Asynchronous Temporal Fields for Action Recognition
The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
Actions are more than just movements and trajectories: we cook to eat and we hold a cup to drink from it. A thorough understanding of videos requires going beyond appearance modeling and necessitates reasoning about the sequence of activities, as well as the higher-level constructs such as intentions. But how do we model and reason about these? We propose a fully-connected temporal CRF model for reasoning over various aspects of activities that includes objects, actions, and intentions, where the potentials are predicted by a deep network. End-to-end training of such structured models is a challenging endeavor: For inference and learning we need to construct mini-batches consisting of whole videos, leading to mini-batches with only a few videos. This causes high-correlation between data points leading to breakdown of the backprop algorithm. To address this challenge, we present an asynchronous variational inference method that allows efficient end-to-end training. Our method achieves a classification mAP of 22.4% on the Charades [42] benchmark, outperforming the state-of-the-art (17.2% mAP), and offers equal gains on the task of temporal localization.
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
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
Playing Atari with Deep Reinforcement Learning
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. (2013) · arXiv · doi:10.48550/arxiv.1312.5602 · Cited by 9,471
Does the chimpanzee have a theory of mind?
Premack, D., & Woodruff, G. (1978) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00076512 · Cited by 8,743
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
3D Convolutional Neural Networks for Human Action Recognition
Ji, S., Xu, W., Yang, M., & Yu, K. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.59 · Cited by 6,235
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370
Long-term recurrent convolutional networks for visual recognition and description
Donahue, J., Hendricks, L. A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Darrell, T., & Saenko, K. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298878 · Cited by 5,228
Training Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879 · cited 1×
“This shares ideas with contrastive divergence [11, 38].”
Research works printed but not linked: 47
- schwing, 2015, Fully Connected Deep Structured Networks
- salakhutdinov, 2009, Deep boltzmann machines, AISTATS
- 10.21236/ADA612444 · DOI
- 10.1109/CVPR.2014.85 · DOI · Paper page
- 10.1109/CVPR.2012.6247806 · DOI · Paper page
- 10.1109/CVPR.2007.383487 · DOI · Paper page
- rohrbach, 2012, Script data for attribute-based recognition of composite activities, ECCV
- 10.1109/TPAMI.2011.158 · DOI · Paper page
- weinzaepfel, 2016, Towards weakly-supervised action localization
- 10.1109/CVPR.2016.597 · DOI · Paper page
- 10.1109/CVPR.2015.7298789 · DOI · Paper page
- yeung, 2015, Every moment counts Dense detailed labeling of actions in complex videos
- mettes, 2016, Spot on: Action localization from pointly-supervised proposals, ECCV
- 10.1109/CVPR.2015.7299101 · DOI · Paper page
- zhang, 2016, Instance-level segmentation with deep densely connected mrfs, CVPR
- peng, 2014, Action recognition with stacked fisher vectors, ECCV
- dalal, 2006, Human detection using oriented histograms of flow and appearance, ECCV
- chen, 2015, Learning Deep Structured Models, Proc ICML
- 10.1109/ICCV.2015.517 · DOI · Paper page
- 10.1007/s11263-005-1838-7 · DOI · Paper page
- lan, 2015, Beyond gaussian pyramid: Multi-skip feature stacking for action recognition, CVPR
- 10.1109/CVPR.2011.5995496 · DOI · Paper page
- 10.1109/CVPR.2008.4587756 · DOI · Paper page
- 10.1109/ICCVW.2009.5457659 · DOI · Paper page
- 10.1109/ICCV.2007.4408872 · DOI · Paper page
- 10.1109/ICCV.2015.522 · DOI · Paper page
- 10.1109/CVPR.2012.6247808 · DOI · Paper page
- 10.1016/j.cviu.2010.10.002 · DOI · Paper page
- 10.1109/CVPR.2016.291 · DOI · Paper page
- 10.1109/CVPR.2016.18 · DOI · Paper page
- 10.1109/CVPR.2016.327 · DOI
- 10.1007/978-3-642-15567-3_11 · DOI · Paper page
- gupta, 2015, Visual semantic role labeling
- 10.1109/CVPR.2016.119 · DOI · Paper page
- 10.1007/978-3-642-33765-9_31 · DOI
- 10.1109/CVPR.2013.332 · DOI
- 10.5244/C.22.99 · DOI · Paper page
- de souza, 2016, Sympathy for the details: Dense trajectories and hybrid classification architectures for action recognition, ECCV
- 10.1109/CVPR.2015.7299176 · DOI · Paper page
- gorban, 2015, THUMOS Challenge Action Recognition with A Large Number of Classes
- 10.1109/CVPR.2015.7298676 · DOI · Paper page
- 10.1109/ICCV.2013.453 · DOI · Paper page
- 10.1109/TPAMI.2009.83 · DOI · Paper page
- 10.1109/CVPR.2013.457 · DOI · Paper page
- simonyan, 2015, Very deep convolutional networks for large-scale image recognition, ICLRE
- sigurdsson, 2016, Hollywood in homes: Crowdsourcing data collection for activity understanding, ECCV
- 10.1007/978-3-319-46454-1_5 · DOI
Cited by
Wang, X., Girshick, R., Gupta, A., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00813 · Cited by 11,596
“8 Asyn-TF [43] RGB + flow 22.”
InfluentialSelf-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
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
R-C3D: Region Convolutional 3D Network for Temporal Activity Detection
Xu, H., Das, A., & Saenko, K. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.617 · Cited by 783
Videos as Space-Time Region Graphs
Wang, X., & Gupta, A. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01228-1_25 · Cited by 765
Self-citationVision-based human activity recognition: a survey
Beddiar, D. R., Nini, B., Sabokrou, M., & Hadid, A. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09004-3 · Cited by 505
Long-Term Feature Banks for Detailed Video Understanding
Wu, C.-Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., & Girshick, R. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00037 · Cited by 441
Compressed Video Action Recognition
Wu, C.-Y., Zaheer, M., Hu, H., Manmatha, R., Smola, A. J., & Krahenbuhl, P. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00631 · Cited by 347
AutoLoc: Weakly-Supervised Temporal Action Localization in Untrimmed Videos
Shou, Z., Gao, H., Zhang, L., Miyazawa, K., & Chang, S.-F. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01270-0_10 · Cited by 288
A Survey on Bayesian Deep Learning
Wang, H., & Yeung, D.-Y. (2021) · ACM Computing Surveys · doi:10.1145/3409383 · Cited by 247
“Computer Vision Asynchronous Temporal Fields [102] LV ✓ Attend, Infer, Repeat (AIR) [20] LV ✓ Fast AIR [105] LV ✓ Sequential AIR [60] LV ✓”
BackgroundMethodD3D: Distilled 3D Networks for Video Action Recognition
Stroud, J. C., Ross, D. A., Sun, C., Deng, J., & Sukthankar, R. (2020) · 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv45572.2020.9093274 · Cited by 192
“Many approaches leverage the strength of single-image (2D) CNNs by applying a CNN to each individual video frame and pooling the predictions across time [28, 6, 27].”
MethodWang, X., Girshick, R., Gupta, A., & He, K. (2017) · arXiv · Cited by 11,689
Self-citationParameter Efficient Multimodal Transformers for Video Representation Learning
Lee, S., Yu, Y., Kim, G., Breuel, T., Kautz, J., & Song, Y. (2020) · arXiv · doi:10.48550/arxiv.2012.04124 · Cited by 49
“, 2019), ATF (Sigurdsson et al., 2017) Table 2: (a; left): Short video classification results on UCF101 (mean accuracy (%)).”
Background
Metadata
- Authors
- Sigurdsson, G. A., Divvala, S., Farhadi, A., & Gupta, A.
- Venue
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2017-07
- Pages
- 5650-5659
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2583815496
- Cited by
- 144
- References
- 19
- FWCI
- 6.63
- 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.