3 papers
cs.CV2024
TRACE: Temporal Grounding Video LLM via Causal Event Modeling
Yongxin Guo, Jingyu Liu, Mingda Li +3
Video Temporal Grounding (VTG) is a crucial capability for video understanding models and plays a vital role in downstream tasks such as video browsing and editing. To effectively…
cs.CV2024
Enhancing Long Video Understanding via Hierarchical Event-Based Memory
Dingxin Cheng, Mingda Li, Jingyu Liu +5
Recently, integrating visual foundation models into large language models (LLMs) to form video understanding systems has attracted widespread attention. Most of the existing models…
cs.CV2024
TC-LLaVA: Rethinking the Transfer from Image to Video Understanding with Temporal Considerations
Mingze Gao, Jingyu Liu, Mingda Li +5
Multimodal Large Language Models (MLLMs) have significantly improved performance across various image-language applications. Recently, there has been a growing interest in adapting…