USTEP: Spatio-Temporal Predictive Learning under A Unified View
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916725250850816 |
|---|---|
| author | Tan, Cheng Wang, Jue Gao, Zhangyang Li, Siyuan Li, Stan Z. |
| author_facet | Tan, Cheng Wang, Jue Gao, Zhangyang Li, Siyuan Li, Stan Z. |
| contents | Spatio-temporal predictive learning plays a crucial role in self-supervised learning, with wide-ranging applications across a diverse range of fields. Previous approaches for temporal modeling fall into two categories: recurrent-based and recurrent-free methods. The former, while meticulously processing frames one by one, neglect short-term spatio-temporal information redundancies, leading to inefficiencies. The latter naively stack frames sequentially, overlooking the inherent temporal dependencies. In this paper, we re-examine the two dominant temporal modeling approaches within the realm of spatio-temporal predictive learning, offering a unified perspective. Building upon this analysis, we introduce USTEP (Unified Spatio-TEmporal Predictive learning), an innovative framework that reconciles the recurrent-based and recurrent-free methods by integrating both micro-temporal and macro-temporal scales. Extensive experiments on a wide range of spatio-temporal predictive learning demonstrate that USTEP achieves significant improvements over existing temporal modeling approaches, thereby establishing it as a robust solution for a wide range of spatio-temporal applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_05829 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | USTEP: Spatio-Temporal Predictive Learning under A Unified View Tan, Cheng Wang, Jue Gao, Zhangyang Li, Siyuan Li, Stan Z. Computer Vision and Pattern Recognition Spatio-temporal predictive learning plays a crucial role in self-supervised learning, with wide-ranging applications across a diverse range of fields. Previous approaches for temporal modeling fall into two categories: recurrent-based and recurrent-free methods. The former, while meticulously processing frames one by one, neglect short-term spatio-temporal information redundancies, leading to inefficiencies. The latter naively stack frames sequentially, overlooking the inherent temporal dependencies. In this paper, we re-examine the two dominant temporal modeling approaches within the realm of spatio-temporal predictive learning, offering a unified perspective. Building upon this analysis, we introduce USTEP (Unified Spatio-TEmporal Predictive learning), an innovative framework that reconciles the recurrent-based and recurrent-free methods by integrating both micro-temporal and macro-temporal scales. Extensive experiments on a wide range of spatio-temporal predictive learning demonstrate that USTEP achieves significant improvements over existing temporal modeling approaches, thereby establishing it as a robust solution for a wide range of spatio-temporal applications. |
| title | USTEP: Spatio-Temporal Predictive Learning under A Unified View |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2310.05829 |