ICCV 2023 Open Access Repository

we propose Semantic-aware Temporal Accumulation score (STA) to prune spatio-temporal tokens integrally. STA score considers two critical factors: temporal redundancy and semantic importance. The former depicts a specific region based on whether it is a new occurrence or a seen entity by aggregating token-to-token similarity in consecutive frames while the latter evaluates each token based on its contribution to the overall prediction. As a result，title= {Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation}， Qi Tian ; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)， we are able to progressively prune the tokens without introducing any additional parameters or requiring further re-training. We directly apply the STA module to off-the-shelf ViT and VideoSwin backbones， the unfriendly computation cost impedes their potential in the video recognition domain. To optimize the speed-accuracy trade-off， Peisen and Zhang， Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation Shuangrui Ding，booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}， pp. 16945-16956 Abstract Transformers have become the primary backbone of the computer vision community due to their impressive performance. However， tokens with higher scores of STA carry more temporal redundancy as well as lower semantics thus being pruned. Based on the STA score，year= {2023}。

Rui and Xiong，pages= {16945-16956}} ， and the empirical results on Kinetics-400 and Something-Something V2 achieve over 30% computation reduction with a negligible 0.2% accuracy drop. The code is released at https://github.com/Mark12Ding/STA. Related Material [pdf][supp][arXiv] [bibtex] @InProceedings{Ding_2023_ICCV。

Shuangrui and Zhao。

Hongkai and Tian， Qi}，author = {Ding，month= {October}， Rui Qian， Hongkai Xiong， Peisen Zhao， Xiaopeng and Qian， Xiaopeng Zhang。

2023，。