# Cycle-Contrast for Self-Supervised Video Representation Learning

arXiv: https://arxiv.org/abs/2010.14810 · HTML: https://mlsanity.com/paper/2010.14810/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2020.

## Built on by (most cited first, 30 of 34)

- [Bridging Video-text Retrieval with Multiple Choice Questions](https://mlsanity.com/paper/2201.04850/) (2022)
- [Motion-aware Contrastive Video Representation Learning via Foreground-background Merging](https://mlsanity.com/paper/2109.15130/) (2021)
- [PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning](https://mlsanity.com/paper/2106.04152/) (2021)
- [Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/2110.05340/) (2021)
- [Universal Time-Series Representation Learning: A Survey](https://mlsanity.com/paper/2401.03717/) (2024)
- [MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval](https://mlsanity.com/paper/2204.12408/) (2022)
- [Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization](https://mlsanity.com/paper/2108.02183/) (2021)
- [Cross-modal Knowledge Distillation for Vision-to-Sensor Action Recognition](https://mlsanity.com/paper/2112.01849/) (2021)
- [Motion-Focused Contrastive Learning of Video Representations](https://mlsanity.com/paper/2201.04029/) (2022)
- [C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentation](https://mlsanity.com/paper/2212.11078/) (2022)
- [Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency](https://mlsanity.com/paper/2105.06463/) (2021)
- [Iterative Contrast-Classify For Semi-supervised Temporal Action Segmentation](https://mlsanity.com/paper/2112.01402/) (2021)
- [Motion-Augmented Self-Training for Video Recognition at Smaller Scale](https://mlsanity.com/paper/2105.01646/) (2021)
- [Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency](https://mlsanity.com/paper/2204.03017/) (2022)
- [Dual Contrastive Learning for Spatio-temporal Representation](https://mlsanity.com/paper/2207.05340/) (2022)
- [Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video Representation](https://mlsanity.com/paper/2112.08913/) (2021)
- [Self-Supervised Video Representation Learning via Latent Time Navigation](https://mlsanity.com/paper/2305.06437/) (2023)
- [Self-Supervised Representation Learning from Temporal Ordering of Automated Driving Sequences](https://mlsanity.com/paper/2302.09043/) (2023)
- [Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation Learning](https://mlsanity.com/paper/2309.00297/) (2023)
- [Contrastive Learning of Global-Local Video Representations](https://mlsanity.com/paper/2104.05418/) (2021)
- [Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting](https://mlsanity.com/paper/2106.10137/) (2021)
- [Progressive Cross-modal Knowledge Distillation for Human Action Recognition](https://mlsanity.com/paper/2208.08090/) (2022)
- [Inter-intra Variant Dual Representations forSelf-supervised Video Recognition](https://mlsanity.com/paper/2107.01194/) (2021)
- [Contrastive Learning of Person-independent Representations for Facial Action Unit Detection](https://mlsanity.com/paper/2403.03400/) (2024)
- [CycleCL: Self-supervised Learning for Periodic Videos](https://mlsanity.com/paper/2311.03402/) (2023)
- [Motion Aware Self-Supervision for Generic Event Boundary Detection](https://mlsanity.com/paper/2210.05574/) (2022)
- [ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning](https://mlsanity.com/paper/2108.10501/) (2021)
- [Learning Contrastive Feature Representations for Facial Action Unit Detection](https://mlsanity.com/paper/2402.06165/) (2024)
- [Exploring the Diversity and Invariance in Yourself for Visual Pre-Training Task](https://mlsanity.com/paper/2106.00537/) (2021)
- [Temporal Contrastive Learning with Curriculum](https://mlsanity.com/paper/2209.00760/) (2022)

## Abstract (arXiv)

We present Cycle-Contrastive Learning (CCL), a novel self-supervised method for learning video representation. Following a nature that there is a belong and inclusion relation of video and its frames, CCL is designed to find correspondences across frames and videos considering the contrastive representation in their domains respectively. It is different from recent approaches that merely learn correspondences across frames or clips. In our method, the frame and video representations are learned from a single network based on an R3D architecture, with a shared non-linear transformation for embedding both frame and video features before the cycle-contrastive loss. We demonstrate that the video representation learned by CCL can be transferred well to downstream tasks of video understanding, outperforming previous methods in nearest neighbour retrieval and action recognition tasks on UCF101, HMDB51 and MMAct.