TCLR: Temporal Contrastive Learning For Video Representation

Abstract

Contrastive learning has nearly closed the gap between supervised and self-supervised learning of image representations, and has also been explored for videos. However, prior work on contrastive learning for video data has not explored the effect of explicitly encouraging the features to be distinct across the temporal dimension. We develop a new temporal contrastive learning framework consisting of two novel losses to improve upon existing contrastive self-supervised video representation learning methods. The local-local temporal contrastive loss adds the task of discriminating between non-overlapping clips from the same video, whereas the global-local temporal contrastive aims to discriminate between timesteps of the feature map of an input clip in order to increase the temporal diversity of the learned features. Our proposed temporal contrastive learning framework achieves significant improvement over the state-of-the-art results in various downstream video understanding tasks such

Stats

• citations126
• S2 citations—
• github stars0
• HF likes0
• heat score15.78
• arxiv keydave2021tclr

Related papers

• Cycle-contrast For Self-supervised Video Representation Learning (2020)0.00
• Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework (2020)18.58
• Self-supervised Video Representation Learning With Cross-stream Prototypical Contrasting (2021)8.82
• Temporal Context Aggregation For Video Retrieval With Contrastive Learning (2020)13.23
• Nearest-neighbor Inter-intra Contrastive Learning From Unlabeled Videos (2023)0.00
• TC-MGC: Text-conditioned Multi-grained Contrastive Learning For Text-video Retrieval (2025)6.93
• Contrastive Video-language Learning With Fine-grained Frame Sampling (2022)6.77
• Lat: Latent Translation With Cycle-consistency For Video-text Retrieval (2022)0.00