Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding
Ziyi Wang, Haoran Wu, Yiming Rong +5
Long video understanding is a complex task that requires both spatial detail and temporal awareness. While Vision-Language Models (VLMs) obtain frame-level understanding capabiliti…
cs.CV2024
Adaptive Runge-Kutta Dynamics for Spatiotemporal Prediction
Xuanle Zhao, Yue Sun, Ziyi Wang +2
Spatiotemporal prediction is important in solving natural problems and processing video frames, especially in weather forecasting and human action recognition. Recent advances atte…