Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning
The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
It is often laborious and costly to manually annotate videos for training high-quality video recognition models, so there has been some work and interest in exploring alternative, cheap, and yet often noisy and indirect training signals for learning the video representations. However, these signals are still coarse, supplying supervision at the whole video frame level, and subtle, sometimes enforcing the learning agent to solve problems that are even hard for humans. In this paper, we instead explore geometry, a grand new type of auxiliary supervision for the self-supervised learning of video representations. In particular, we extract pixel-wise geometry information as flow fields and disparity maps from synthetic imagery and real 3D movies, respectively. Although the geometry and high-level semantics are seemingly distant topics, surprisingly, we find that the convolutional neural networks pre-trained by the geometry cues can be effectively adapted to semantic video understanding tasks. In addition, we also find that a progressive training strategy can foster a better neural network for the video recognition task than blindly pooling the distinct sources of geometry cues together. Extensive results on video dynamic scene recognition and action recognition tasks show that our geometry guided networks significantly outperform the competing methods that are trained with other types of labeling-free supervision signals.
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
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Two-Stream Convolutional Networks for Action Recognition in Videos
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1406.2199 · Cited by 6,756
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
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“The idea embodies curriculum learning [3], namely, we carefully organize the training data, teach the network with accurate geometry cues in the synthetic imagery first, and then feed the network real-world appearance information conveyed by the 3D movies.”
BackgroundDimensionality Reduction by Learning an Invariant Mapping
Hadsell, R., Chopra, S., & LeCun, Y. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.100 · Cited by 5,336
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
Flownet: Learning optical flow with convolutional networks
Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., Smagt, P. V. D., Cremers, D., & Brox, T. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.316 · Cited by 4,313
Li, Z., & Hoiem, D. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2773081 · Cited by 4,202
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 10×
“For the experiments on HMDB51, the learning rate starts from 10−2 and decreases to 10−3 after 3.5K iterations, and then to 10−4 after 4K iterations.”
MethodInfluentialAdapting visual category models to new domains
Saenko, K., Kulis, B., Fritz, M., & Darrell, T. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_16 · Cited by 2,847 · cited 1×
“It has been reported that the models trained with synthesis data perform relatively poor on the real image and video data [29].”
BackgroundUnsupervised Visual Representation Learning by Context Prediction
Doersch, C., Gupta, A., & Efros, A. A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.167 · Cited by 2,629 · cited 4×
“[7] explored the spatial consistency of image as context prediction task to learn feature representation.”
BackgroundInfluentialShapeNet: An Information-Rich 3D Model Repository
Chang, A. X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et al. (2015) · arXiv · doi:10.48550/arxiv.1512.03012 · Cited by 2,330
Self-citationUnsupervised Learning of Video Representations using LSTMs
Srivastava, N., Mansimov, E., & Salakhutdinov, R. (2015) · arXiv · doi:10.48550/arxiv.1502.04681 · Cited by 1,861
Unsupervised Learning of Visual Representations Using Videos
Wang, X., & Gupta, A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.320 · Cited by 1,005
Shuffle 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 9×
“We uniformly sample 25 frames per video in the UCF101 and HMDB51 dataset as suggested in [24].”
BackgroundMethodResultInfluentialLi, Z., & Hoiem, D. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_37 · Cited by 659
Self-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×
“More recently, [24, 11, 20] presented CNN-based unsupervised video representation learning method.”
MethodDeep learning from temporal coherence in video
Mobahi, H., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553469 · Cited by 328 · cited 1×
“Particularly, we compare with DrLim [13], TempoCoh [25], Object patch [37], Seq.”
Result
Cited by
Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey
Jing, L., & Tian, Y. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2992393 · Cited by 2,036
Tian, Y., Krishnan, D., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58621-8_45 · Cited by 1,997
Rethinking Few-Shot Image Classification: A Good Embedding is All You Need?
Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J. B., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58568-6_16 · Cited by 952
Human Action Recognition and Prediction: A Survey
Kong, Y., & Fu, Y. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01594-9 · Cited by 780
End-to-End Learning of Visual Representations From Uncurated Instructional Videos
Miech, A., Alayrac, J.-B., Smaira, L., Laptev, I., Sivic, J., & Zisserman, A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00990 · Cited by 580
Metadata
- Authors
- Gan, C., Gong, B., Liu, K., Su, H., & Guibas, L. J.
- Venue
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2018-06
- Pages
- 5589-5597
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2798271879
- Cited by
- 120
- References
- 19
- FWCI
- 5.85
- 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.