Sequential Deep Trajectory Descriptor for Action Recognition With Three-Stream CNN
Open accessThe DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
Abstract
Learning the spatial-temporal representation of motion information is crucial to human action recognition. Nevertheless, most of the existing features or descriptors cannot capture motion information effectively, especially for long-term motion. To address this problem, this paper proposes a long-term motion descriptor called sequential deep trajectory descriptor (sDTD). Specifically, we project dense trajectories into two-dimensional planes, and subsequently a CNN-RNN network is employed to learn an effective representation for long-term motion. Unlike the popular two-stream ConvNets, the sDTD stream is introduced into a three-stream framework so as to identify actions from a video sequence. Consequently, this three-stream framework can simultaneously capture static spatial features, short-term motion, and long-term motion in the video. Extensive experiments were conducted on three challenging datasets: KTH, HMDB51, and UCF101. Experimental results show that our method achieves state-of-the-art performance on the KTH and UCF101 datasets, and is comparable to the state-of-the-art methods on the HMDB51 dataset.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“This should be considered in the future works.”
BackgroundImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 1×
“In recent years, many studies (e.g., [1], [2], [3], [4]) made their efforts on representing an action with low-level visual Manuscript received September 21,2016; revised July 16,2016 and September 21,2016; accepted February 04, 2017.”
BackgroundGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
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 · cited 1×
“This work was partially supported by the National Basic Research Program of China under grant 2015CB351806, the National Natural Science Foundation of China under contract No. 61390515, No.”
MethodFischler, M. A., & Bolles, R. C. (1981) · Communications of the ACM · doi:10.1145/358669.358692 · Cited by 25,893 · cited 1×
“This deep neural network is composed of a CNN part and a LSTM part, where the CNN part aims at learning the spatial features while the LSTM part is designed to capture the temporal features.”
BackgroundDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“This deep neural network is composed of a CNN part and a LSTM part, where the CNN part aims at learning the spatial features while the LSTM part is designed to capture the temporal features.”
BackgroundCaffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077 · cited 1×
“This section will first introduce the detail of datasets and their corresponding evaluation schemes.”
BackgroundSpeech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 1×
“This should be considered in the future works.”
BackgroundTwo-Stream Convolutional Networks for Action Recognition in Videos
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1406.2199 · Cited by 6,756
Cited by
A survey of the recent architectures of deep convolutional neural networks
Khan, A., Sohail, A., Zahoora, U., & Qureshi, A. S. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-020-09825-6 · Cited by 3,137
CNN Variants for Computer Vision: History, Architecture, Application, Challenges and Future Scope
Bhatt, D., Patel, C., Talsania, H., Patel, J., Vaghela, R., Pandya, S., Modi, K., & Ghayvat, H. (2021) · Electronics · doi:10.3390/electronics10202470 · Cited by 890
“In 2016, Frizzi employed CNN in another technique to identify some emergencies, such as fire or smoke, in the video [54].”
MethodDeep Learning for Spatio-Temporal Data Mining: A Survey
Wang, S., Cao, J., & Yu, P. S. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.3025580 · Cited by 822
Vision-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
Pareek, P., & Thakkar, A. (2021) · Artificial Intelligence Review · doi:10.1007/s10462-020-09904-8 · Cited by 455
A Deep Neural Framework for Continuous Sign Language Recognition by Iterative Training
Cui, R., Liu, H., & Zhang, C. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2889563 · Cited by 421
A Review on Human Activity Recognition Using Vision-Based Method
Zhang, S., Wei, Z., Nie, J., Huang, L., Wang, S., & Li, Z. (2017) · Journal of Healthcare Engineering · doi:10.1155/2017/3090343 · Cited by 328
Recurrent Spatial-Temporal Attention Network for Action Recognition in Videos
Du, W., Wang, Y., & Qiao, Y. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2778563 · Cited by 219
Self-citationAnomaly detection using edge computing in video surveillance system: review
Patrikar, D. R., & Parate, M. R. (2022) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-022-00227-8 · Cited by 177
“Trajectory based descriptors are also widely used to capture long term motion information and to estimate the dynamic information of foreground objects for action recognition [83].”
BackgroundMethodAmbient Sensors for Elderly Care and Independent Living: A Survey
Uddin, M. Z., Khaksar, W., & Torresen, J. (2018) · Sensors · doi:10.3390/s18072027 · Cited by 166
“[83] (2016) Recognition of activities of daily living Three sequential deep trajectory descriptors were tried with deep recurrent neural networks and convolutional neural networks for efficient activity recognition.”
Background
Metadata
- Authors
- Shi, Y., Tian, Y., Wang, Y., & Huang, T.
- Venue
- IEEE Transactions on Multimedia
- Published
- 2017-07
- Volume
- 19
- Issue
- 7
- Pages
- 1510-1520
- ISSN
- 1520-9210 (ISSN-L)
- 1941-0077
- OpenAlex
- W2519750370
- Cited by
- 210
- References
- 46
- FWCI
- 10.56
- Type
- journal article
- 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.