Yanhao Jing, Feng Wang. TP-VIT: A Two-Pathway Vision Transformer for Video Action Recognition. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022. pages 2185-2189, IEEE, 2022. [doi]
@inproceedings{JingW22-0, title = {TP-VIT: A Two-Pathway Vision Transformer for Video Action Recognition}, author = {Yanhao Jing and Feng Wang}, year = {2022}, doi = {10.1109/ICASSP43922.2022.9747276}, url = {https://doi.org/10.1109/ICASSP43922.2022.9747276}, researchr = {https://researchr.org/publication/JingW22-0}, cites = {0}, citedby = {0}, pages = {2185-2189}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022}, publisher = {IEEE}, isbn = {978-1-6654-0540-9}, }