Ruyang Liu

6

Papers

127

Total Citations

Papers (6)

ST-LLM: Large Language Models Are Effective Temporal Learners

Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow

MUSE: Mamba Is Efficient Multi-scale Learner for Text-video Retrieval

BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning

Contextual Debiasing for Visual Recognition With Causal Mechanisms

Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring