Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Fine-grained action detection is an important task with numerous applications in robotics and human-computer interaction. Existing methods typically utilize a two-stage approach including extraction of local spatio-temporal features followed by temporal modeling to capture long-term dependencies. While most recent papers have focused on the latter (long-temporal modeling), here, we focus on producing features capable of modeling fine-grained motion more efficiently. We propose a novel locally-consistent deformable convolution, which utilizes the change in receptive fields and enforces a local coherency constraint to capture motion information effectively. Our model jointly learns spatio-temporal features (instead of using independent spatial and temporal streams). The temporal component is learned from the feature space instead of pixel space, e.g. optical flow. The produced features can be flexibly used in conjunction with other long-temporal modeling networks, e.g. ST-CNN, DilatedTCN, and ED-TCN. Overall, our proposed approach robustly outperforms the original long-temporal models on two fine-grained action datasets: 50 Salads and GTEA, achieving F1 scores of 80.22% and 75.39% respectively.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
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
Action Recognition with Improved Trajectories
Wang, H., & Schmid, C. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.441 · Cited by 3,407
Temporal Convolutional Networks for Action Segmentation and Detection
Lea, C., Flynn, M. D., Vidal, R., Reiter, A., & Hager, G. D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.113 · Cited by 2,238
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation
Farha, Y. A., & Gall, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00369 · Cited by 673 · cited 1×
“The TCN model was also further improved with multi stage mechanism in Multi-Stage TCN (MS-TCN) [6].”
MethodLearning to recognize objects in egocentric activities
Fathi, A., Ren, X., & Rehg, J. M. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995444 · Cited by 557 · cited 2×
“Georgia Tech Egocentric Activities (GTEA) [ 7]: This dataset contains 28 videos of 7 action classes, performed by 4 subjects.”
BackgroundMethodT-CNN: Tubelets With Convolutional Neural Networks for Object Detection From Videos
Kang, K., Li, H., Yan, J., Zeng, X., Yang, B., Xiao, T., Zhang, C., Wang, Z., Wang, R., Wang, X., et al. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2736553 · Cited by 554
A Multi-stream Bi-directional Recurrent Neural Network for Fine-Grained Action Detection
Singh, B., Marks, T. K., Jones, M., Tuzel, O., & Shao, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.216 · Cited by 461 · cited 5×
“The second step models long-term dependency of extracted spatio-temporal features over the whole video, e.g . bi-directional LSTM [23], spatial-temporal CNN (ST-CNN) with segmentation models [16], temporal convolutional networks (TCN) [15], and temporal deformable residual networks (TDRN) [17].”
BackgroundMethodInfluentialCombining embedded accelerometers with computer vision for recognizing food preparation activities
Stein, S., & McKenna, S. J. (2013) · Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing · doi:10.1145/2493432.2493482 · Cited by 448 · cited 2×
“50 Salads Dataset [25]: This dataset contains 50 salad making videos from multiple sensors.”
BackgroundMethodSegmental Spatiotemporal CNNs for Fine-Grained Action Segmentation
Lea, C., Reiter, A., Vidal, R., & Hager, G. D. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46487-9_3 · Cited by 246 · cited 10×
“SpatialCNN [16]: a VGG-like model that learns both spatial and short-term temporal information by stacking an RGB frame with the corresponding MHI (the difference be-tween frames over a short period of time).”
BackgroundMethodResultInfluential
Research works printed but not linked: 18
- 10.1109/CVPR.2017.75 · DOI · Paper page
- 10.1007/978-3-642-75988-8_28 · DOI · Paper page
- kang, 2016, Review of action recognition and detection methods, arXiv preprint arXiv 1610 09756
- 10.1109/CVPR.2018.00705 · DOI · Paper page
- lucas, 1981, An iterative image registration technique with an application to stereo vision, International Joint Conference on Artificial Intelligence (IJ-CAI)
- 10.1016/S0893-6080(98)00116-6 · DOI · Paper page
- 10.1007/11744047_33 · DOI · Paper page
- 10.1109/ICCV.2015.510 · DOI · Paper page
- yu, 2016, Multi-scale context aggregation by dilated convolutions, International Conference on Learning Representations (ICLR)
- davis, 2001, The representation and recognition of action using temporal templates, IEEE Trans Pattern Analysis and Machine Intelligence (TPAMI)
- feichtenhofer, 2016, Spatiotemporal residual networks for video action recognition, Conference on Neural Information Processing Systems (NeurIPS)
- 10.1109/ICCV.2017.89 · DOI · Paper page
- 10.1109/CVPR.2016.213 · DOI · Paper page
- 10.1109/CVPR.2017.502 · DOI · Paper page
- 10.1109/CVPR.2012.6247801 · DOI · Paper page
- simonyan, 2014, Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv 1409 1556
- simonyan, 2014, Two-stream convolutional networks for action recognition in videos, Conference on Neural Information Processing Systems (NeurIPS)
- 10.1109/CVPR.2015.7298594 · DOI · Paper page
Cited by
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation
Farha, Y. A., & Gall, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00369 · Cited by 673
“[31] propose to learn spatio-temporal features using deformable convolutions and local consistency constraints.”
BackgroundMS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation
Li, S., Farha, Y. A., Liu, Y., Cheng, M.-M., & Gall, J. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3021756 · Cited by 349
“[31] propose to learn spatio-temporal features using deformable convolutions and local consistency constraints.”
BackgroundAlleviating Over-segmentation Errors by Detecting Action Boundaries
Ishikawa, Y., Kasai, S., Aoki, Y., & Kataoka, H. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00237 · Cited by 171
MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation
Li, S., Farha, Y. A., Liu, Y., Cheng, M.-M., & Gall, J. (2020) · arXiv · Cited by 350
“[31] propose to learn spatio-temporal features using deformable convolutions and local consistency constraints.”
Background
Metadata
- Authors
- Mac, K.-N., Joshi, D., Yeh, R., Xiong, J., Feris, R., & Do, M.
- Venue
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 6281-6290
- OpenAlex
- W2984100309
- Cited by
- 43
- References
- 11
- FWCI
- 1.86
- Type
- conference paper
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection. https://app.cochat.ai/papers/10.1109/iccv.2019.00638
- The paper
- Mac, K.-N., Joshi, D., Yeh, R., Xiong, J., Feris, R., & Do, M. (2019). Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection. 2019 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv.2019.00638
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.