Related papers: Structured Relational Reasoning for Group Activity…

Retrieval-augmented generation (RAG) has become the standard way to ground large language models in external knowledge, but many systems still organize evidence as flat chunks and retrieve it through largely unstructured search. This weak…

For a robot to be called socially intelligent, it must be able to infer users internal states from their current behaviour, predict the users future behaviour, and if required, respond appropriately. In this work, we investigate how robots…

Integrating intelligent systems, such as robots, into dynamic group settings poses challenges due to the mutual influence of human behaviors and internal states. A robust representation of social interaction dynamics is essential for…

We present a novel Multi-Relational Graph Convolutional Network (MRGCN) based framework to model on-road vehicle behaviors from a sequence of temporally ordered frames as grabbed by a moving monocular camera. The input to MRGCN is a…

Text-to-image generative models like DALL-E and Stable Diffusion have revolutionized visual content creation across various applications, including advertising, personalized media, and design prototyping. However, crafting effective textual…

Social relation reasoning aims to identify relation categories such as friends, spouses, and colleagues from images. While current methods adopt the paradigm of training a dedicated network end-to-end using labeled image data, they are…

Content-based collaborative filtering (CCF) predicts user-item interactions based on both users' interaction history and items' content information. Recently, pre-trained language models (PLM) have been used to extract high-quality item…

Robust fine-tuning aims to adapt large foundation models to downstream tasks while preserving their robustness to distribution shifts. Existing methods primarily focus on constraining and projecting current model towards the pre-trained…

Retrieval Augmented Generation (RAG) has become the standard approach for equipping Large Language Models (LLMs) with up-to-date knowledge. However, standard RAG, relying on independent passage retrieval, often fails to capture the…

Group Activity Recognition (GAR) is a fundamental problem in computer vision, with diverse applications in sports video analysis, video surveillance, and social scene understanding. Unlike conventional action recognition, GAR aims to…

Large Language Models (LLMs) achieve strong performance across diverse tasks, but their effectiveness often depends on the quality of the provided context. Retrieval-Augmented Generation (RAG) enriches prompts with external information, but…

Multimodal knowledge graphs (MKGs), which intuitively organize information in various modalities, can benefit multiple practical downstream tasks, such as recommendation systems, and visual question answering. However, most MKGs are still…

Large vision-language models (LVLMs) have witnessed significant progress on visual understanding tasks. However, they often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation.…

In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias and is largely confined to math or science domains. This…

Retrieval-Augmented Generation (RAG) systems are widely adopted in knowledge-intensive NLP tasks, but current evaluations often overlook the structural complexity and multi-step reasoning required in real-world scenarios. These benchmarks…

Scene graph generation (SGG) is built on top of detected objects to predict object pairwise visual relations for describing the image content abstraction. Existing works have revealed that if the links between objects are given as prior…

State-of-the-art text-to-image models excel at photorealistic rendering but often struggle to capture the layout and object relationships implied by complex prompts. Scene graphs provide a natural structural prior, yet previous graph-guided…

Learning latent actions from action-free video has emerged as a powerful paradigm for scaling up controllable world model learning. Latent actions provide a natural interface for users to iteratively generate and manipulate videos. However,…

Group recommendation aims at providing optimized recommendations tailored to diverse groups, enabling groups to enjoy appropriate items. On the other hand, most existing group recommendation methods are built upon deep neural network (DNN)…

Fine-grained video classification requires understanding complex spatio-temporal and semantic cues that often exceed the capacity of a single modality. In this paper, we propose a multimodal framework that fuses video, image, and text…