The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Learning latent temporal structure for complex event detection
Abstract
In this paper, we tackle the problem of understanding the temporal structure of complex events in highly varying videos obtained from the Internet. Towards this goal, we utilize a conditional model trained in a max-margin framework that is able to automatically discover discriminative and interesting segments of video, while simultaneously achieving competitive accuracies on difficult detection and recognition tasks. We introduce latent variables over the frames of a video, and allow our algorithm to discover and assign sequences of states that are most discriminative for the event. Our model is based on the variable-duration hidden Markov model, and models durations of states in addition to the transitions between states. The simplicity of our model allows us to perform fast, exact inference using dynamic programming, which is extremely important when we set our sights on being able to process a very large number of videos quickly and efficiently. We show promising results on the Olympic Sports dataset [16] and the 2011 TRECVID Multimedia Event Detection task [18]. We also illustrate and visualize the semantic understanding capabilities of our model.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Object Detection with Discriminatively Trained Part-Based Models
Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.167 · Cited by 9,853
Activity Recognition and Abnormality Detection with the Switching Hidden Semi-Markov Model
Duong, T. V., Bui, H. H., Phung, D. Q., & Venkatesh, S. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.61 · Cited by 535 · cited 2×
“Our model for videos is the conditional variant of the variable-duration hidden Markov model (HMM), also referred to as an explicit-duration HMM or a hidden semiMarkov model [2, 14].”
MethodCoupled Hidden Semi Markov Models for Activity Recognition
Natarajan, P., & Nevatia, R. (2007) · 2007 IEEE Workshop on Motion and Video Computing (WMVC'07) · doi:10.1109/wmvc.2007.12 · Cited by 144
Research works printed but not linked: 27
- 10.1109/TPAMI.2007.1124 · DOI · Paper page
- 10.1007/s11263-007-0122-4 · DOI · Paper page
- over, 2011, Trecvid 2011 - An overview of the goals, tasks, data, evaluation mechanisms and metrics, Proc TRECVID 2011
- 10.1109/ICCV.2009.5459426 · DOI · Paper page
- niebles, 2010, Modeling temporal structure of decomposable motion segments for activity classification, ECCV
- liu, 2009, Recognizing realistic actions from videos "in the wild, CVPR
- 10.1007/s11263-005-1838-7 · DOI · Paper page
- 10.1109/CVPR.2008.4587756 · DOI · Paper page
- satkin, 2010, Modeling the temporal extent of actions, ECCV
- sarawagi, 2004, Semi-markov conditional random fields for information extraction, NIPS
- 10.1109/ICPR.2004.1334462 · DOI · Paper page
- 10.1016/j.cviu.2006.07.014 · DOI · Paper page
- 10.1109/TCSVT.2008.2005594 · DOI · Paper page
- 10.1109/CVPR.2010.5539949 · DOI · Paper page
- 10.1109/CVPR.2011.5995407 · DOI · Paper page
- 10.5244/C.23.124 · DOI · Paper page
- 10.1109/TPAMI.2009.43 · DOI · Paper page
- 10.1145/1553374.1553523 · DOI · Paper page
- fan, 2008, LIBLINEAR: A library for large linear classification, JMLR
- 10.5244/C.22.99 · DOI · Paper page
- 10.1109/TMM.2008.2001369 · doi:10.1109/tmm.2008.2001369
- 10.1162/08997660360581958 · DOI · Paper page
- 10.1109/CVPR.2011.5995470 · DOI · Paper page
- gorelick, 2007, Actions as space-time shapes, IEEE TPAMI, 10.1109/TPAMI.2007.70711 · DOI · Paper page
- 10.1109/CVPR.2011.5995646 · DOI
- 10.1109/ICCV.2007.4409011 · DOI · Paper page
- hongeng, 2003, Large-scale event detection using semi-hidden markov models, ICCV
Cited by
Describing Videos by Exploiting Temporal Structure
Yao, L., Torabi, A., Cho, K., Ballas, N., Pal, C., Larochelle, H., & Courville, A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.512 · Cited by 1,035
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
“A hidden Markov model is also used in [26] to model both transitions between states and their durations.”
MethodTVSum: Summarizing web videos using titles
Song, Y., Vallmitjana, J., Stent, A., & Jaimes, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299154 · Cited by 623
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response
Koppula, H. S., & Saxena, A. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2430335 · Cited by 596
A survey of video datasets for human action and activity recognition
Chaquet, J. M., Carmona, E. J., & Fernández-Caballero, A. (2013) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2013.01.013 · Cited by 455
Metadata
- Authors
- Tang, K., Fei-Fei, L., & Koller, D.
- Venue
- 2012 IEEE Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2012-06
- Pages
- 1250-1257
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2142258645
- Cited by
- 355
- References
- 3
- FWCI
- 32.36
- 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
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 latent temporal structure for complex event detection. https://app.cochat.ai/papers/10.1109/cvpr.2012.6247808
- The paper
- Tang, K., Fei-Fei, L., & Koller, D. (2012). Learning latent temporal structure for complex event detection. 2012 IEEE Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/cvpr.2012.6247808
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.
