Learning convolutional action primitives for fine-grained action recognition
The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
Fine-grained action recognition is important for many applications of human-robot interaction, automated skill assessment, and surveillance. The goal is to segment and classify all actions occurring in a time series sequence. While recent recognition methods have shown strong performance in robotics applications, they often require hand-crafted features, use large amounts of domain knowledge, or employ overly simplistic representations of how objects change throughout an action. In this paper we present the Latent Convolutional Skip Chain Conditional Random Field (LC-SC-CRF). This time series model learns a set of interpretable and composable action primitives from sensor data. We apply our model to cooking tasks using accelerometer data from the University of Dundee 50 Salads dataset and to robotic surgery training tasks using robot kinematic data from the JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS). Our performance on 50 Salads and JIGSAWS are 18.0% and 5.3% higher than the state of the art, respectively. This model performs well without requiring hand-crafted features or intricate domain knowledge. The code and features have been made public.
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
Combining 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 5×
“action primitives per class achieves 79% precision and 79% recall compared to 65% and 67% using the state of the art approach [13].”
BackgroundMethodResultInfluential
Research works printed but not linked: 19
- 10.1561/0600000033 · DOI · Paper page
- 10.1109/IROS.2014.6943279 · DOI
- 10.1109/TBME.2005.869771 · DOI · Paper page
- 10.1007/978-3-642-30618-1_17 · DOI
- 10.1007/978-3-642-40760-4_43 · DOI
- tsochantaridis, 2009, Large Margin Methods for Structured and Interdependent Output Variables, Journal of Machine Learning Research
- 10.1109/CVPR.2014.338 · DOI · Paper page
- 10.1109/TPAMI.2010.214 · DOI · Paper page
- 10.1109/ICRA.2014.6907165 · DOI · Paper page
- 10.1109/IROS.2013.6697213 · DOI
- koppula, 2013, Learning spatio-temporal structure from rgb-d videos for human activity detection and anticipation, International Conference on Machine Learning (ICML)
- 10.1109/ICRA.2014.6906983 · DOI
- 10.1145/2370216.2370248 · DOI · Paper page
- 10.1109/WACV.2015.154 · DOI
- gao, 2014, The jhu-isi gesture and skill assessment dataset (jigsaws): A surgical activity working set for human motion modeling, Med Image Comput Comput Assist Intervent MICCAI
- duchi, 2010, Adaptive subgradient methods for online learning and stochastic optimization, EECS Department
- müller, 2013, Learning a Loopy Model For Semantic Segmentation Exactly, arXiv preprint arXiv 1309 4061
- 10.1109/CVPR.2013.331 · DOI
- 10.1145/1553374.1553523 · DOI · Paper page
Cited by
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
“F1@k is our segmental F1 score, Edit is the Segmental edit score from [17], and Acc is frame-wise accuracy.”
BackgroundSelf-citationTemporal Convolutional Networks: A Unified Approach to Action Segmentation
Lea, C., Vidal, R., Reiter, A., & Hager, G. D. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-49409-8_7 · Cited by 924
Self-citationA Dataset and Benchmarks for Segmentation and Recognition of Gestures in Robotic Surgery
Ahmidi, N., Tao, L., Sefati, S., Gao, Y., Lea, C., Haro, B. B., Zappella, L., Khudanpur, S., Vidal, R., & Hager, G. D. (2017) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2016.2647680 · Cited by 289
Self-citationDeep reinforcement learning in computer vision: a comprehensive survey
Le, N., Rathour, V. S., Yamazaki, K., Luu, K., & Savvides, M. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10061-9 · Cited by 261
Segmental 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
“Their approach uses holistic features with a Markov Semi-Markov CRF. Metrics: We evaluate on segmental and frame-wise metrics as suggested by [37] for the 50 Salads dataset.”
BackgroundMethodInfluentialSelf-citation
Metadata
- Authors
- Lea, C., Vidal, R., & Hager, G. D.
- Venue
- 2016 IEEE International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2016-05
- Pages
- 1642-1649
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2413983136
- Cited by
- 106
- References
- 1
- FWCI
- 4.58
- 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.