VidCompress: Memory-Enhanced Temporal Compression for Video Understanding in Large Language Models

15 October 2024

Papers citing "VidCompress: Memory-Enhanced Temporal Compression for Video Understanding in Large Language Models"

2 / 2 papers shown

Title
VideoSAVi: Self-Aligned Video Language Models without Human Supervision Yogesh Kulkarni Pooyan Fazli VLM 103 2 0 01 Dec 2024
Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models Yang Jiao Shaoxiang Chen Zequn Jie Wenke Huang Lin Ma Yueping Jiang MLLM 42 18 0 12 Mar 2024