paper-with-me

Papers

LVBench: An Extreme Long Video Understanding Benchmark

2024-06-12 · Weihan Wang, Zehai He, Wenyi Hong, Yean Cheng, Xiaohan Zhang, Ji Qi, Xiaotao Gu, Shiyu Huang, Bin Xu, Yuxiao Dong, Ming Ding, Jie Tang

Recent progress in multimodal large language models has markedly enhanced the understanding of short videos (typically under one minute), and several evaluation datasets have emerged accordingly. However, these advancements fall short of meeting the demands of real-world applications such as embodied intelligence for long-term decision-making, in-depth movie reviews and discussions, and live sports commentary, all of which require comprehension of long videos spanning several hours. To address this gap, we introduce LVBench, a benchmark specifically designed for long video understanding. Our dataset comprises publicly sourced videos and encompasses a diverse set of tasks aimed at long video comprehension and information extraction. LVBench is designed to challenge multimodal models to demonstrate long-term memory and extended comprehension capabilities. Our extensive evaluations reveal that current multimodal models still underperform on these demanding long video understanding tasks. Through LVBench, we aim to spur the development of more advanced models capable of tackling the complexities of long video comprehension. Our data and code are publicly available at: https://lvbench.github.io.

📄 PDF Abstract BibTeX arXiv:2406.08035

Code (1)

THUDM/LVBench 공식 구현

Tasks

Decision MakingVideo Understanding

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Flash-VStream: Efficient Real-Time Understanding for Long Video Streams

2025-06-30 · Haoji Zhang, Yiqin Wang, Yansong Tang, Yong liu 외

Benefiting from the advances in large language models and cross-modal alignment, existing multimodal large language models have achieved prominent performance in image and short video understanding. However, the understa…

cross-modal alignmentEgoSchemaMMEMVBench+2

Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers

2025-03-14 · Weiming Ren, Wentao Ma, Huan Yang, Cong Wei 외

State-of-the-art transformer-based large multimodal models (LMMs) struggle to handle hour-long video inputs due to the quadratic complexity of the causal self-attention operations, leading to high computational costs dur…

GPUMambaToken ReductionVideo Understanding

One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding

2026-04-15 · Zheyu Zhang, Ziqi Pang, Shixing Chen, Xiang Hao 외 arxiv

Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames. With each video frame typically expanding into tens or hundreds of tokens, the limited conte…

VideoDeepResearch: Long Video Understanding With Agentic Tool Using

2025-06-12 · Huaying Yuan, Zheng Liu, Junjie Zhou, Ji-Rong Wen 외

Long video understanding (LVU) presents a significant challenge for current multi-modal large language models (MLLMs) due to the task's inherent complexity and context window constraint. It is widely assumed that address…

MMEVideo MMEVideo Understanding

AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding

2026-03-30 · Haozhe Qi, Kevin Qu, Mahdi Rad, Rui Wang 외 arxiv

Long video understanding remains challenging for Multi-modal Large Language Models (MLLMs) due to high memory costs and context-length limits. Prior approaches mitigate this by scoring and selecting frames/tokens within …