paper-with-me

홈 › Papers

Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding

2024-03-14 · Guo Chen, Yifei HUANG, Jilan Xu, Baoqi Pei, Zhe Chen, Zhiqi Li, Jiahao Wang, Kunchang Li, Tong Lu, LiMin Wang

Understanding videos is one of the fundamental directions in computer vision research, with extensive efforts dedicated to exploring various architectures such as RNN, 3D CNN, and Transformers. The newly proposed architecture of state space model, e.g., Mamba, shows promising traits to extend its success in long sequence modeling to video modeling. To assess whether Mamba can be a viable alternative to Transformers in the video understanding domain, in this work, we conduct a comprehensive set of studies, probing different roles Mamba can play in modeling videos, while investigating diverse tasks where Mamba could exhibit superiority. We categorize Mamba into four roles for modeling videos, deriving a Video Mamba Suite composed of 14 models/modules, and evaluating them on 12 video understanding tasks. Our extensive experiments reveal the strong potential of Mamba on both video-only and video-language tasks while showing promising efficiency-performance trade-offs. We hope this work could provide valuable data points and insights for future research on video understanding. Code is public: https://github.com/OpenGVLab/video-mamba-suite.

📄 PDF Abstract BibTeX arXiv:2403.09626

Code (1)

opengvlab/video-mamba-suite 공식 구현 pytorch

Tasks

MambaMoment RetrievalTemporal Action LocalizationVideo Understanding

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
3D CNN 설명 없음

Similar Papers 제목 키워드 기반

Characterizing the Behavior of Training Mamba-based State Space Models on GPUs

2025-08-25 · Trinayan Baruah, Kaustubh Shivdikar, Sara Prescott, David Kaeli arxiv

Mamba-based State Space Models (SSM) have emerged as a promising alternative to the ubiquitous transformers. Despite the expressive power of transformers, the quadratic complexity of computing attention is a major impedi…

Text Generation

Gather-Scatter Mamba: Accelerating Propagation with Efficient State Space Model

2025-10-01 · Hyun-kyu Ko, Youbin Kim, Jihyeon Park, Dongheok Park 외 arxiv

State Space Models (SSMs)-most notably RNNs-have historically played a central role in sequential modeling. Although attention mechanisms such as Transformers have since dominated due to their ability to model global con…

Video Super-ResolutionLong-range modeling

Samba+: General and Accurate Salient Object Detection via A More Unified Mamba-based Framework

2026-02-02 · Wenzhuo Zhao, Keren Fu, Jiahao He, Xiaohong Liu 외 arxiv

Existing salient object detection (SOD) models are generally constrained by the limited receptive fields of convolutional neural networks (CNNs) and quadratic computational complexity of Transformers. Recently, the emerg…

Computational EfficiencySalient Object DetectionContinual Learning

MambaVF: State Space Model for Efficient Video Fusion

2026-02-05 · Zixiang Zhao, Yukun Cui, Lilun Deng, Haowen Bai 외 arxiv

Video fusion is a fundamental technique in various video processing tasks. However, existing video fusion methods heavily rely on optical flow estimation and feature warping, resulting in severe computational overhead an…

Optical Flow Estimation

TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition

2025-12-12 · Yanan Liu, Jun Liu, Hao Zhang, Dan Xu 외 arxiv

Skeleton-based action recognition has garnered significant attention in the computer vision community. Inspired by the recent success of the selective state-space model (SSM) Mamba in modeling 1D temporal sequences, we p…

Temporal SequencesAction Recognition