existing methods struggle with high sensitivity to reward functions and weak generalization to new goals, limiting its practical impact. Inspired by single-agent Offl
Recent class-incremental learning (CIL) methods built on large pre-trained vision models have shown that strong performance can be retained even under strict data access constraints. This raises a fundamental question: which properties of pre-trained representations make such recovery possible in th…
Teleoperation via natural-language reduces operator workload and enhances safety in high-risk or remote settings. However, in dynamic remote scenes, transmission latency during bidirectional communication creates gaps between remote perceived states and operator intent, leading to command misunderst…
While reinforcement learning with verifiable rewards (RLVR) has advanced LLM reasoning in structured domains like mathematics and programming, its application to general-domain reasoning tasks remains challenging due to the absence of verifiable reward signals. To this end, methods like Reinforcemen
Hypergraphs provide a natural and expressive framework for modeling high-order relationships, enabling the representation of group-wise interactions beyond pairwise connections. While hypergraph neural networks (HNNs) have shown promise for learning on such structures, existing models often rely on
Despite its success in enriching LLMs with external knowledge, RAG remains plagued by faithfulness hallucinations, where generated text contradicts the retrieved source information. Previous research on faithfulness hallucination in LLMs is frequently hindered by prohibitive manual annotation costs
The rapid advancement of multimodal large language models has demonstrated impressive capabilities, yet nearly all operate in an offline paradigm, hindering real-time interactivity. Addressing this gap, we introduce the Real-tIme Video intERaction Bench (RIVER Bench), designed for evaluating online…
Large Vision-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs. Although recent token reduction methods mitigate this issue, they mainly target single-turn Visual Question Answering (VQA), leaving the more practical mult
Neural algorithmic reasoning has recently emerged as a popular research direction. It aims to train neural networks to mimic the step-by-step behavior of classical rule-based algorithms. More specifically, the execution of such algorithms can be abstracted as a sequence of states, where each state
Sea Surface Temperature (SST) is crucial for understanding upper-ocean thermal dynamics and ocean-atmosphere interactions, which have profound economic and social impacts. While data-driven models show promise in SST prediction, their black-box nature often limits interpretability and overlooks key
Textile pattern generation (TPG) aims to synthesize fine-grained textile pattern images based on given clothing images. Although previous studies have not explicitly investigated TPG, existing image-to-image models appear to be natural candidates for this task. However, when applied directly, these
Query rewriting is a crucial task for improving retrieval, especially in professional domains such as law and medicine, where user queries are often underspecified and ambiguous. While large language models (LLMs) offer strong understanding and generation capabilities, existing LLM-based approaches
Long video understanding is essential for human-like intelligence, enabling coherent perception and reasoning over extended temporal contexts. While the emerging thinking-with-frames paradigm--which alternates between global temporal reasoning and local frame examination--has advanced the reasoning
Ocean heat extremes, including marine heatwaves and the El Ni\~no–Southern Oscillation (ENSO), exert profound impacts on marine ecosystems and socio-economic stability. Establishing robust early warning systems is critical for proactive risk management; however, conventional predictive models often
Tourism and travel planning increasingly rely on digital assistance, yet existing multimodal AI systems often lack specialized knowledge and contextual understanding of urban environments. We present TraveLLaMA, a specialized multimodal language model designed for comprehensive travel assistance. Ou
Tokenizer is a crucial component for both visual understanding and generation. To advance toward the ultimate goal of universal modeling, recent research has focused on developing a unified tokenizer. However, existing tokenizers face a significant performance trade-off between understanding and gen…
As hubs of human activity, urban surfaces consist of a wealth of semantic entities. Segmenting these various entities from satellite imagery is crucial for a range of downstream applications. Current advanced segmentation models can reliably segment entities defined by physical attributes (e.g., bui…
Recent advances in video understanding have been driven by MLLMs. But these MLLMs are good at analyzing short videos, while suffering from difficulties in understanding videos with a longer context. To address this difficulty, several agent paradigms have recently been proposed, using MLLMs as agen
Long-context video modeling is critical for multimodal large language models (MLLMs), enabling them to process movies, online video streams, and so on. Despite its advances, handling long videos remains challenging due to the difficulty in efficiently understanding the extremely long video context.…
Existing multimodal large language models for long-video understanding predominantly rely on uniform sampling and single-turn inference, limiting their ability to identify sparse yet critical evidence amid extensive redundancy. We introduce VideoSeeker, a novel framework that supports iterative disc…
Classifying the status of NSCLC PD-L1 on chest CT is a cost-effective and non-invasive method. The existing multiple instance learning (MIL) methods are not effective for this task, due to the lack of an efficient feature encoder for 3D instances and ignoring the importance of representative instanc…
Retinal vein cannulation (RVC) is a minimally invasive microsurgical procedure for treating retinal vein occlusion (RVO), a leading cause of vision impairment. However, the small size and fragility of retinal veins, coupled with the need for high-precision, tremor-free needle manipulation, create si
Diffusion models, known for their generative ability, have recently been adapted to time series analysis. Most pioneering works rely on the standard isotropic diffusion, treating each time step and the entire frequency spectrum identically. However, it may not be suitable for time series, which ofte…
Most of the existing methods to evaluate the quality of panoramic content mainly focus on studying the quality evaluation of static panoramic images, rather than the more widely used dynamic panoramic videos. Also, the few panoramic video quality metrics that are available have obvious weaknesses in…
Egocentric interaction perception is one of the essential branches in investigating human-environment interaction, which lays the basis for developing next-generation intelligent systems. However, existing egocentric interaction understanding methods cannot yield coherent textual and pixel-level res…
Existing semi-supervised learning methods typically mitigate the impact of unreliable predictions by suppressing low-confidence regions. However, these methods fail to explore which regions hold higher learning value and how to design adaptive learning strategies for these regions. To address these…
Heterophilic graph neural networks (GNNs) have gained prominence for their ability to learn effective representations in graphs with diverse, attribute-aware relationships. While existing methods leverage attribute inference during message passing to improve performance, they often struggle with cha
This paper introduces Bidirectional Lazy Informed Trees (BLIT*), the first algorithm to incorporate anytime incremental lazy bidirectional heuristic search (Bi-HS) into batch-wise sampling-based motion planning (Bw-SBMP). BLIT* operates on batches of informed states (states that can potentially impr
In bidirectional heuristic search, the meeting-in-the-middle property (MMP) and the theory of must-expand pairs (MEP) have driven significant recent developments in search efficiency. However, these methodologies typically terminate the search based on minimal priority metrics in the forward and bac
Creating high-quality data for training robust language-instructed agents is a long-lasting challenge in embodied AI. In this paper, we introduce a Self-Refining Data Flywheel (SRDF) that generates high-quality and large-scale navigational instruction-trajectory pairs by iteratively refining the dat…
Automated weather stations play a pivotal role in fine-grained weather forecasting, due to their cost-effectiveness and global deployment potential. Data-driven methods, particularly deep learning techniques, have emerged as potent tools for precise weather forecasting. However, capturing meaningful…
Coral reefs are vital yet vulnerable ecosystems that require continuous monitoring to support conservation. While coral reef images provide essential information in coral monitoring, interpreting such images remains challenging due to the need for domain expertise. Visual Question Answering (VQA), p…
Large Language Models (LLMs) are widely applied in decision making, but their deployment is threatened by jailbreak attacks, where adversarial users manipulate model behavior to bypass safety measures. Existing defense mechanisms, such as safety fine-tuning and model editing, either require extensiv…
Hypergraphs provide a flexible framework for modeling high-order (complex) interactions among multiple entities, extending beyond traditional pairwise correlations in graph structures. However, deep hypergraph neural networks (HGNNs) often face the challenge of oversmoothing with increasing depth, s…
Diffusion models have demonstrated exceptional capabilities in image restoration, yet their application to video super-resolution (VSR) faces significant challenges in balancing fidelity with temporal consistency. Our evaluation reveals a critical gap: existing approaches consistently fail on severe…
In video Multimodal Large Language Models (video MLLMs), the visual encapsulation process plays a pivotal role in converting video contents into representative tokens for LLM input. While linear projectors are widely employed for encapsulation, they introduce semantic indistinctness and temporal inc…
Concept Bottleneck Models (CBMs) try to make the decision-making process transparent by exploring an intermediate concept space between the input image and the output prediction. Existing CBMs just learn coarse-grained relations between the whole image and the concepts, less considering local image…
The current Federated Recommendation System (FedRS) focuses on personalized recommendation services and assumes clients are personalized IoT devices (e.g., Mobile phones). In this paper, we deeply dive into new but practical FedRS applications within the joint venture ecosystem. Subsidiaries engage…
Multimodal federated learning (MMFL) has gained increasing popularity due to its ability to leverage the correlation between various modalities, meanwhile preserving data privacy for different clients. However, recent studies show that correlation between modalities increase the vulnerability of fed…
Coral reefs play a crucial role in marine ecosystems, offering a nutrient-rich environment and safe shelter for numerous marine species. Automated coral image recognition aids in monitoring ocean health at a scale without experts' manual effort. Recently, large vision-language models like CLIP have…
Precise, generalizable subject-agnostic seizure prediction (SASP) remains a fundamental challenge due to the intrinsic complexity and significant spectral variability of electrophysiologial signals across individuals and recording modalities. We propose \model{FAPEX}, a novel architecture that intro…
Federated Learning (FL) has emerged as a promising approach for distributed machine learning, enabling clients to collaboratively train models without sharing their data. However, existing FL methods continue to face challenges when dealing with non-IID data, particularly under conditions of extreme…
Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated significant potential over traditional rendering techniques, attracting widespread attention from both industry and academia. However, real-time rendering with 3DGS remains a challenging problem, particularly in large-scale, high-reso…
Class imbalance is a prevalent issue in real-world graph-structure data, such as social and citation networks, posing significant challenges for Graph Neural Networks (GNNs). Existing solutions often focus on balancing class distributions via oversampling techniques, which may lead to overfitting an…
With the growing adoption of Hypergraph Neural Networks (HNNs) to model higher-order relationships in complex data, concerns about their security and robustness have become increasingly important. However, current security research often overlooks the unique structural characteristics of hypergraph…
Virtual environments are essential to AI agent research. Existing environments for LLM agent research typically focus on either physical task solving or social simulation, with the former oversimplifying agent individuality and social dynamics, and the latter lacking physical grounding of social beh
Dataset distillation aims to streamline the training process by creating a compact yet effective dataset for a much larger original dataset. However, existing methods often struggle with distilling large, high-resolution datasets due to prohibitive resource costs and limited performance, primarily s…
Auto-regressive models have made significant progress in the realm of text-to-image synthesis, yet devising an appropriate model architecture and training strategy to achieve a satisfactory level remains an important avenue of exploration. In this work, we introduce MARS, a novel framework for T2I g…
The out-of-distribution (OOD) detection on graph-structured data is crucial for deploying graph neural networks securely in open-world scenarios. However, existing methods have overlooked the prevalent scenario of multi-label classification in real-world applications. In this work, we investigate th…
We introduce MM-Mixing, a multi-modal mixing alignment framework for 3D understanding. MM-Mixing applies mixing-based methods to multi-modal data, preserving and optimizing cross-modal connections while enhancing diversity and improving alignment across modalities. Our proposed two-stage training pi…
In autonomous driving, the ability to detect pedestrians accurately is crucial for safety. Some detectors, however, often struggle with occlusions, where pedestrians partially hidden behind objects appear incomplete and are harder to be identified accurately. To alleviate this issue, we introduce Cl…
Current video training methods rely on fixed spatiotemporal sampling grids to extract a predetermined number of tokens, limiting adaptability to diverse computational budgets and resulting in suboptimal accuracy-computation trade-offs. This rigidity constrains high-performance models trained in reso…
Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of speakers may suffer from confusion of speaker identity. In th…
Predicting variations in complex traffic environments is crucial for the safety of autonomous driving. Recent advancements in occupancy forecasting have enabled forecasting future 3D occupied status in driving environments by observing historical 2D images. However, high computational demands make o…
Image-text interleaved data, consisting of multiple images and texts arranged in a natural document format, aligns with the presentation paradigm of internet data and closely resembles human reading habits. Recent studies have shown that such data aids multimodal in-context learning and maintains th…
Traffic prediction plays a critical role in mitigating congestion, optimizing traffic flow, and enhancing urban mobility. Accurate predictions contribute directly to improved safety, reduced travel times, and a more efficient transportation system. For example, when a surge in traffic is anticipated…
While visual autoregressive modeling (VAR) strategies have shed light on image generation with the autoregressive models, their potential for segmentation, a task that requires precise low-level spatial perception, remains unexplored. Inspired by the multi-scale modeling of classic Mask2Former-based…
Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting prompts that induce LLMs to generate harmful content. Current methods typically target exact affirmative responses, suffering from lim…
The advancement of diffusion models has enhanced the realism of AI-generated content but also raised concerns about misuse, necessitating robust copyright protection and tampering localization. Although recent methods have made progress toward unified solutions, their reliance on post hoc processing…
Multimodal Large Language Models (MLLMs) have recently achieved remarkable progress in video understanding. However, their effectiveness in real-time streaming scenarios remains limited due to storage constraints of historical visual features and insufficient real-time spatiotemporal reasoning. To a…
Estuarine systems, located at the interface of land, ocean, and atmosphere, are vital to global ecosystems and economies due to their rich exchanges among multiple environments. Tropical cyclones cause significant fluctuations in salinity and other environmental parameters within estuaries, impactin…
Current multimodal large language models (MLLMs) struggle with fine-grained or precise understanding of visuals although they give comprehensive perception and reasoning in a spectrum of vision applications. Recent studies either develop tool-using or unify specific visual tasks into the autoregress…
Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in short video understanding. However, understanding long-form videos still remains challenging for MLLMs. This paper proposes TimeSuite, a collection of new designs to adapt the existing short-form video MLLMs for lon…
Advances in Earth observation (EO) foundation models have unlocked the potential of big satellite data to learn generic representations from space, benefiting a wide range of downstream applications crucial to our planet. However, most existing efforts remain limited to fixed spectral sensors, focus…
Event-based cameras offer unique advantages such as high temporal resolution, high dynamic range, and low power consumption. However, the massive storage requirements and I/O burdens of existing synthetic data generation pipelines and the scarcity of real data prevent event-based training datasets f…
We present VRBench, the first long narrative video benchmark crafted for evaluating large models' multi-step reasoning capabilities, addressing limitations in existing evaluations that overlook temporal reasoning and procedural validity. It comprises 960 long videos (with an average duration of 1.6…
Recent efforts in video reasoning segmentation (VRS) integrate large language models (LLMs) with perception models to localize and track objects via textual instructions, achieving barely satisfactory results in simple scenarios. However, they struggled to discriminate and deduce the objects from us…
Inducing reasoning in multimodal large language models (MLLMs) is critical for achieving human-level perception and understanding. Existing methods mainly leverage LLM reasoning to analyze parsed visuals, often limited by static perception stages. This paper introduces Visual Test-Time Scaling (VTTS…
Point Cloud Transformers have become a cornerstone in 3D representation for their ability to model long-range dependencies via self-attention. However, these models tend to overemphasize salient regions while neglecting other informative regions, which limits feature diversity and compromises robust…
Supervised Fine-tuning has been pivotal in training autoregressive language models, yet it introduces exposure bias. To mitigate this, Post Fine-tuning, including on-policy and off-policy methods, has emerged as a solution to enhance models further. However, each has its limitations regarding perfor…
Hypergraph neural networks (HNNs) have shown promise in handling tasks characterized by high-order correlations, achieving notable success across various applications. However, there has been limited focus on heterophilic hypergraph learning (HHL), in contrast to the increasing attention given to gr…
Cotton is a critical agricultural product and industrial raw material, playing a key role in the national economies and people's living conditions, particularly in developing countries. However, cotton picking and processing often result in the contamination with various foreign fibers, such as hair…
Nowadays, gastrointestinal cancer has widely impacted people's health worldwide due to its high mortality rate. Early treatment of gastrointestinal cancer by endoscopic procedure can greatly increase survival rates of patients. Nevertheless, current flexible endoscopic instruments lack of degree of
Endoscopic robot has garnered significant attention for its ability to offer auxiliary traction and precise maneuverability. However, the low stiffness of its insertion tube makes it susceptible to deformation, which poses great challenges for precise control. Existing variable stiffness technologie
Model-based reinforcement learning has shown promise in sample efficiency but suffers from errors accumulated during multi-step model sampling. To tackle this issue, we propose corrected data aggregation for model-based policy optimization. This approach involves aligning simulated trajectories with…
We examine both the manifold hypothesis (Bengio et al., 2013) and the union of manifold hypothesis (Brown et al., 2023), and argue that, in contrast to these hypotheses, the local intrinsic dimension varies from point to point even in the same connected component. We propose an alternative CW comple…
While LLMs demonstrate impressive capabilities in musical knowledge, we find that music reasoning is still an unsolved task.We introduce ChatMusician, an open-source large language model (LLM) that integrates intrinsic musical abilities. It is based on continual pre-training and finetuning LLaMA2 on…
Visual interpretation is extremely important in human geography as the primary technique for geographers to use photograph data in identifying, classifying, and quantifying geographic and topological objects or regions. However, it is also time-consuming and requires overwhelming manual effort from…
Video understanding relies on accurate action detection for temporal analysis. However, existing mainstream methods have limitations in real-world applications due to their offline and closed-set evaluation approaches, as well as their dependence on manual annotations. To address these challenges an…
Explaining multivariate time series is a compound challenge, as it requires identifying important locations in the time series and matching complex temporal patterns. Although previous saliency-based methods addressed the challenges, their perturbation may not alleviate the distribution shift issue,…
Online Class Incremental Learning (OCIL) aims to train models incrementally, where data arrive in mini-batches, and previous data are not accessible. A major challenge in OCIL is Catastrophic Forgetting, i.e., the loss of previously learned knowledge. Among existing baselines, replay-based methods s…
In this letter, we present a fast and decentralized state estimation framework for the control of legged locomotion. The nonlinear estimation of the floating base states is decentralized to <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">an orientati
Normalization layers are ubiquitous in deep learning, greatly accelerating optimization. However, they also introduce many unexpected phenomena during training, for example, the Fast Equilibrium conjecture proposed by (Li et al.,2020), which states that the scale-invariant normalized network, when t…
This paper introduces InternVid, a large-scale video-centric multimodal dataset that enables learning powerful and transferable video-text representations for multimodal understanding and generation. InternVid contains over 7 million videos lasting nearly 760K hours, yielding 234M video clips accomp…
Knowledge distillation, the technique of transferring knowledge from large, complex models to smaller ones, marks a pivotal step towards efficient AI deployment. Distilling Step-by-Step (DSS), a novel method utilizing chain-of-thought (CoT) distillation, has demonstrated promise by imbuing smaller m…
With the rapid development of Multi-modal Large Language Models (MLLMs) a number of diagnostic benchmarks have recently emerged to evaluate the comprehension capabilities of these models. However most benchmarks predominantly assess spatial understanding in the static image tasks while overlooking t…
Despite their success in LIDAR object detection, modern detectors are vulnerable to uncommon instances and corner cases (e.g., a runaway tire) since they are closed-set and static. Networks under the closed-set setup only predict labels of seen classes, while static models suffer from catastrophic f…
Data augmentation is an effective regularization strategy for mitigating overfitting in deep neural networks, and it plays a crucial role in 3D vision tasks, where the point cloud data is relatively limited. While mixing-based augmentation has shown promise for point clouds, previous methods mix poi…
Code comments are crucial for gaining in-depth insights to facilitate code comprehension. The key to obtaining these insights lies in precisely summarizing the main purpose of the code. Recent approaches on code comment generation lie in prompting large language models (LLMs) such as ChatGPT, instea…
Recent DETR-based methods have advanced the development of Video Instance Segmentation (VIS) through transformers' efficiency and capability in modeling spatial and temporal information. Despite harvesting remarkable progress, existing works follow asynchronous designs, which model video sequences v…
Time series analysis is widely used in many fields such as power energy, economics, and transportation, including different tasks such as forecasting, anomaly detection, classification, etc. Missing values are widely observed in these tasks, and often leading to unpredictable negative effects on exi…
We present a novel controller design on a robotic locomotor that combines an aerial vehicle with a spring-loaded leg. The main motivation is to enable the terrestrial locomotion capability on aerial vehicles so that they can carry heavy loads: heavy enough that flying is no longer possible, e.g., wh…
Mamba, a state-space model with selective mechanisms and hardware-aware architecture, has demonstrated outstanding performance in long sequence modeling tasks, particularly garnering widespread exploration and application in the field of computer vision. While existing works have mixed opinions of i…
Semantic scene completion is a difficult task that involves completing the geometry and semantics of a scene from point clouds in a large-scale environment. Many current methods use 3D/2D convolutions or attention mechanisms, but these have limitations in directly constructing geometry and accuratel…
Conventional crowd counting methods exploit a large number of point annotations to train regression-based neural networks for density map estimation. However, laborious point annotations of human heads (strong supervision) are required in training. This paper presents a simple and effective crowd co…
In this paper, we study a real-world JPEG image restoration problem with bit errors on the encrypted bitstream. The bit errors bring unpredictable color casts and block shifts on decoded image contents, which cannot be trivially resolved by existing image restoration methods mainly relying on pre-de…
The past decade has witnessed great strides in video recovery by specialist technologies, like video inpainting, completion, and error concealment. However, they typically simulate the missing content by manual-designed error masks, thus failing to fill in the realistic video loss in video communica…
Distilled student models in teacher-student architectures are widely considered for computational-effective deployment in real-time applications and edge devices. However, there is a higher risk of student models to encounter adversarial attacks at the edge. Popular enhancing schemes such as adversa…
The spiking neural network (SNN) using leaky-integrated-and-fire (LIF) neurons has been commonly used in automatic speech recognition (ASR) tasks. However, the LIF neuron is still relatively simple compared to that in the biological brain. Further research on more types of neurons with different sca…
Cross-scene generalizable NeRF models, which can directly synthesize novel views of unseen scenes, have become a new spotlight of the NeRF field. Several existing attempts rely on increasingly end-to-end "neuralized" architectures, i.e., replacing scene representation and/or rendering modules with p…
Early diagnosis of Alzheimer’s disease (AD) is crucial in facilitating preventive care and to delay further progression. Speech based automatic AD screening systems provide a non-intrusive and more scalable alternative to other clinical screening techniques. Textual embedding features produced by pr…
Automatic recognition of disordered and elderly speech remains a highly challenging task to date due to the difficulty in collecting such data in large quantities. This paper explores a series of approaches to integrate domain adapted Self-Supervised Learning (SSL) pre-trained models into TDNN and C…
In this paper, we consider the problem of open-vocabulary semantic segmentation (OVS), which aims to segment objects of arbitrary classes instead of pre-defined, closed-set categories. The main contributions are as follows: First, we propose a transformer-based model for OVS, termed as OVSegmentor,…
Neural radiance fields(NeRF) show great success in novel-view synthesis. However, in real-world scenes, recovering high-quality details from the source images is still challenging for the existing NeRF-based approaches, due to the potential imperfect calibration information and scene representation…
Virtual reality and augmented reality (XR) bring increasing demand for 3D content generation. However, creating high-quality 3D content requires tedious work from a human expert. In this work, we study the challenging task of lifting a single image to a 3D object and, for the first time, demonstrate…
Driving under the influence (DUI) is one of the main causes of traffic accidents, often leading to severe life and property losses. Setting up sobriety checkpoints on certain roads is the most commonly used practice to identify DUI-drivers in many countries worldwide. However, setting up checkpoints…
Salient object detection (SOD) aims to mimic the human visual system (HVS) and cognition mechanisms to identify and segment salient objects. However, due to the complexity of these mechanisms, current methods are not perfect. Accuracy and robustness need to be further improved, particularly in compl…
Accurate prediction of electric load is crucial in power grid planning and management. In this paper, we solve the electric load forecasting problem under extreme events such as scorching heats. One challenge for accurate forecasting is the lack of training samples under extreme conditions. Also loa…
The Landsat program is the longest-running Earth observation program in history, with 50+ years of data acquisition by 8 satellites. The multispectral imagery captured by sensors onboard these satellites is critical for a wide range of scientific fields. Despite the increasing popularity of deep lea…
Recent research in language-guided visual navigation has demonstrated a significant demand for the diversity of traversable environments and the quantity of supervision for training generalizable agents. To tackle the common data scarcity issue in existing vision-and-language navigation datasets, we…
Patient-independent detection of epileptic activities based on visual spectral representation of continuous EEG (cEEG) has been widely used for diagnosing epilepsy. However, precise detection remains a considerable challenge due to subtle variabilities across subjects, channels and time points. Thus…
Training on large-scale datasets can boost the performance of video instance segmentation while the annotated datasets for VIS are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific datasets, thus, it is appealing to jointly train models across the aggr…
Music timbre style transfer aims at replacing the instrument timbre in a solo recording with another instrument, while preserving the musical content. Existing GAN-based methods can only achieve timbre style transfer between two given timbres. Inspired by the practice in voice conversion, we propose…
The prolific performances of Vision Transformers (ViTs) in image tasks have prompted research into adapting the image ViTs for video tasks. However, the substantial gap between image and video impedes the spatiotemporal learning of these image-pretrained models. Though video-specialized models like…
Video Foundation Models (VFMs) have received limited exploration due to high computational costs and data scarcity. Previous VFMs rely on Image Foundation Models (IFMs), which face challenges in transferring to the video domain. Although VideoMAE has trained a robust ViT from limited data, its low-l…
Scale is the primary factor for building a powerful foundation model that could well generalize to a variety of downstream tasks. However, it is still challenging to train video foundation models with billions of parameters. This paper shows that video masked autoencoder (VideoMAE) is a scalable and…
Tactile sensing plays a vital role for human hand function in terms of object exploration, grasping and manipulation. Different types of tactile sensors have been designed during the past decades, which are mainly focused on either the fingertips for grasping or the upper-body for human-robot intera
Referring expressions are commonly used when referring to a specific target in people's daily dialogue. In this paper, we develop a novel task of audio-visual grounding referring expression for robotic manipulation. The robot leverages both the audio and visual information to understand the referrin…
Twisted and Coiled Actuators (TCAs) are a class of new artificial muscles for flexible actuations. However, conventional TCAs based on nylon fibers commonly require high driving temperature, which limits their applications. Although the TCAs based on spandex fibers can produce high strain under low
Few-shot Intent Detection (FSID) is a challenging task in dialogue systems due to the scarcity of available annotated utterances. Although existing few-shot learning approaches have made remarkable progress, they fall short in adapting to the Generalized Few-shot Intent Detection (GFSID) task where…
The potential diagnostic applications of magnet-actuated capsules have been greatly increased in recent years. For most of these potential applications, accurate position control of the capsule have been highly demanding. However, the friction between the robot and the environment as well as the dra…
Recent studies have shown the importance of modeling long-range interactions in the inpainting problem. To achieve this goal, existing approaches exploit either standalone attention techniques or transformers, but usually under a low resolution in consideration of computational cost. In this paper,…
Nonlinear ICA is a fundamental problem in machine learning, aiming to identify the underlying independent components (sources) from data which is assumed to be a nonlinear function (mixing function) of these sources. Recent works prove that if the sources have some particular structures (e.g. tempor…
"Multimodal ambiguity and color bleeding remain challenging in colorization. To tackle these problems, we propose a new GAN-based colorization approach PalGAN, integrated with palette estimation and chromatic attention. To circumvent the multimodality issue, we present a new colorization formulation…
"The superiority of deep learning based point cloud representations relies on large-scale labeled datasets, while the annotation of point clouds is notoriously expensive. One of the most effective solutions is to transfer the knowledge from existing labeled source data to unlabeled target data. Howe…
Facial expression recognition (FER) based on the convolutional neural network (CNN) in the wild have numerous challenges. For instance, the complexity of the network model makes FER tasks difficult to deploy on portable devices. Some approaches design lightweight networks to reduce the model size, w…
We justify the fast equilibrium conjecture on stochastic gradient descent from (Li et al. 2020) under the assumptions that critical points are non-degenerate and the stochastic noise is a standard Gaussian. In this case, we prove an SGD with constant effective learning rate consists of three stages:…
In this work, we explore the challenging task of generating 3D shapes from text. Beyond the existing works, we propose a new approach for text-guided 3D shape generation, capable of producing high-fidelity shapes with colors that match the given text description. This work has several technical cont…
Learning-based classifiers are susceptible to adversarial examples. Existing defence methods are mostly devised on individual classifiers. Recent studies showed that it is viable to increase adversarial robustness by promoting diversity over an ensemble of models. In this paper, we propose adversari…
Recently, 3D medical image reconstruction (MIR) and segmentation (MIS) based on deep neural networks have been developed with promising results, and attention mechanism has been further designed for performance enhancement. However, the large size of 3D volume images poses a great computational chal…
In this paper, we present a novel approach to synthesize realistic images based on their semantic layouts. It hypothesizes that for objects with similar appearance, they share similar representation. Our method establishes dependencies between regions according to their appearance correlation, yield…
In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option severely hurts the detection performance. This paper focuses on boosting the performance of a low-resolution model, by distilling knowledge from…
Knowledge distillation (KD) transfers the dark knowledge from cumbersome networks (teacher) to lightweight (student) networks and expects the student to achieve more promising performance than training without the teacher's knowledge. However, a counter-intuitive argument is that better teachers do…
Recently, removing rain streaks from videos has drawn wide concerns in vision and multimedia communities. But existing works ignore the depicts of image inherent structure and rain location to cause details loss, and their adopted manners of exploiting temporal information are still insufficient. In…
Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled with a Markov chain. It is still not sufficient for categories with complicated structures. In this paper, we characteriz…
Latent fingerprint reconstruction is a vital preprocessing step for its identification. This task is very challenging due to not only existing complicated degradation patterns but also its scarcity of paired training data. To address these challenges, we propose a novel generative adversarial networ…
With numerous coding tools adopted in the forthcoming Versatile Video Coding (VVC) standard, much less work has been dedicated to study the corresponding Rate-Distortion (R-D) characteristics. This paper proposes a new quadratic R-D model for Versatile Video Coding. In particular, based on the propo…
In this paper, we propose a camera control system towards occasionally videoing preassigned objects. Based on the technique of real-time visual detection and tracking, using the Kalman filter and re-identification (ReID), we propose continuous composition of lens, based on the atomic rules of shots,…
Recent semantic segmentation methods model the relationship between pixels to construct the contextual representations. In this paper, we introduce the \emph{Region Attention Network} (RANet), a novel attention network for modeling the relationship between object regions. RANet divides the image int…
Blind inpainting is a task to automatically complete visual contents without specifying masks for missing areas in an image. Previous works assume missing region patterns are known, limiting its application scope. In this paper, we relax the assumption by defining a new blind inpainting setting, mak…
In this paper, we present an effective convolutional neural network (CNN) for object counting in video surveillance, namely multi-scale density map regressor (MSDMR). In contrast to existing CNN-based methods that achieve high accuracy by means of empirically increasing the model capacity with more…
Vehicle license plate (VLP) super-resolution (SR) is of great demand in intelligent traffic systems. Super-Resolution for extremely low-resolution VLP remains challenging and the state-of-the-art SR methods hardly provide satisfying results for low-resolution (LR) VLPs. In this study, from a new per…
This paper studies the fundamental problem of extrapolating visual context using deep generative models, i.e., extending image borders with plausible structure and details. This seemingly easy task actually faces many crucial technical challenges and has its unique properties. The two major issues a…
In this paper, we propose a reliable video storage architecture in hybrid SLC/MLC storage systems. In this architecture, the video stream is reconstructed as the key cluster and the non-key cluster according to the importance of video restoration. The key cluster is stored in SLC blocks to ensure th…
In order to scale standard Gaussian process (GP) regression to large-scale datasets, aggregation models employ factorized training process and then combine predictions from distributed experts. The state-of-the-art aggregation models, however, either provide inconsistent predictions or require time-…
In this paper, we propose a generative multi-column network for image inpainting. This network synthesizes different image components in a parallel manner within one stage. To better characterize global structures, we design a confidence-driven reconstruction loss while an implicit diversified MRF r…
Single image dehazing is an ill-posed problem. Most existing works use the atmospheric scattering model (ASM) [1] and some natural priors to dehazing. Recently, DehazeNet [2] was developed using deep learning approach achieves the state-of-the-art results on many test hazy images, which motivates us…
Novelty detection, which aims to determine whether a given data belongs to any category of training data or not, is considered to be an important and challenging problem in areas of Pattern Recognition, Machine Learning, etc. Recently, kernel null space method (KNDA) was reported to have state-of-th…
Robust and efficient image alignment remains a challenging task, due to the massiveness of images, great illumination variations between images, partial occlusion and corruption. To address these challenges, we propose an online image alignment method via subspace learning from image gradient orient…
We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech–two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks, end-to-end learning allows us to handle a diverse variety of s…
Wireless capsule endoscopy (WCE) is an innovative solution for gastrointestinal disease detection. The image quality of WCE is not satisfactory for medical applications since some of them are dark or hazy. For the purpose of improving WCE image quality, we take a new way to establish a parametric im…
Stochastic partition processes in a product space play an important role in modeling relational data. Recent studies on the Mondrian process have introduced more flexibility into the block structure in relational models. A side-effect of such high flexibility is that, in data sparsity scenarios, the…