TCLR: Temporal contrastive learning for video representation
Open accessThe DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
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 as action recognition, limited-label action classification, and nearest-neighbor video retrieval on multiple video datasets and backbones. We also demonstrate significant improvement in fine-grained action classification for visually similar classes. With the commonly used 3D ResNet-18 architecture with UCF101 pretraining, we achieve 82.4% (+5.1% increase over the previous best) top-1 accuracy on UCF101 and 52.9% (+5.4% increase) on HMDB51 action classification, and 56.2% (+11.7% increase) Top-1 Recall on UCF101 nearest neighbor video retrieval. Code released at https://github.com/DAVEISHAN/TCLR.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Momentum Contrast for Unsupervised Visual Representation Learning
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00975 · Cited by 13,347
Learning Spatiotemporal Features with 3D Convolutional Networks
Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.510 · Cited by 9,593
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Carreira, J., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.502 · Cited by 9,570
Large-Scale Video Classification with Convolutional Neural Networks
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.223 · Cited by 6,354 · cited 1×
“The recent advances in video understanding tasks can largely be attributed to the existence of large-scale labeled datasets such as Kinetics [7], HACS [57], Sports-1M [24], YouTube8M [1] etc.”
BackgroundRepresentation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242
Ucf101: A dataset of 101 human actions classes from videos in the wild
Soomro, K., Zamir, A. R., & Shah, M. (2012) · arXiv · doi:10.48550/arxiv.1212.0402 · Cited by 4,575
Self-citationSlowFast Networks for Video Recognition
Feichtenhofer, C., Fan, H., Malik, J., & He, K. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00630 · Cited by 4,007
Hmdb: a large video database for human motion recognition
Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126543 · Cited by 3,965 · cited 2×
“ics400 [7], and HMDB51 [28] for our experiments.”
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
Grill, J.-B., Strub, F., Altché, F., Tallec, C., Richemond, P. H., Buchatskaya, E., Doersch, C., Pires, B. A., Guo, Z. D., Azar, M. G., et al. (2020) · arXiv · doi:10.48550/arxiv.2006.07733 · Cited by 3,846
A Closer Look at Spatiotemporal Convolutions for Action Recognition
Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., & Paluri, M. (2017) · arXiv · doi:10.48550/arxiv.1711.11248 · Cited by 3,664
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020) · arXiv · doi:10.48550/arxiv.2006.09882 · Cited by 2,499
Zagoruyko, S., & Komodakis, N. (2016) · arXiv · doi:10.48550/arxiv.1612.03928 · Cited by 2,027
Self-Supervised Learning of Pretext-Invariant Representations
Misra, I., & van der Maaten, L. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00674 · Cited by 1,435 · cited 2×
“can be useful but is not sufficient for all video understanding tasks [34].”
BackgroundShuffle and Learn: Unsupervised Learning Using Temporal Order Verification
Misra, I., Zitnick, C. L., & Hebert, M. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_32 · Cited by 779 · cited 2×
“Other works propose frame-based contrastive learning, along with existing pretext tasks of frame rotation prediction [27] and frame-tuple order verification [55], with the pretext tasks borrowed from from [22] and [35], respectively.”
BackgroundSelf-Supervised Video Representation Learning with Odd-One-Out Networks
Fernando, B., Bilen, H., Gavves, E., & Gould, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.607 · Cited by 421 · cited 1×
“Pretext task based approaches: Various pretext tasks have been devised for self-supervised video representation learning based on learning the correct temporal order of the data: verifying correct frame order [44], identifying the correctly ordered tuple from a set of shuffled orderings [20,53], sorting frame order [3…”
MethodSelf-Supervised Learning by Cross-Modal Audio-Video Clustering
Alwassel, H., Mahajan, D., Korbar, B., Torresani, L., Ghanem, B., & Tran, D. (2019) · arXiv · doi:10.48550/arxiv.1911.12667 · Cited by 298
Self-supervised Co-training for Video Representation Learning
Han, T., Xie, W., & Zisserman, A. (2020) · arXiv · doi:10.48550/arxiv.2010.09709 · Cited by 292 · cited 3×
“optical flow [25,52,54,55,64] or dense trajectories [56]).”
VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples
Pan, T., Song, Y., Yang, T., Jiang, W., & Liu, W. (2021) · arXiv · doi:10.48550/arxiv.2103.05905 · Cited by 238
A large-scale study on unsupervised spatiotemporal representation learning
Feichtenhofer, C., Fan, H., Xiong, B., Girshick, R., & He, K. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00331 · Cited by 222
Wang, J., Jiao, J., Bao, L., He, S., Liu, Y., & Liu, W. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00413 · Cited by 210 · cited 2×
“Many recent works rely on predicting video properties like playback rate of the video [13, 50, 63, 70], temporal transformation that has been applied from a given set [29, 30], speediness of moving objects [7], and motion and appearance statistics of the video [61, 62].”
BackgroundUnsupervised Video Representation Learning by Bidirectional Feature Prediction
Behrmann, N., Gall, J., & Noroozi, M. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00171 · Cited by 28
Cited by
Self-supervised learning for videos: A survey
Schiappa, M. C., Rawat, Y. S., & Shah, M. (2023) · ACM Computing Surveys · doi:10.1145/3577925 · Cited by 155
Self-citationMHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series
Meng, Q., Qian, H., Liu, Y., Cui, L., Xu, Y., & Shen, Z. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i8.26098 · Cited by 52
Metadata
- Authors
- Dave, I., Gupta, R., Rizve, M. N., & Shah, M.
- Venue
- Computer Vision and Image Understanding
- Publisher
- Elsevier BV
- Published
- 2022-06
- Volume
- 219
- Pages
- 103406
- ISSN
- 1077-3142 (ISSN-L)
- OpenAlex
- W3123599388
- Cited by
- 163
- References
- 22
- FWCI
- 11.41
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.