8 papers
Contact Matrix: Enhancing Dance Motion Synthesis with Precise Interaction Modeling
Xuhai Chen, Zhi Cen, Huaijin Pi +3
Generating realistic reactive motions, in which one person reacts to the fixed motions of others, is challenging due to strict interaction constraints and a limited feasible soluti…
Knowledge is Power: Advancing Few-shot Action Recognition with Multimodal Semantics from MLLMs
Jiazheng Xing, Chao Xu, Hangjie Yuan +4
Multimodal Large Language Models (MLLMs) have propelled the field of few-shot action recognition (FSAR). However, preliminary explorations in this area primarily focus on generatin…
LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation
Jiazheng Xing, Fei Du, Hangjie Yuan +7
Recent advances in diffusion models have significantly improved text-to-video generation, enabling personalized content creation with fine-grained control over both foreground and…
SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training
Mengmeng Wang, Dengyang Jiang, Liuzhuozheng Li +6
Denoising-based diffusion transformers, despite their strong generation performance, suffer from inefficient training convergence. Existing methods addressing this issue, such as R…
Visual Object Tracking across Diverse Data Modalities: A Review
Mengmeng Wang, Teli Ma, Shuo Xin +5
Visual Object Tracking (VOT) is an attractive and significant research area in computer vision, which aims to recognize and track specific targets in video sequences where the targ…
Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing
Haonan Lin, Mengmeng Wang, Jiahao Wang +7
Text-guided diffusion models have significantly advanced image editing, enabling high-quality and diverse modifications driven by text prompts. However, effective editing requires…