Media Summary: [ECCV 2022] Efficient Video Transformers with Spatial-Temporal Token Selection Authors: Yimin Wei (Sun Yat-Sen University); Hao Liu (Sun Yat-Sen University); Tingting Xie (Queen Mary University of London); ... This paper studies the problem of concept-based interpretability of
Eccv 2022 Efficient Video Transformers With Spatial Temporal Token Selection - Detailed Analysis & Overview
[ECCV 2022] Efficient Video Transformers with Spatial-Temporal Token Selection Authors: Yimin Wei (Sun Yat-Sen University); Hao Liu (Sun Yat-Sen University); Tingting Xie (Queen Mary University of London); ... This paper studies the problem of concept-based interpretability of
![[ECCV 2022] Efficient Video Transformers with Spatial-Temporal Token Selection](https://i.ytimg.com/vi/6u7IMMkSc-I/mqdefault.jpg)
![[ECCV 2022 Oral] Adaptive Token Sampling for Efficient Vision Transformers](https://i.ytimg.com/vi/NJvyCcRjMfg/mqdefault.jpg)
![[ECCV 2022] Intro video: Flow-Guided Transformer for Video Inpainting](https://i.ytimg.com/vi/GGZwkpf7xwo/mqdefault.jpg)
![[CVPR 2026] Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods](https://i.ytimg.com/vi/USJ5pKu0Vho/mqdefault.jpg)
