Foundation Models for Video Understanding: A Survey

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Madan, Neelu, Moegelmose, Andreas, Modi, Rajat, Rawat, Yogesh S., Moeslund, Thomas B.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917659119976448
author Madan, Neelu
Moegelmose, Andreas
Modi, Rajat
Rawat, Yogesh S.
Moeslund, Thomas B.
author_facet Madan, Neelu
Moegelmose, Andreas
Modi, Rajat
Rawat, Yogesh S.
Moeslund, Thomas B.
contents Video Foundation Models (ViFMs) aim to learn a general-purpose representation for various video understanding tasks. Leveraging large-scale datasets and powerful models, ViFMs achieve this by capturing robust and generic features from video data. This survey analyzes over 200 video foundational models, offering a comprehensive overview of benchmarks and evaluation metrics across 14 distinct video tasks categorized into 3 main categories. Additionally, we offer an in-depth performance analysis of these models for the 6 most common video tasks. We categorize ViFMs into three categories: 1) Image-based ViFMs, which adapt existing image models for video tasks, 2) Video-Based ViFMs, which utilize video-specific encoding methods, and 3) Universal Foundational Models (UFMs), which combine multiple modalities (image, video, audio, and text etc.) within a single framework. By comparing the performance of various ViFMs on different tasks, this survey offers valuable insights into their strengths and weaknesses, guiding future advancements in video understanding. Our analysis surprisingly reveals that image-based foundation models consistently outperform video-based models on most video understanding tasks. Additionally, UFMs, which leverage diverse modalities, demonstrate superior performance on video tasks. We share the comprehensive list of ViFMs studied in this work at: \url{https://github.com/NeeluMadan/ViFM_Survey.git}
format Preprint
id arxiv_https___arxiv_org_abs_2405_03770
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Foundation Models for Video Understanding: A Survey
Madan, Neelu
Moegelmose, Andreas
Modi, Rajat
Rawat, Yogesh S.
Moeslund, Thomas B.
Computer Vision and Pattern Recognition
Video Foundation Models (ViFMs) aim to learn a general-purpose representation for various video understanding tasks. Leveraging large-scale datasets and powerful models, ViFMs achieve this by capturing robust and generic features from video data. This survey analyzes over 200 video foundational models, offering a comprehensive overview of benchmarks and evaluation metrics across 14 distinct video tasks categorized into 3 main categories. Additionally, we offer an in-depth performance analysis of these models for the 6 most common video tasks. We categorize ViFMs into three categories: 1) Image-based ViFMs, which adapt existing image models for video tasks, 2) Video-Based ViFMs, which utilize video-specific encoding methods, and 3) Universal Foundational Models (UFMs), which combine multiple modalities (image, video, audio, and text etc.) within a single framework. By comparing the performance of various ViFMs on different tasks, this survey offers valuable insights into their strengths and weaknesses, guiding future advancements in video understanding. Our analysis surprisingly reveals that image-based foundation models consistently outperform video-based models on most video understanding tasks. Additionally, UFMs, which leverage diverse modalities, demonstrate superior performance on video tasks. We share the comprehensive list of ViFMs studied in this work at: \url{https://github.com/NeeluMadan/ViFM_Survey.git}
title Foundation Models for Video Understanding: A Survey
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.03770