7 papers
WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation
Yuhui Zeng, Wang Chen, Jinfa Huang +5
Existing Large Vision-Language Models (LVLMs) struggle with long-form video understanding due to the quadratic computational cost of visual tokens. While recent efficient methods a…
OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models
Jinsen Su, Yongdong Luo, Yuexiao Ma +4
Existing token compression methods for omnimodal large language models typically rely on one modality to determine what to retain in the other. We show that this assumption often b…
Training-Free Multimodal Large Language Model Orchestration
Tianyu Xie, Yuexiao Ma, Yuhang Wu +5
Building interactive omni-modal assistants often relies on end-to-end multimodal alignment to fuse heterogeneous modalities, which incurs substantial data and compute costs and lim…
Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
Yongdong Luo, Xiawu Zheng, Guilin Li +8
Existing large video-language models (LVLMs) struggle to comprehend long videos correctly due to limited context. To address this problem, fine-tuning long-context LVLMs and employ…
Watch Where You Move: Region-aware Dynamic Aggregation and Excitation for Gait Recognition
Binyuan Huang, Yongdong Luo, Xianda Guo +4
Deep learning-based gait recognition has achieved great success in various applications. The key to accurate gait recognition lies in considering the unique and diverse behavior pa…
QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension
Yongdong Luo, Wang Chen, Xiawu Zheng +8
Recent advances in long video understanding typically mitigate visual redundancy through visual token pruning based on attention distribution. However, while existing methods emplo…