Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition
arXiv:2106.05058
Abstract
With the recent surge in the research of vision transformers, they have demonstrated remarkable potential for various challenging computer vision applications, such as image recognition, point cloud classification as well as video understanding. In this paper, we present empirical results for training a stronger video vision transformer on the EPIC-KITCHENS-100 Action Recognition dataset. Specifically, we explore training techniques for video vision transformers, such as augmentations, resolutions as well as initialization, etc. With our training recipe, a single ViViT model achieves the performance of 47.4\% on the validation set of EPIC-KITCHENS-100 dataset, outperforming what is reported in the original paper by 3.4%. We found that video transformers are especially good at predicting the noun in the verb-noun action prediction task. This makes the overall action prediction accuracy of video transformers notably higher than convolutional ones. Surprisingly, even the best video transformers underperform the convolutional networks on the verb prediction. Therefore, we combine the video vision transformers and some of the convolutional video networks and present our solution to the EPIC-KITCHENS-100 Action Recognition competition.
arXiv commentCVPRW 2021, EPIC-KITCHENS-100 Competition Report
References in corpus (10)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- mixup: Beyond Empirical Risk Minimization
- The Kinetics Human Action Video Dataset
- Is Space-Time Attention All You Need for Video Understanding?
- A Short Note on the Kinetics-700-2020 Human Action Dataset
- DeepViT: Towards Deeper Vision Transformer
- Self-supervised Co-training for Video Representation Learning
- Temporal Context Aggregation Network for Temporal Action Proposal Refinement
- CBR-Net: Cascade Boundary Refinement Network for Action Detection: Submission to ActivityNet Challenge 2020 (Task 1)
- Self-supervised Motion Learning from Static Images