Recognition of Complex Events: Exploiting Temporal Dynamics between Underlying Concepts
Open accessThe DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
While approaches based on bags of features excel at low-level action classification, they are ill-suited for recognizing complex events in video, where concept-based temporal representations currently dominate. This paper proposes a novel representation that captures the temporal dynamics of windowed mid-level concept detectors in order to improve complex event recognition. We first express each video as an ordered vector time series, where each time step consists of the vector formed from the concatenated confidences of the pre-trained concept detectors. We hypothesize that the dynamics of time series for different instances from the same event class, as captured by simple linear dynamical system (LDS) models, are likely to be similar even if the instances differ in terms of low-level visual features. We propose a two-part representation composed of fusing: (1) a singular value decomposition of block Hankel matrices (SSID-S) and (2) a harmonic signature (HS) computed from the corresponding eigen-dynamics matrix. The proposed method offers several benefits over alternate approaches: our approach is straightforward to implement, directly employs existing concept detectors and can be plugged into linear classification frameworks. Results on standard datasets such as NIST's TRECVID Multimedia Event Detection task demonstrate the improved accuracy of the proposed method.
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
Recognizing human action in time-sequential images using hidden Markov model
Yamato, J., Ohya, J., & Ishii, K. (2003) · Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.1992.223161 · Cited by 1,273 · cited 1×
“Since H is typically not square, we perform singular value decomposition on H · HT to obtain the orthonormal bases (singular vectors, E) and singular values in diagonal matrix D.”
Method
Research works printed but not linked: 25
- 10.1109/WMVC.2008.4544064 · DOI
- lim, 2006, Dynamic appearance modeling for human tracking, CVPR, 1, 751
- 10.1109/CVPR.2006.105 · doi:10.1109/cvpr.2006.105
- li, 2012, Recognizing activities by attribute dynamics, NIPS, 1115
- 10.1109/CVPR.2013.334 · DOI
- 10.1109/CVPR.2011.5995672 · DOI
- 10.14778/1920841.1920893 · DOI
- jiang, 2010, Columbia-UCF TRECVID2010 multimedia event detection: Combining multiple modalities, contextual concepts, and temporal matching, Proc NIST TRECVID Workshop
- 10.1109/TIT.1974.1055174 · DOI · Paper page
- 10.1016/0005-1098(94)90230-5 · DOI · Paper page
- 10.1109/CVPR.2012.6247814 · DOI · Paper page
- ristic, 2004, Beyond the Kalman Filter Particle Filters for Tracking Applications
- 10.1109/CVPR.2012.6247808 · DOI · Paper page
- 10.1109/CVPR.2011.5995407 · DOI · Paper page
- 10.1016/j.jvcir.2006.03.004 · DOI · Paper page
- 10.1109/TPAMI.2007.70738 · DOI · Paper page
- 10.1007/978-3-642-33709-3_49 · DOI
- 10.1007/s13735-012-0024-2 · DOI · Paper page
- box, 1990, Time Series Analysis Forecasting and Control
- 10.1109/TMM.2006.876289 · doi:10.1109/tmm.2006.876289
- 10.1023/A:1021669406132 · DOI · Paper page
- 10.1007/978-3-540-76856-2_33 · DOI
- 10.1109/CVPR.2009.5206821 · DOI · Paper page
- jackson, 1991, Perspectives of Nonlinear Dynamics Chapter 2
- 10.1006/cviu.2000.0896 · 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
“[1] use a vector time series representation of videos to model the temporal dynamics of complex actions using methods from linear dynamical systems theory.”
MethodMS-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
“[20] use a vector time series representa-”
Temporal Action Detection Using a Statistical Language Model
Richard, A., & Gall, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.341 · Cited by 215
An end-to-end generative framework for video segmentation and recognition
Kuehne, H., Gall, J., & Serre, T. (2016) · 2016 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2016.7477701 · Cited by 188
Super Normal Vector for Human Activity Recognition with Depth Cameras
Yang, X., & Tian, Y. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2565479 · Cited by 162
Weakly supervised learning of actions from transcripts
Kuehne, H., Richard, A., & Gall, J. (2017) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2017.06.004 · Cited by 119
“Others try to model temporal dynamics with mid-level concept detectors [18] or encounter the relation to speech processing and extract features comparable to acoustic features from a speech signal which are then fed into a classical hidden HMM based speech recognizer [19].”
BackgroundEvent-based media processing and analysis: A survey of the literature
Tzelepis, C., Ma, Z., Mezaris, V., Ionescu, B., Kompatsiaris, I., Boato, G., Sebe, N., & Yan, S. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2016.05.005 · Cited by 49
“In [16], the authors first propose a video representation that captures the temporal dynamics of mid-level con-”
BackgroundMS-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
“[20] use a vector time series representa-”
Metadata
- Authors
- Bhattacharya, S., Kalayeh, M. M., Sukthankar, R., & Shah, M.
- Venue
- 2014 IEEE Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2014-06
- Pages
- 2243-2250
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2169992457
- Cited by
- 67
- References
- 1
- FWCI
- 7.75
- 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
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.