The DOI matches its Crossref record; 44 of the 46 references it cites were found in a registry or an index.
Two-Stream 3-D convNet Fusion for Action Recognition in Videos With Arbitrary Size and Length
Abstract
3-D convolutional neural networks (3-D-convNets) have been very recently proposed for action recognition in videos, and promising results are achieved. However, existing 3-D-convNets has two “artificial” requirements that may reduce the quality of video analysis: 1) It requires a fixed-sized (e.g., 112 $\times$ 112) input video; and 2) most of the 3-D-convNets require a fixed-length input (i.e., video shots with fixed number of frames). To tackle these issues, we propose an end-to-end pipeline named Two-stream 3-D-convNet Fusion, which can recognize human actions in videos of arbitrary size and length using multiple features. Specifically, we decompose a video into spatial and temporal shots. By taking a sequence of shots as input, each stream is implemented using a spatial temporal pyramid pooling (STPP) convNet with a long short-term memory (LSTM) or CNN-E model, softmax scores of which are combined by a late fusion. We devise the STPP convNet to extract equal-dimensional descriptions for each variable-size shot, and we adopt the LSTM/CNN-E model to learn a global description for the input video using these time-varying descriptions. With these advantages, our method should improve all 3-D CNN-based video analysis methods. We empirically evaluate our method for action recognition in videos and the experimental results show that our method outperforms the state-of-the-art methods (both 2-D and 3-D based) on three standard benchmark datasets (UCF101, HMDB51 and ACT datasets).
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“It is also worth pointing out that DH [35], another deep-based hashing method in those baselines, yields unsatisfactory performance on all datasets, where three speculations are illustrated for those results as follows.”
From Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval (2019) · cites this paper as [35]
Citations
Cites
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2389824 · Cited by 11,971
Learning Spatiotemporal Features with 3D Convolutional Networks
Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.510 · Cited by 9,593
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. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.59 · Cited by 6,313
Long-term recurrent convolutional networks for visual recognition and description
Donahue, J., Hendricks, L. A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Darrell, T., & Saenko, K. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298878 · Cited by 5,228
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., & Gool, L. V. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46484-8_2 · Cited by 4,232
A Convolutional Neural Network for Modelling Sentences
Kalchbrenner, N., Grefenstette, E., & Blunsom, P. (2014) · Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.3115/v1/p14-1062 · Cited by 3,601
Learning realistic human actions from movies
Ivan Laptev, A., Marszałek, M., Schmid, C., & Rozenfeld, B. (2008) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2008.4587756 · Cited by 3,481
Action 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
Cited by
Sorted by citations
Human Action Recognition From Various Data Modalities: A Review
Sun, Z., Ke, Q., Rahmani, H., Bennamoun, M., Wang, G., & Liu, J. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3183112 · Cited by 719
“Instead of using 2D CNN, some other works [95], [96], [97], [98] used 3D CNNs as their feature extractors.”
MethodDropout vs. batch normalization: an empirical study of their impact to deep learning
Garbin, C., Xingquan Zhu, A., & Marques, O. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-019-08453-9 · Cited by 620
“…as a new machine learning paradigms that have shown tremendous performance gain compared to conventional machine learning algorithms, especially for applications such as voice recognition [4], image classification [13], video action recognition [32, 33], and spatio-temporal data applications [14].”
BackgroundEnhancing transportation systems via deep learning: A survey
Yuan, W., Zhang, D., Liu, Y., Dai, B., & Lee, L. H. (2018) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2018.12.004 · Cited by 322
Self-Supervised Video Hashing With Hierarchical Binary Auto-Encoder
Song, J., Zhang, H., Li, X., Gao, L., Wang, M., & Hong, R. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2814344 · Cited by 283
“But it is beyond a set of frames and the temporal information in video is important for video content analysis [33].”
BackgroundSelf-citationFrom Deterministic to Generative: Multimodal Stochastic RNNs for Video Captioning
Song, J., Guo, Y., Gao, L., Li, X., Hanjalić, A., & Shen, H. T. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2851077 · Cited by 260
Self-citation
Metadata
- Authors
- Wang, X., Gao, L., Wang, P., Sun, X., & Liu, X.
- Affiliations
- University of Electronic Science and Technology of China (CN)
- The University of Adelaide (AU)
- Harbin Institute of Technology (CN)
- Beihang University (CN)
- Venue
- IEEE Transactions on Multimedia
- Published
- 2018-03
- Volume
- 20
- Issue
- 3
- Pages
- 634-644
- ISSN
- 1520-9210 (ISSN-L)
- 1941-0077
- OpenAlex
- W2751445731
- Cited by
- 263
- References
- 46
- Citations by year
- 2026: 4 · 2025: 5 · 2024: 12 · 2023: 24 · 2022: 23 · 2021: 44 · 2020: 47 · 2019: 60 · 2018: 42
- FWCI
- 17.03
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Multimedia (publishedVersion)
- Adelaide Research & Scholarship (AR&S) (University of Adelaide) (submittedVersion)
- Funders
- Fundamental Research Funds for the Central Universities (ZYGX2014J063, ZYGX2014Z007)
- National Natural Science Foundation of China (61502080, 61632007)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- 3D convolutional neural networks, long short-term memory, decision fusion
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
