MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hong, Wenyi, Cheng, Yean, Yang, Zhuoyi, Wang, Weihan, Wang, Lefan, Gu, Xiaotao, Huang, Shiyu, Dong, Yuxiao, Tang, Jie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918497369456640
author Hong, Wenyi
Cheng, Yean
Yang, Zhuoyi
Wang, Weihan
Wang, Lefan
Gu, Xiaotao
Huang, Shiyu
Dong, Yuxiao
Tang, Jie
author_facet Hong, Wenyi
Cheng, Yean
Yang, Zhuoyi
Wang, Weihan
Wang, Lefan
Gu, Xiaotao
Huang, Shiyu
Dong, Yuxiao
Tang, Jie
contents In recent years, vision language models (VLMs) have made significant advancements in video understanding. However, a crucial capability - fine-grained motion comprehension - remains under-explored in current benchmarks. To address this gap, we propose MotionBench, a comprehensive evaluation benchmark designed to assess the fine-grained motion comprehension of video understanding models. MotionBench evaluates models' motion-level perception through six primary categories of motion-oriented question types and includes data collected from diverse sources, ensuring a broad representation of real-world video content. Experimental results reveal that existing VLMs perform poorly in understanding fine-grained motions. To enhance VLM's ability to perceive fine-grained motion within a limited sequence length of LLM, we conduct extensive experiments reviewing VLM architectures optimized for video feature compression and propose a novel and efficient Through-Encoder (TE) Fusion method. Experiments show that higher frame rate inputs and TE Fusion yield improvements in motion understanding, yet there is still substantial room for enhancement. Our benchmark aims to guide and motivate the development of more capable video understanding models, emphasizing the importance of fine-grained motion comprehension. Project page: https://motion-bench.github.io .
format Preprint
id arxiv_https___arxiv_org_abs_2501_02955
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models
Hong, Wenyi
Cheng, Yean
Yang, Zhuoyi
Wang, Weihan
Wang, Lefan
Gu, Xiaotao
Huang, Shiyu
Dong, Yuxiao
Tang, Jie
Computer Vision and Pattern Recognition
In recent years, vision language models (VLMs) have made significant advancements in video understanding. However, a crucial capability - fine-grained motion comprehension - remains under-explored in current benchmarks. To address this gap, we propose MotionBench, a comprehensive evaluation benchmark designed to assess the fine-grained motion comprehension of video understanding models. MotionBench evaluates models' motion-level perception through six primary categories of motion-oriented question types and includes data collected from diverse sources, ensuring a broad representation of real-world video content. Experimental results reveal that existing VLMs perform poorly in understanding fine-grained motions. To enhance VLM's ability to perceive fine-grained motion within a limited sequence length of LLM, we conduct extensive experiments reviewing VLM architectures optimized for video feature compression and propose a novel and efficient Through-Encoder (TE) Fusion method. Experiments show that higher frame rate inputs and TE Fusion yield improvements in motion understanding, yet there is still substantial room for enhancement. Our benchmark aims to guide and motivate the development of more capable video understanding models, emphasizing the importance of fine-grained motion comprehension. Project page: https://motion-bench.github.io .
title MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.02955