计算机科学
变压器
地点
人工智能
建筑
杠杆(统计)
动作识别
计算机视觉
模式识别(心理学)
工程类
电气工程
哲学
艺术
视觉艺术
电压
班级(哲学)
语言学
作者
Ze Liu,Ning Jia,Yue Cao,Yixuan Wei,Zheng Zhang,Stephen Lin,Hanping Hu
出处
期刊:Cornell University - arXiv
日期:2021-01-01
被引量:40
标识
DOI:10.48550/arxiv.2106.13230
摘要
The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks. These video models are all built on Transformer layers that globally connect patches across the spatial and temporal dimensions. In this paper, we instead advocate an inductive bias of locality in video Transformers, which leads to a better speed-accuracy trade-off compared to previous approaches which compute self-attention globally even with spatial-temporal factorization. The locality of the proposed video architecture is realized by adapting the Swin Transformer designed for the image domain, while continuing to leverage the power of pre-trained image models. Our approach achieves state-of-the-art accuracy on a broad range of video recognition benchmarks, including on action recognition (84.9 top-1 accuracy on Kinetics-400 and 86.1 top-1 accuracy on Kinetics-600 with ~20x less pre-training data and ~3x smaller model size) and temporal modeling (69.6 top-1 accuracy on Something-Something v2). The code and models will be made publicly available at https://github.com/SwinTransformer/Video-Swin-Transformer.
科研通智能强力驱动
Strongly Powered by AbleSci AI