VideoMamba: Spatio-Temporal Selective State Space Model
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911952820764672 |
|---|---|
| author | Park, Jinyoung Kim, Hee-Seon Ko, Kangwook Kim, Minbeom Kim, Changick |
| author_facet | Park, Jinyoung Kim, Hee-Seon Ko, Kangwook Kim, Minbeom Kim, Changick |
| contents | We introduce VideoMamba, a novel adaptation of the pure Mamba architecture, specifically designed for video recognition. Unlike transformers that rely on self-attention mechanisms leading to high computational costs by quadratic complexity, VideoMamba leverages Mamba's linear complexity and selective SSM mechanism for more efficient processing. The proposed Spatio-Temporal Forward and Backward SSM allows the model to effectively capture the complex relationship between non-sequential spatial and sequential temporal information in video. Consequently, VideoMamba is not only resource-efficient but also effective in capturing long-range dependency in videos, demonstrated by competitive performance and outstanding efficiency on a variety of video understanding benchmarks. Our work highlights the potential of VideoMamba as a powerful tool for video understanding, offering a simple yet effective baseline for future research in video analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_08476 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VideoMamba: Spatio-Temporal Selective State Space Model Park, Jinyoung Kim, Hee-Seon Ko, Kangwook Kim, Minbeom Kim, Changick Computer Vision and Pattern Recognition We introduce VideoMamba, a novel adaptation of the pure Mamba architecture, specifically designed for video recognition. Unlike transformers that rely on self-attention mechanisms leading to high computational costs by quadratic complexity, VideoMamba leverages Mamba's linear complexity and selective SSM mechanism for more efficient processing. The proposed Spatio-Temporal Forward and Backward SSM allows the model to effectively capture the complex relationship between non-sequential spatial and sequential temporal information in video. Consequently, VideoMamba is not only resource-efficient but also effective in capturing long-range dependency in videos, demonstrated by competitive performance and outstanding efficiency on a variety of video understanding benchmarks. Our work highlights the potential of VideoMamba as a powerful tool for video understanding, offering a simple yet effective baseline for future research in video analysis. |
| title | VideoMamba: Spatio-Temporal Selective State Space Model |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.08476 |