Time-Contrastive Networks: Self-Supervised Learning from Multi-view Observation
The DOI matches its Crossref record.
Abstract
We propose a self-supervised approach for learning representations of relationships between humans and their environment, including object interactions, attributes, and body pose, entirely from unlabeled videos recorded from multiple viewpoints (Fig. 2). We train an embedding with a triplet loss that contrasts a pair of simultaneous frames from different viewpoints with temporally adjacent and visually similar frames (Fig. 1). We call this model Time- Contrastive Networks (TCN). The contrastive signal encourages the model to discover meaningful dimensions and attributes that can explain the changing state of objects and the world from visually similar frames while learning invariance to viewpoint, occlusions, motion blur, lighting, background. The experimental evaluation of our multiviewpoint embedding technique examines its application to reasoning about object interactions, as well as human pose imitation with a real robot. We demonstrate that our model can correctly identify corresponding steps in complex object interactions, such as pouring (Table 1), between different videos and with different instances. We also show what is, to the best of our knowledge, the first self-supervised results for end-to-end imitation learning of human motions with a real robot (Table 2). Results are best visualized in videos available at1and the full paper is available at2.
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
Cited by
Representation 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
“More recent work includes Time Contrastive Networks [24] which proposes to minimize distances between embeddings from multiple viewpoints of the same scene and whilst maximizing distances between embeddings extracted from different timesteps.”
BackgroundTian, Y., Krishnan, D., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58621-8_45 · Cited by 1,997
Temporal Relational Reasoning in Videos
Zhou, B., Andonian, A., Oliva, A., & Torralba, A. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01246-5_49 · Cited by 1,067
Self-supervised learning for medical image analysis using image context restoration
Chen, L., Bentley, P., Mori, K., Misawa, K., Fujiwara, M., & Rueckert, D. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.101539 · Cited by 575
State representation learning for control: An overview
Lesort, T., Díaz-Rodríguez, N., Goudou, J.-F., & Filliat, D. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.07.006 · Cited by 301
Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation
Liu, Y., Gupta, A., Abbeel, P., & Levine, S. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8462901 · Cited by 278
Self-citationMonocular 3D Object Detection with Pseudo-LiDAR Point Cloud
Weng, X., & Kitani, K. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00114 · Cited by 268
Reinforcement and Imitation Learning for Diverse Visuomotor Skills
Zhu, Y., Wang, Z., Merel, J., Rusu, A., Erez, T., Cabi, S., Tunyasuvunakool, S., Kramár, J., Hadsell, R., de Freitas, N., et al. (2018) · Robotics: Science and Systems XIV · doi:10.15607/rss.2018.xiv.009 · Cited by 260
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
Grauman, K., Westbury, A., Torresani, L., Kitani, K., Malik, J., Afouras, T., Ashutosh, K., Baiyya, V., Bansal, S., Boote, B., et al. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01834 · Cited by 182
COCOA: Cross Modality Contrastive Learning for Sensor Data
Deldari, S., Xue, H., Saeed, A., Smith, D. V., & Salim, F. D. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3550316 · Cited by 92
Deldari, S., Xue, H., Saeed, A., He, J., Smith, D. V., & Salim, F. D. (2022) · arXiv · doi:10.48550/arxiv.2206.02353 · Cited by 26
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
Grauman, K., Westbury, A., Torresani, L., Kitani, K., Malik, J., Afouras, T., Ashutosh, K., Baiyya, V., Bansal, S., Boote, B., et al. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02557-6 · Cited by 3
Metadata
- Authors
- Sermanet, P., Lynch, C., Hsu, J., & Levine, S.
- Venue
- 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
- Publisher
- IEEE
- Published
- 2017-07
- Pages
- 486-487
- OpenAlex
- W2609990452
- Cited by
- 111
- References
- 0
- FWCI
- 3.56
- Type
- conference paper
- Language
- en
- Open access
- closed
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.