ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding

29 December 2024

Papers citing "ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding"

6 / 6 papers shown

Title
MR. Video: "MapReduce" is the Principle for Long Video Understanding Ziqi Pang Yu-xiong Wang VLM 32 0 0 22 Apr 2025
Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark Enxin Song Wenhao Chai Weili Xu Jianwen Xie Yuxuan Liu Gaoang Wang 54 0 0 20 Apr 2025
VideoPASTA: 7K Preference Pairs That Matter for Video-LLM Alignment Yogesh Kulkarni Pooyan Fazli 27 0 0 18 Apr 2025
From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment Yucheng Suo Fan Ma Linchao Zhu T. Wang Fengyun Rao Yi Yang LRM 68 0 0 26 Mar 2025
AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding Xiao Wang Qingyi Si Jianlong Wu Shiyu Zhu Li Cao Liqiang Nie VLM 75 2 0 16 Mar 2025
VideoSAVi: Self-Aligned Video Language Models without Human Supervision Yogesh Kulkarni Pooyan Fazli VLM 83 2 0 01 Dec 2024