"Knights": First Place Submission for VIPriors21 Action Recognition Challenge at ICCV 2021
arXiv:2110.07758
Abstract
This technical report presents our approach "Knights" to solve the action recognition task on a small subset of Kinetics-400 i.e. Kinetics400ViPriors without using any extra-data. Our approach has 3 main components: state-of-the-art Temporal Contrastive self-supervised pretraining, video transformer models, and optical flow modality. Along with the use of standard test-time augmentation, our proposed solution achieves 73% on Kinetics400ViPriors test set, which is the best among all of the other entries Visual Inductive Priors for Data-Efficient Computer Vision's Action Recognition Challenge, ICCV 2021.
arXiv commentChallenge results are available at https://vipriors.github.io/challenges/#action-recognition
References in corpus (7)
- The Kinetics Human Action Video Dataset
- Is Space-Time Attention All You Need for Video Understanding?
- TCLR: Temporal Contrastive Learning for Video Representation
- Spatiotemporal Contrastive Video Representation Learning
- Multiscale Vision Transformers
- Video Swin Transformer
- How to Start Training: The Effect of Initialization and Architecture