Timezone: »

Shifted Chunk Transformer for Spatio-Temporal Representational Learning
Xuefan Zha · Wentao Zhu · Lv Xun · Sen Yang · Prof. Ji Liu Liu

Wed Dec 08 04:30 PM -- 06:00 PM (PST) @ None #None

Spatio-temporal representational learning has been widely adopted in various fields such as action recognition, video object segmentation, and action anticipation.Previous spatio-temporal representational learning approaches primarily employ ConvNets or sequential models, e.g., LSTM, to learn the intra-frame and inter-frame features. Recently, Transformer models have successfully dominated the study of natural language processing (NLP), image classification, etc. However, the pure-Transformer based spatio-temporal learning can be prohibitively costly on memory and computation to extract fine-grained features from a tiny patch. To tackle the training difficulty and enhance the spatio-temporal learning, we construct a shifted chunk Transformer with pure self-attention blocks. Leveraging the recent efficient Transformer design in NLP, this shifted chunk Transformer can learn hierarchical spatio-temporal features from a local tiny patch to a global videoclip. Our shifted self-attention can also effectively model complicated inter-frame variances. Furthermore, we build a clip encoder based on Transformer to model long-term temporal dependencies. We conduct thorough ablation studies to validate each component and hyper-parameters in our shifted chunk Transformer, and it outperforms previous state-of-the-art approaches on Kinetics-400, Kinetics-600,UCF101, and HMDB51.

Author Information

Xuefan Zha (Kuaishou Technology)
Wentao Zhu (Kuaishou Technology)
Lv Xun (Kuaishou Technology)
Sen Yang (Kuaishou Technology)
Prof. Ji Liu Liu (Kwai Inc.)

More from the Same Authors