58 accepted papers
Multi-agent LLM debates are increasingly deployed in domains such as policy analysis and city planning, where no objective ground truth exists. Despite this, debate quality is typically evaluated using outcome-based proxies such as LLM-as-judge scores that provide little insight into whether meaning…
The integration of vision-language models (VLMs) is driving a new generation of embodied agents capable of operating in human-centered environments. However, as deployment expands, these systems face growing safety risks, particularly when executing hazardous instructions. Current safety evaluation
We present AudioGen-Omni - a unified approach based on multimodal diffusion transformers (MMDit), capable of generating high-fidelity audio, speech, and song coherently synchronized with the input video. AudioGen-Omni introduces a novel joint training paradigm that seamlessly integrates large-scale…
Despite extensive research on tactile sensing, exploiting it to model and interpret the external world remains largely underexplored. We propose a unified framework that leverages vision-based tactile sensors to construct fine-grained object models, enhancing situational understanding. This frame wo
In real-world scenarios, multi-view cameras are typically employed for fine-grained manipulation tasks. Existing approaches (e.g., ACT ) tend to treat multi-view features equally and directly concatenate them for policy learning. How ever, it will introduce redundant visual information and bring hig…
Time series forecasting faces a fundamental challenge: the uneven distribution of predictive importance in time series data, where some specific time points and feature combinations carry disproportionately predictive power. As a result, uniform processing methods that treat all data alike inevitabl
While Multimodal Large Language Models (MLLMs) show immense promise for achieving truly human-like interactions, progress is hindered by the lack of fine-grained evaluation frameworks for human-centered scenarios, encompassing both the understanding of complex human intentions and the provision of e
3D Referring Expression segmentation (3D-RES) is an emerging field that segments 3D objects in point cloud scenes based on given referring expressions. Although existing methods have achieved substantial progress, they primarily focus on semantic cues and often overlook spatial relations, which are
Miniature amphibious robots are capable of performing various tasks in complex terrestrial and aquatic environments due to their superior adaptability. However, the mobility of existing miniature amphibious robots in such environments is limited by their complex locomotion systems and single mode of
In real-world scenarios, multi-view cameras are typically employed for fine-grained manipulation tasks. Existing approaches (e.g., ACT [1]) tend to treat multi-view features equally and directly concatenate them for policy learning. However, it will introduce redundant visual information and bring h
Mixture-of-Experts (MoE) models have become increasingly powerful in multimodal learning by enabling modular specialization across modalities. However, their effectiveness remains unclear when additional modalities introduce more noise than complementary information. Existing approaches, such as the
Temporal sentence grounding is a challenging task that aims to localize the moment spans relevant to a language description. Although recent DETR-based models have achieved notable progress by leveraging multiple learnable moment queries, they suffer from overlapped and redundant proposals, leading…
Learning generalizable robotic manipulation policies remains a key challenge due to the scarcity of diverse real-world training data. While recent approaches have attempted to mitigate this through self-supervised representation learning, most either rely on 2D vision pretraining paradigms such as m…
Sufficient cross-task interaction is crucial for success in multi-task dense prediction. However, sufficient interaction often results in high computational complexity, forcing existing methods to face the trade-off between interaction completeness and computational efficiency. To address this limit…
Large language models (LLMs) augmented with retrieval systems have demonstrated significant potential in handling knowledge-intensive tasks. However, these models often struggle with unfaithfulness issues, generating outputs that either ignore the retrieved context or inconsistently blend it with th…
Robotic manipulation in high-precision tasks is essential for numerous industrial and real-world applications where accuracy and speed are required. Yet current diffusion-based policy learning methods generally suffer from low computational efficiency due to the iterative denoising process during in…
Video temporal grounding is a critical video understanding task, which aims to localize moments relevant to a language description. The challenge of this task lies in distinguishing relevant and irrelevant moments. Previous methods focused on learning continuous features exhibit weak differentiation…
Robotic manipulation based on visual observations and natural language instructions is a long-standing challenge in robotics. Yet prevailing approaches model action distribution by adopting explicit or implicit representations, which often struggle to achieve a trade-off between accuracy and efficie…
Despite the rapid and substantial advancements in object detection, it continues to face limitations imposed by pre-defined category sets. Current methods for visual grounding primarily focus on how to better leverage the visual backbone to generate text-tailored visual features, which may require a…
World models allow agents to simulate the consequences of actions in imagined environments for planning, control, and long-horizon decision-making. However, existing autoregressive world models struggle with visually coherent predictions due to disrupted spatial structure, inefficient decoding, and…
The performance of current scene graph generation models is affected by training with cross-entropy loss, exacerbating the problem of prediction bias stemming from biased training data. Energy-based model adopts a learning method for joint image and scene graph to alleviate this challenge. However,…
Embodied localization based on vision and natural language dialogues presents a persistent challenge in embodied intelligence. Existing methods often approach this task as an image translation problem, leveraging encoder-decoder architectures to predict heatmaps. However, these methods frequently ex…
This paper introduces VisHall3D, a novel two-stage framework for monocular semantic scene completion that aims to address the issues of feature entanglement and geometric inconsistency prevalent in existing methods. VisHall3D decomposes the scene completion task into two stages: reconstructing the v…
"Deep learning approaches have made significant success in single-view 3D reconstruction, but they often rely on expensive 3D annotations for training. Recent efforts tackle this challenge by adopting an analysis-by-synthesis paradigm to learn 3D reconstruction with only 2D annotations. However, exi…
"Semi-supervised learning has emerged as a widely adopted technique in the field of medical image segmentation. The existing works either focuses on the construction of consistency constraints or the generation of pseudo labels to provide high-quality supervisory signals, whose main challenge mainly…
"3D anomaly detection plays a crucial role in monitoring parts for localized inherent defects in precision manufacturing. Embedding-based and reconstruction-based approaches are among the most popular and successful methods. However, there are two major challenges to the practical application of the…
Visual Grounding aims to localize the referring object in an image given a natural language expression. Recent advancements in DETR-based visual grounding methods have attracted considerable attention, as they directly predict the coordinates of the target object without relying on additional effort…
Video Person Re-Identification (Re-ID) is a task of retrieving persons from multi-camera surveillance systems. Despite the progress made in leveraging spatio-temporal information in videos, occlusion in dense crowds still hinders further progress. To address this issue, we propose a Temporal Correla…
Multi-Object Tracking (MOT) encompasses various tracking scenarios each characterized by unique traits. Effective trackers should demonstrate a high degree of generalizability across diverse scenarios. However existing trackers struggle to accommodate all aspects or necessitate hypothesis and experi…
This letter presents a hierarchical motion planner for generating smooth and feasible trajectories for autonomous vehicles in unstructured environments with static and moving obstacles. The framework enables real-time computation by progressively shrinking the solution space. First, a graph searcher
Semi-Supervised Temporal Action Localization (SS-TAL) aims to improve the generalization ability of action detectors with large-scale unlabeled videos. Albeit the recent advancement, one of the major challenges still remains: noisy pseudo labels hinder efficient learning on abundant unlabeled videos…
The main challenge of Multi-Object Tracking (MOT) lies in maintaining a continuous trajectory for each target. Existing methods often learn reliable motion patterns to match the same target between adjacent frames and discriminative appearance features to re-identify the lost targets after a long pe…
Forecasting the future trajectory of pedestrians is an important task in computer vision with a range of applications, from security cameras to autonomous driving. It is very challenging because pedestrians not only move individually across time but also interact spatially, and the spatial and tempo…
Learning discriminative features from very few labeled samples to identify novel classes has received increasing attention in skeleton-based action recognition. Existing works aim to learn action-specific embeddings by exploiting either intra-skeleton or inter-skeleton spatial associations, which ma…
Deep neural networks (DNNs) are known to be vulnerable to both backdoor attacks as well as adversarial attacks. In the literature, these two types of attacks are commonly treated as distinct problems and solved separately, since they belong to training-time and inference-time attacks respectively. H…
Pedestrian trajectory prediction is critical in many vision tasks but challenging due to the multimodality of the future trajectory. Most existing methods predict multimodal trajectories conditioned by goals (future endpoints) or instances (all future points). However, goal-conditioned methods ignor…
Pedestrian trajectory prediction is an essentially connecting link to understanding human behavior. Recent works achieve state-of-the-art performance gained from the hand-designed post-processing, e.g., clustering. However, this post-processing suffers from expensive inference time and neglects the…
Pedestrian trajectory prediction is crucial in many practical applications due to the diversity of pedestrian movements, such as social interactions and individual motion behaviors. With similar observable trajectories and social environments, different pedestrians may make completely different futu…
Recent studies have found that removing the norm-bounded projection and increasing search steps in adversarial training can significantly improve robustness. However, we observe that a too large number of search steps can hurt accuracy. We aim to obtain strong robustness efficiently using fewer step…
A common approach to Temporal Action Localization (TAL) is to generate action proposals and then perform action classification and localization on them. For each proposal, existing methods universally use a shared proposal-level representation for both tasks. However, our analysis indicates that thi…
The main challenge of Temporal Action Localization is to retrieve subtle human actions from various co-occurring ingredients, e.g., context and background, in an untrimmed video. While prior approaches have achieved substantial progress through devising advanced action detectors, they still suffer f…
Understanding the multiple socially-acceptable future behaviors is an essential task for many vision applications. In this paper, we propose a tree-based method, termed as Social Interpretable Tree (SIT), to address this multi-modal prediction task, where a hand-crafted tree is built depending on th…
The object of Weakly-supervised Temporal Action Localization (WS-TAL) is to localize all action instances in an untrimmed video with only video-level supervision. Due to the lack of frame-level annotations during training, current WS-TAL methods rely on attention mechanisms to localize the foregroun…
Effectively tackling the problem of temporal action localization (TAL) necessitates a visual representation that jointly pursues two confounding goals, i.e., fine-grained discrimination for temporal localization and sufficient visual invariance for action classification. We address this challenge by…
Unsupervised person re-identification (Re-ID) remains challenging due to the lack of ground-truth labels. Existing methods often rely on estimated pseudo labels via iterative clustering and classification, and they are unfortunately highly susceptible to performance penalties incurred by the inaccur…
Recent studies unveil the vulnerabilities of deep ranking models, where an imperceptible perturbation can trigger dramatic changes in the ranking result. While previous attempts focus on manipulating absolute ranks of certain candidates, the possibility of adjusting their relative order remains unde…
Pedestrian trajectory prediction is a key technology in autopilot, which remains to be very challenging due to complex interactions between pedestrians. However, previous works based on dense undirected interaction suffer from modeling superfluous interactions and neglect of trajectory motion tenden…
Understanding complex social interactions among agents is a key challenge for trajectory prediction. Most existing methods consider the interactions between pairwise traffic agents or in a local area, while the nature of interactions is unlimited, involving an uncertain number of agents and non-loca…
Weakly-supervised Temporal Action Localization (WS-TAL) methods learn to localize temporal starts and ends of action instances in a video under only video-level supervision. Existing WS-TAL methods rely on deep features learned for action recognition. However, due to the mismatch between classificat…
Graph convolutional networks (GCNs) have been applied to 3D human pose estimation (HPE) from 2D body joint detections and have shown encouraging performance. One limitation of the vanilla graph convolution is that it models the relationships between neighboring nodes via a shared weight matrix. This…
Deep Neural Network (DNN) classifiers are vulnerable to adversarial attack, where an imperceptible perturbation could result in misclassification. However, the vulnerability of DNN-based image ranking systems remains under-explored. In this paper, we propose two attacks against deep ranking systems,…
The image-based fine-grained identification of individual giant pandas (Ailuropoda melanoleuca) is an emerging technology, and it is extraordinarily challenging due to the extremely subtle visual differences between individual giant pandas and limited annotated training data. To address these challe…
Weakly-supervised Temporal Action Localization (W-TAL) aims to classify and localize all action instances in an untrimmed video under only video-level supervision. However, without frame-level annotations, it is challenging for W-TAL methods to identify false positive action proposals and generate a…
For Zero-Shot Learning (ZSL), the Nearest Neighbor (NN) search is generally conducted for classification, which may cause unacceptable computational complexity for large-scale datasets. To compress zero-shot classes by the trained quantizer for efficient search, it tends to induce large quantization…
Weakly-supervised temporal action localization (WS-TAL) is a promising but challenging task with only video-level action categorical labels available during training. Without requiring temporal action boundary annotations in training data, WS-TAL could possibly exploit automatically retrieved video…
We develop a unified framework for complex event retrieval, recognition and recounting. The framework is based on a compact video representation that exploits the temporal correlations in image features. Our feature alignment procedure identifies and removes the feature redundancies across frames an…
We address the problem of dense visual-semantic embedding that maps not only full sentences and whole images but also phrases within sentences and salient regions within images into a multimodal embedding space. As a result, we can produce several region-oriented and expressive phrases rather than j…
To address the non-stationary property of aging patterns, age estimation can be cast as an ordinal regression problem. However, the processes of extracting features and learning a regression model are often separated and optimized independently in previous work. In this paper, we propose an End-to-E…