The DOI matches its Crossref record; 57 of the 58 references it cites were found in a registry or an index.
Unsupervised Learning of Visual Representations Using Videos
Open accessAbstract
Is strong supervision necessary for learning a good visual representation? Do we really need millions of semantically-labeled images to train a Convolutional Neural Network (CNN)? In this paper, we present a simple yet surprisingly powerful approach for unsupervised learning of CNN. Specifically, we use hundreds of thousands of unlabeled videos from the web to learn visual representations. Our key idea is that visual tracking provides the supervision. That is, two patches connected by a track should have similar visual representation in deep feature space since they probably belong to same object or object part. We design a Siamese-triplet network with a ranking loss function to train this CNN representation. Without using a single image from ImageNet, just using 100K unlabeled videos and the VOC 2012 dataset, we train an ensemble of unsupervised networks that achieves 52% mAP (no bounding box regression). This performance comes tantalizingly close to its ImageNet-supervised counterpart, an ensemble which achieves a mAP of 54.4%. We also show that our unsupervised network can perform competitively in other tasks such as surface-normal estimation.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Our survey found that most deepfake detection methods assume a static game (Mirsky and Lee 2021; Wang and Gupta 2015).”
From Deepfake video detection: challenges and opportunities (2024) · cites this paper as Wang and Gupta 2015
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077
Extracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436
Flagged first, then by citations
1 of the 58 references couldn’t be matched to a known paper.
Research works printed but not linked: 1
- lecun, 1990, Handwritten digit recognition with a backpropagation network, NIPS
Cited by
Sorted by citations
Items 1,001–1,002 of 1,002
Unsupervised representation learning for time series with temporal neighborhood coding
Tonekaboni, S., Eytan, D., & Goldenberg, A. (2021) · arXiv · doi:10.48550/arxiv.2106.00750 · Cited by 170
Learning visual groups from co-occurrences in space and time
Isola, P., Zoran, D., Krishnan, D., & Adelson, E. H. (2015) · arXiv · doi:10.48550/arxiv.1511.06811 · Cited by 90
Metadata
- Authors
- Wang, X., & Gupta, A.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- 2015 IEEE International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2015-12
- Pages
- 2794-2802
- OpenAlex
- W219040644
- Cited by
- 1,005
- References
- 58
- Citations by year
- 2026: 8 · 2025: 32 · 2024: 44 · 2023: 63 · 2022: 97 · 2021: 146 · 2020: 173 · 2019: 140 · 2018: 121 · 2017: 108 · 2016: 65 · 2015: 8
- FWCI
- 41.29
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1320083)
- Nvidia
- Defense Advanced Research Projects Agency (FA8750-14- 2-0244, FA8750)
- Multidisciplinary University Research Initiative
- Office of Naval Research (N00014-10-10934, MURI N000141010934)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- video-based learning, visual object tracking, ranking loss, object detection, unlabeled video, surface normal estimation, convolutional neural networks
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
