"Knights": First Place Submission for VIPriors21 Action Recognition Challenge at ICCV 2021

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 t...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-10
Main Authors: Ishan Dave, Biyani, Naman, Clark, Brandon, Gupta, Rohit, Rawat, Yogesh, Shah, Mubarak
Format: Article
Language:English
Subjects:
Activity recognition
Computer vision
Optical flow (image analysis)
Testing time
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422