作者位次 #4/6ACL 2026OralOutstanding Paper· Natural Language Processing
V i LL - E : Video LLM Embeddings for Retrieval
Rohit Gupta · Jayakrishnan Unnikrishnan · Fan Fei · Sheng Liu · Son Tran · Mubarak Shah
摘要
Video Large Language Models (VideoLLMs) excel at video understanding tasks where outputs are textual, such as Video Question Answering and Video Captioning. However, they underperform specialized embedding-based models in Retrieval tasks, such as Text-toVideo Retrieval and Moment Retrieval. We in...