# Inter-intra Variant Dual Representations forSelf-supervised Video Recognition

Source: [Inter-intra Variant Dual Representations forSelf-supervised Video Recognition](<https://www.sota2.com/research/paper/68fa6b191e209131cea2c2bb>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:40:16.064Z

Authors: Lin Zhang, Qi She, Zhengyang Shen, Changhu Wang

Published: 2021-07-02T17:03:04.000Z

## Abstract

Contrastive learning applied to self-supervised representation learning has seen a resurgence in deep models. In this paper, we find that existing contrastive learning based solutions for self-supervised video recognition focus on inter-variance encoding but ignore the intra-variance existing in clips within the same video. We thus propose to learn dual representations for each clip which (\\romannumeral 1) encode intra-variance through a shuffle-rank pretext task; (\\romannumeral 2) encode inter-variance through a temporal coherent contrastive loss. Experiment results show that our method plays an essential role in balancing inter and intra variances and brings consistent performance gains on multiple backbones and contrastive learning frameworks. Integrated with SimCLR and pretrained on Kinetics-400, our method achieves $\\textbf{82.0\\%}$ and $\\textbf{51.2\\%}$ downstream classification accuracy on UCF101 and HMDB51 test sets respectively and $\\textbf{46.1\\%}$ video retrieval accuracy on UCF101, outperforming both pretext-task based and contrastive learning based counterparts. Our code is available at \\href{https://github.com/lzhangbj/DualVar}{https://github.com/lzhangbj/DualVar}.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Action Recognition on HMDB51 (test)](<https://www.sota2.com/research/sota/action-recognition-on-hmdb51-test.md>): Action Recognition; HMDB51 (test); Accuracy: 0.512.

- [Action Recognition on UCF101 (test)](<https://www.sota2.com/research/sota/action-recognition-on-ucf101-test.md>): Action Recognition; UCF101 (test); Accuracy: 82.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2107.01194>)

[PDF](<https://arxiv.org/pdf/2107.01194.pdf>)
