paper-with-me

Papers

KeyVideoLLM: Towards Large-scale Video Keyframe Selection

2024-07-03 · Hao Liang, Jiapeng Li, Tianyi Bai, Xijie Huang, Linzhuang Sun, Zhengren Wang, Conghui He, Bin Cui, Chong Chen, Wentao Zhang

Recently, with the rise of web videos, managing and understanding large-scale video datasets has become increasingly important. Video Large Language Models (VideoLLMs) have emerged in recent years due to their strong video understanding capabilities. However, training and inference processes for VideoLLMs demand vast amounts of data, presenting significant challenges to data management, particularly regarding efficiency, robustness, and effectiveness. In this work, we present KeyVideoLLM, a text-video frame similarity-based keyframe selection method designed to manage VideoLLM data efficiently, robustly, and effectively. Specifically, KeyVideoLLM achieves a remarkable data compression rate of up to 60.9 times, substantially lowering disk space requirements, which proves its high efficiency. Additionally, it maintains a 100% selection success rate across all video formats and scales, enhances processing speed by up to 200 times compared to existing keyframe selection methods, and does not require hyperparameter tuning. Beyond its outstanding efficiency and robustness, KeyVideoLLM further improves model performance in video question-answering tasks during both training and inference stages. Notably, it consistently achieved the state-of-the-art (SoTA) experimental results on diverse datasets.

📄 PDF Abstract BibTeX arXiv:2407.03104

Code (0)

등록된 구현이 없습니다.

Tasks

Data CompressionManagementQuestion AnsweringVideo Question AnsweringVideo Understanding

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

K-frames: Scene-Driven Any-k Keyframe Selection for long video understanding

2025-10-14 · Yifeng Yao, Yike Yun, Jing Wang, Huishuai Zhang 외 arxiv

Multimodal Large Language Models (MLLMs) have demonstrated significant capabilities in image understanding, but long-video are constrained by context windows and computational cost. Uniform frame sampling often leads to …

Reinforcement Learning

Learning Question-Aware Keyframe Selection with Synthetic Supervision for Video Question Answering

2026-03-16 · Minchan Kwon, Hyounguk Shon, Junmo Kim arxiv

Large multimodal models (LMMs) have recently demonstrated remarkable performance in video question answering (VideoQA), yet reasoning over video remains challenging due to high inference cost and diluted information. Key…

Video Question Answering

FOCUS: Efficient Keyframe Selection for Long Video Understanding

2025-10-31 · Zirui Zhu, Hailun Xu, Yang Luo, Yong Liu 외 arxiv

Multimodal large language models (MLLMs) represent images and video frames as visual tokens. Scaling from single images to hour-long videos, however, inflates the token budget far beyond practical limits. Popular pipelin…

Multi-Armed Bandits

Adaptive Keyframe Sampling for Long Video Understanding

2025-01-01 · CVPR 2025 1 · Xi Tang, Jihao Qiu, Lingxi Xie, Yunjie Tian 외

Multimodal large language models (MLLMs) have enabled open-world visual understanding by injecting visual input as extra tokens into large language models (LLMs) as contexts. However, when the visual input changes fr…

Video Understanding

Coverage-Driven Adaptive Keyframe Selection for Video Understanding

2026-08-01 · Junyang Zhang, Puhan Luo, Chen Tang, Yuxi Shi 외 arxiv

Recent advances in large vision-language models (LVLMs) have enabled long-video understanding and analysis. However, processing the large number of frames in a video incurs substantial computational overhead. Existing me…