paper-with-me

홈 › Papers

Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning

2022-06-24 · CVPR 2023 1 · Cheng Tan, Zhangyang Gao, Lirong Wu, Yongjie Xu, Jun Xia, Siyuan Li, Stan Z. Li

Spatiotemporal predictive learning aims to generate future frames by learning from historical frames. In this paper, we investigate existing methods and present a general framework of spatiotemporal predictive learning, in which the spatial encoder and decoder capture intra-frame features and the middle temporal module catches inter-frame correlations. While the mainstream methods employ recurrent units to capture long-term temporal dependencies, they suffer from low computational efficiency due to their unparallelizable architectures. To parallelize the temporal module, we propose the Temporal Attention Unit (TAU), which decomposes the temporal attention into intra-frame statical attention and inter-frame dynamical attention. Moreover, while the mean squared error loss focuses on intra-frame errors, we introduce a novel differential divergence regularization to take inter-frame variations into account. Extensive experiments demonstrate that the proposed method enables the derived model to achieve competitive performance on various spatiotemporal prediction benchmarks.

📄 PDF Abstract BibTeX arXiv:2206.12126

Code (2)

chengtan9907/OpenSTL 공식 구현 pytorch
chengtan9907/simvpv2 pytorch

Tasks

Computational EfficiencyDecoderVideo Prediction

Similar Papers 제목 키워드 기반

Triplet Attention Transformer for Spatiotemporal Predictive Learning

2023-10-28 · Xuesong Nie, Xi Chen, Haoyuan Jin, Zhihang Zhu 외

Spatiotemporal predictive learning offers a self-supervised learning paradigm that enables models to learn both spatial and temporal patterns by predicting future sequences based on historical sequences. Mainstream metho…

Computational EfficiencyPredictionSelf-Supervised LearningTrajectory Prediction+1

PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs

2017-12-01 · Conference 2017 12 · Yunbo Wang Mingsheng Long Jianmin Wang Zhifeng Gao Philip S. Yu

The predictive learning of spatiotemporal sequences aims to generate future images by learning from the historical frames, where spatial appearances and temporal variations are two crucial structures. This paper models t…

Video Prediction

PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs

2017-12-01 · NeurIPS 2017 12 · Yunbo Wang, Mingsheng Long, Jian-Min Wang, Zhifeng Gao 외

The predictive learning of spatiotemporal sequences aims to generate future images by learning from the historical frames, where spatial appearances and temporal variations are two crucial structures. This paper models t…

Video Prediction

SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning

2022-11-22 · Cheng Tan, Zhangyang Gao, Siyuan Li, Stan Z. Li

Recent years have witnessed remarkable advances in spatiotemporal predictive learning, with methods incorporating auxiliary inputs, complex neural architectures, and sophisticated training strategies. While SimVP has int…

Computational EfficiencyVideo Prediction

A Gravity-informed Spatiotemporal Transformer for Human Activity Intensity Prediction

2025-06-16 · Yi Wang, Zhenghong Wang, Fan Zhang, Chengling Tang 외

Human activity intensity prediction is a crucial to many location-based services. Although tremendous progress has been made to model dynamic spatiotemporal patterns of human activity, most existing methods, including sp…