Temporal Pyramid Pooling-Based Convolutional Neural Network for Action Recognition
The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Encouraged by the success of convolutional neural networks (CNNs) in image classification, recently much effort is spent on applying the CNNs to the video-based action recognition problems. One challenge is that a video contains a varying number of frames, which is incompatible to the standard input format of the CNNs. Existing methods handle this issue either by directly sampling a fixed number of frames or bypassing this issue by introducing a 3D convolutional layer, which conducts convolution in spatial-temporal domain. In this paper, we propose a novel network structure, which allows an arbitrary number of frames as the network input. The key to our solution is to introduce a module consisting of an encoding layer and a temporal pyramid pooling layer. The encoding layer maps the activation from the previous layers to a feature vector suitable for pooling, whereas the temporal pyramid pooling layer converts multiple frame-level activations into a fixed-length video-level representation. In addition, we adopt a feature concatenation layer that combines the appearance and motion information. Compared with the frame sampling strategy, our method avoids the risk of missing any important frames. Compared with the 3D convolutional method, which requires a huge video data set for network training, our model can be learned on a small target data set because we can leverage the off-the-shelf image-level CNN for model parameter initialization. Experiments on three challenging data sets, Hollywood2, HMDB51, and UCF101 demonstrate the effectiveness of the proposed network.
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
ImageNet: 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
Two-Stream Convolutional Networks for Action Recognition in Videos
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1406.2199 · Cited by 6,756
Large-Scale Video Classification with Convolutional Neural Networks
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.223 · Cited by 6,354
3D Convolutional Neural Networks for Human Action Recognition
Ji, S., Xu, W., Yang, M., & Yu, K. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.59 · Cited by 6,235
Ucf101: A dataset of 101 human actions classes from videos in the wild
Soomro, K., Zamir, A. R., & Shah, M. (2012) · arXiv · doi:10.48550/arxiv.1212.0402 · Cited by 4,575
Hmdb: a large video database for human motion recognition
Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126543 · Cited by 3,965 · cited 3×
“According to the protocol in [26], three training-testing splits are provided for this dataset.”
BackgroundMethodInfluentialAction 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
Return of the Devil in the Details: Delving Deep into Convolutional Nets
Chatfield, K., Simonyan, K., Vedaldi, A., & Zisserman, A. (2014) · Proceedings of the British Machine Vision Conference 2014 · doi:10.5244/c.28.6 · Cited by 3,335
Locality-constrained Linear Coding for image classification
Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., & Gong, Y. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5540018 · Cited by 3,100 · cited 1×
“Hybrid improved dense trajectories in [12], employs multiple unsupervised encoding methods i.e. Fisher vector [4], VLAD [29] and LLC [30].”
MethodImproving the Fisher Kernel for Large-Scale Image Classification
Perronnin, F., Sánchez, J., & Mensink, T. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_11 · Cited by 2,588 · cited 4×
“the unsupervised feature encoding methods, such as Fisher vector encoding [4].”
BackgroundMethodInfluentialUnsupervised Learning of Video Representations using LSTMs
Srivastava, N., Mansimov, E., & Salakhutdinov, R. (2015) · arXiv · doi:10.48550/arxiv.1502.04681 · Cited by 1,861
Aggregating Local Image Descriptors into Compact Codes
Jegou, H., Perronnin, F., Douze, M., Sanchez, J., Perez, P., & Schmid, C. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.235 · Cited by 1,503
Action recognition with trajectory-pooled deep-convolutional descriptors
Wang, L., Qiao, Y., & Tang, X. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299059 · Cited by 1,194
Cited by
Temporal Action Detection with Structured Segment Networks
Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., & Lin, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.317 · Cited by 892
Pareek, P., & Thakkar, A. (2021) · Artificial Intelligence Review · doi:10.1007/s10462-020-09904-8 · Cited by 455
Review of tool condition monitoring in machining and opportunities for deep learning
Serin, G., Sener, B., Ozbayoglu, A. M., & Unver, H. O. (2020) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-020-05449-w · Cited by 360
MS2L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition
Lin, L., Song, S., Yang, W., & Liu, J. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413548 · Cited by 223
“7 MS2L Jointly (Our)85.1745.70 Table 5: Comparison of action recognition results with supervised learning approaches on the NTU dataset. Models NTU LSTM [13] 71.90 BLSTM 71.40 STA-LSTM [31] 73.40 TPN [40] 75.30 ST-GCN [43]81.50 MS2L Rand-S 78.44 MS2L Pretrain (Our) 78.33 MS2L Moving (Our) 78.46 MS2L Jointly (Our) 78.5…”
MethodInfluentialMulti-attention Network for One Shot Learning
Wang, P., Liu, L., Shen, C., Huang, Z., Van Den Hengel, A., & Shen, H. T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.658 · Cited by 91
“• Supervised encoding (SE): to verify the effectiveness of the attention scheme, we choose another end-toend learning baseline, namely supervised encoding [24, 13].”
MethodSelf-citation
Metadata
- Authors
- Wang, P., Cao, Y., Shen, C., Liu, L., & Shen, H. T.
- Venue
- IEEE Transactions on Circuits and Systems for Video Technology
- Published
- 2017-12
- Volume
- 27
- Issue
- 12
- Pages
- 2613-2622
- ISSN
- 1051-8215 (ISSN-L)
- 1558-2205
- OpenAlex
- W2142694332
- Cited by
- 127
- References
- 14
- FWCI
- 11.64
- Type
- journal article
- 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.