29 accepted papers
This paper pays attention to open-vocabulary 3D object affordance grounding (OVAG), which aims to localize affordance regions on 3D objects by leveraging interaction images or textual instructions. Most existing methods treat interaction images as sources of external affordance knowledge and align t…
Recent graph-based RAG approaches leverage knowledge graphs by extracting entities from a query to fetch their associated relationships and metadata. However, relying solely on entity extraction often results in the misinterpretation or omission of latent critical information and relationships. This…
Diffusion policy has shown impressive performance in robotic manipulation tasks while struggling with out-of-distribution shifts and limited demonstrations. Recent advances primarily focus on improving geometric or perceptual representations for diffusion policy. However, these approaches rely heavi
Knowledge distillation (KD) aims to improve the performance of lightweight student networks under the guidance of pre-trained teachers. However, the large capacity gap between teachers and students limits the distillation gains. Previous methods addressing this problem have two weaknesses. First, mo…
Suicide remains a major global mental health challenge, and early intervention hinges on recognizing signs of suicidal ideation. In private conversations, such ideation is often expressed in subtle or conflicted ways, making detection especially difficult. Existing data sets are mainly based on publ
In Multiple Instance Learning (MIL) for Whole Slide Image (WSI) analysis, attention mechanisms are often employed to weigh the importance of different instances. However, global attention may lead to feature homogenization and overlook tissue differences. Adding local attention can capture these var…
Navigating dense and dynamic environments poses a significant challenge for autonomous driving systems, owing to the intricate nature of multimodal interaction, wherein the actions of various traffic participants and the autonomous vehicle are complex and implicitly coupled. In this paper, we propos
Large Language Models (LLMs) have demonstrated remarkable performance across various domains, showcasing significant potential for long-term time series forecasting (LTSF), and consequently attracting substantial research interest. In LTSF, temporal decomposition has been widely adopted in existing…
Image denoising enhances image quality, serving as a foundational technique across various computational photography applications. The obstacle to clean image acquisition in real scenarios necessitates the development of self-supervised image denoising methods only depending on noisy images, especia…
Backdoor unalignment attacks against Large Language Models (LLMs) enable the stealthy compromise of safety alignment using a hidden trigger while evading normal safety auditing. These attacks pose significant threats to the applications of LLMs in the real-world Large Language Model as a Service (LL…
Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of tasks in different domains. However, they sometimes generate responses that are logically coherent but factually incorrect or misleading, which is known as LLM hallucinations. Data-driven supervised methods tr…
Backdoor attacks pose an increasingly severe security threat to Deep Neural Networks (DNNs) during their development stage. In response, backdoor sample purification has emerged as a promising defense mechanism, aiming to eliminate backdoor triggers while preserving the integrity of the clean conten…
Recently an audio-visual segmentation (AVS) task has been introduced aiming to group pixels with sounding objects within a given video. This task necessitates a first-ever audio-driven pixel-level understanding of the scene posing significant challenges. In this paper we propose an innovative audio-…
Listening head generation aims to synthesize a non-verbal responsive listener head by modeling the correlation between the speaker and the listener in dynamic conversion. The applications of listener agent generation in virtual interaction have promoted many works achieving diverse and fine-grained…
Stock price forecasting has remained an extremely challenging problem for many decades due to the high volatility of the stock market. Recent efforts have been devoted to modeling complex stock correlations toward joint stock price forecasting. Existing works share a common neural architecture that…
Recent research on mobile robots has focused on increasing their adaptability to unpredictable and unstructured environments using soft materials and structures. However, the determination of key design parameters and control over these compliant robots are predominantly iterated through experiments…
Digital mental health (DMH) interventions, such as text-message-based lessons and activities, offer immense potential for accessible mental health support. While these interventions can be effective, real-world experimental testing can further enhance their design and impact. Adaptive experimentatio…
Three-fingered hands can offer more contact points and flexible fingertip configurations, enabling complex grasping modes and finer manipulations for objects of various shapes and sizes. However, existing research on visual-tactile integrated robotic grasping primarily focuses on grippers, and lacks
"Human-centric perception (detection, segmentation, pose estimation, and attribute analysis) is a long-standing problem for computer vision. This paper introduces a unified and versatile framework (HQNet) for single-stage multi-person multi-task human-centric perception (HCP). Our approach centers o…
Recently, the text-to-table generation task has attracted increasing attention due to its wide applications. In this aspect, the dominant model formalizes this task as a sequence-to-sequence generation task and serializes each table into a token sequence during training by concatenating all rows in…
Existing studies for rumor detection rely heavily on a large number of labeled data to operate in a fully-supervised manner. However, manual data annotation in realistic cases is very expensive and time-consuming. In this paper, we propose a novel self-supervised Relation-Event based Contrastive Lea…
Generating safe and non-conservative behaviors in dense, dynamic environments remains challenging for automated vehicles due to the stochastic nature of traffic participants' behaviors and their implicit interaction with the ego vehicle. This letter presents a novel planning framework, Multipolicy A
In this paper, we present Iterative Symmetry Completion Network (ISCNet), a single depth-image shape completion method that exploits reflective symmetry cues to obtain more detailed shapes. The efficacy of single depth-image shape completion methods is often sensitive to the accuracy of the symmetry…
Heterogeneous graph neural networks (HGNs) are prominent approaches to node classification tasks on heterogeneous graphs. Despite the superior performance, insights about the predictions made from HGNs are obscure to humans. Existing explainability techniques are mainly proposed for GNNs on homogene…
Most human activities in daily living or professional work rely on upper body motion. Measuring upper body motion is essential for many applications such as health evaluation, rehabilitation, human power augmentation, skill transferring, etc. Computer vision-based systems have been widely used to di…
Geometry problem solving is a well-recognized testbed for evaluating the high-level multi-modal reasoning capability of deep models. In most existing works, two main geometry problems: calculation and proving, are usually treated as two specific tasks, hindering a deep model to unify its reasoning c…
Multi-goal reaching is an important problem in reinforcement learning needed to achieve algorithmic generalization. Despite recent advances in this field, current algorithms suffer from three major challenges: high sample complexity, learning only a single way of reaching the goals, and difficultie…
Contextualised word embeddings is a powerful tool to detect contextual synonyms. However, most of the current state-of-the-art (SOTA) deep learning concept extraction methods remain supervised and underexploit the potential of the context. In this paper, we propose a self-supervised pre-training app…
The increasing amount of urban data enable us to investigate urban dynamics, assist urban planning, and eventually, make our cities more livable and sustainable. In this paper, we focus on learning an embedding space from urban data for urban regions. For the first time, we propose a multi-view join…