Related papers: Interaction-aware Representation Modeling with Co-…

How can agents learn internal models that veridically represent interactions with the real world is a largely open question. As machine learning is moving towards representations containing not just observational but also interventional…

Transformers are increasingly dominating multi-modal reasoning tasks, such as visual question answering, achieving state-of-the-art results thanks to their ability to contextualize information using the self-attention and co-attention…

Humanoid agents are expected to emulate the complex coordination inherent in human social behaviors. However, existing methods are largely confined to single-agent scenarios, overlooking the physically plausible interplay essential for…

Accurately modeling detailed interactions between human/hand and object is an appealing yet challenging task. Current multi-view capture systems are only capable of reconstructing multiple subjects into a single, unified mesh, which fails…

This report describes the 2nd place solution to the ECCV 2022 Human Body, Hands, and Activities (HBHA) from Egocentric and Multi-view Cameras Challenge: Action Recognition. This challenge aims to recognize hand-object interaction in an…

Human interaction recognition is very important in many applications. One crucial cue in recognizing an interaction is the interactive body parts. In this work, we propose a novel Interaction Graph Transformer (IGFormer) network for…

Incorporating knowledge bases (KB) into end-to-end task-oriented dialogue systems is challenging, since it requires to properly represent the entity of KB, which is associated with its KB context and dialogue context. The existing works…

Transformer-based architectures have advanced medical image analysis by effectively modeling long-range dependencies, yet they often struggle in 3D settings due to substantial memory overhead and insufficient capture of fine-grained local…

In the field of cross-modal retrieval, single encoder models tend to perform better than dual encoder models, but they suffer from high latency and low throughput. In this paper, we present a dual encoder model called BagFormer that…

Until recently, the question of the effective inductive bias of deep models on tabular data has remained unanswered. This paper investigates the hypothesis that arithmetic feature interaction is necessary for deep tabular learning. To test…

This paper addresses a novel task of anticipating 3D human-object interactions (HOIs). Most existing research on HOI synthesis lacks comprehensive whole-body interactions with dynamic objects, e.g., often limited to manipulating small or…

Due to various and complicated snow degradations, single image desnowing is a challenging image restoration task. As prior arts can not handle it ideally, we propose a novel transformer, SnowFormer, which explores efficient cross-attentions…

This paper investigates the performance of transformer-based architectures for person identification in natural, face-to-face conversation scenario. We implement and evaluate a two-stream framework that separately models spatial…

Person re-identification aims to retrieve persons in highly varying settings across different cameras and scenarios, in which robust and discriminative representation learning is crucial. Most research considers learning representations…

Transformer-based QA models use input-wide self-attention -- i.e. across both the question and the input passage -- at all layers, causing them to be slow and memory-intensive. It turns out that we can get by without input-wide…

Predicting soccer match outcomes is a challenging task due to the inherently unpredictable nature of the game and the numerous dynamic factors influencing results. While it conventionally relies on meticulous feature engineering, deep…

With the diversification of human-object interaction (HOI) applications and the success of capturing human meshes, HOI reconstruction has gained widespread attention. Existing mainstream HOI reconstruction methods often rely on explicitly…

4D millimeter-wave radar has emerged as a promising sensing modality for autonomous driving due to its robustness and affordability. However, its sparse and weak geometric cues make reliable instance activation difficult, limiting the…

Time-series data are critical in diverse applications, such as industrial monitoring, medical diagnostics, and climate research. However, effectively integrating these high-dimensional temporal signals with natural language for dynamic,…

Recent advances in deep learning have significantly improved facial landmark detection. However, existing facial landmark detection datasets often define different numbers of landmarks, and most mainstream methods can only be trained on a…