A Benchmark Dataset and Comparison Study for Multi-modal Human Action Analytics
The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Large-scale benchmarks provide a solid foundation for the development of action analytics. Most of the previous activity benchmarks focus on analyzing actions in RGB videos. There is a lack of large-scale and high-quality benchmarks for multi-modal action analytics. In this article, we introduce PKU Multi-Modal Dataset (PKU-MMD), a new large-scale benchmark for multi-modal human action analytics. It consists of about 28,000 action instances and 6.2 million frames in total and provides high-quality multi-modal data sources, including RGB, depth, infrared radiation (IR), and skeletons. To make PKU-MMD more practical, our dataset comprises two subsets under different settings for action understanding, namely Part I and Part II. Part I contains 1,076 untrimmed video sequences with 51 action classes performed by 66 subjects, while Part II contains 1,009 untrimmed video sequences with 41 action classes performed by 13 subjects. Compared to Part I, Part II is more challenging due to short action intervals, concurrent actions and heavy occlusion. PKU-MMD can be leveraged in two scenarios: action recognition with trimmed video clips and action detection with untrimmed video sequences. For each scenario, we provide benchmark performance on both subsets by conducting different methods with different modalities under two evaluation protocols, respectively. Experimental results show that PKU-MMD is a significant challenge to many state-of-the-art methods. We further illustrate that the features learned on PKU-MMD can be well transferred to other datasets. We believe this large-scale dataset will boost the research in the field of action analytics for the community.
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
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Carreira, J., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.502 · Cited by 9,570
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 · cited 1×
“Recently, there are also several works aiming at collecting datasets in certain fields like TV series [9], movies [28], and the Olympic Games [26].”
BackgroundSpatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
Yan, S., Xiong, Y., & Lin, D. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12328 · Cited by 5,410 · cited 4×
“Note that STA-LSTM [53], TPN [19], VA-LSTM [82], and ST-GCN [75] are only for skeletons.”
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
NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
Shahroudy, A., Liu, J., Ng, T.-T., & Wang, G. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.115 · Cited by 3,148
Self-citationImproving 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 1×
“As a kind of low-level video representation, densely tracking points in the optical flow field with more features like Histogram of Oriented Gradient (HOG), Histogram of Flow (HOF), and Motion Boundary Histograms (MBH) [43, 59] achieve good performance in action recognition.”
BackgroundActivityNet: A large-scale video benchmark for human activity understanding
Heilbron, F. C., Escorcia, V., Ghanem, B., & Niebles, J. C. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298698 · Cited by 2,578
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
Zhang, P., Lan, C., Xing, J., Zeng, W., Xue, J., & Zheng, N. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.233 · Cited by 691 · cited 2×
“Note that STA-LSTM [53], TPN [19], VA-LSTM [82], and ST-GCN [75] are only for skeletons.”
Background
Research works printed but not linked: 76
- Amiri S. Mohsen, Proceedings of the IEEE International Conference on E-health Networking, Application 8 Services (Healthcom’13)
- 10.1109/CVPRW.2012.6239175 · DOI · Paper page
- 10.1007/s11042-016-3374-6 · DOI
- 10.1109/ICIP.2015.7350781 · DOI · Paper page
- 10.1007/978-3-642-33868-7_6 · DOI
- 10.1007/978-3-319-46454-1_17 · DOI · Paper page
- 10.1109/CVPR.2015.7298878 · DOI · Paper page
- 10.1109/TIP.2016.2552404 · DOI · Paper page
- 10.1007/978-3-319-46487-9_47 · DOI · Paper page
- 10.1007/s11263-009-0275-4 · DOI · Paper page
- 10.1109/CVPR.2016.213 · DOI · Paper page
- 10.1145/2207676.2208303 · DOI · Paper page
- 10.1109/ICCV.2019.00502 · DOI · Paper page
- 10.1007/s11263-013-0683-3 · DOI · Paper page
- 10.1109/TPAMI.2016.2640292 · DOI · Paper page
- 10.5244/C.31.72 · DOI
- 10.1145/3177757 · DOI
- Jain Arpit, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2571--2578
- Jain Manan, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 740--747
- 10.5555/2789272.2789280 · doi:10.5555/2789272.2789280
- 10.1109/TIP.2015.2456412 · DOI
- 10.1109/CVPRW.2017.44 · DOI
- Kuehne H., Proceedings of the IEEE International Conference on Computer Vision. 2556--2563
- 10.1109/CVPR.2008.4587756 · DOI · Paper page
- Li Bo, 2017, Proceedings of the IEEE International Conference on Multimedia Expo Workshops. 613--616
- Li Chao, 2017, Proceedings of the IEEE International Conference on Multimedia Expo Workshops. 597--600
- 10.24963/ijcai.2018/109 · DOI · Paper page
- 10.1109/CVPRW.2010.5543273 · DOI · Paper page
- 10.1007/978-3-319-46478-7_13 · DOI · Paper page
- 10.1109/CVPR.2014.109 · DOI · Paper page
- 10.1016/j.sigpro.2014.08.038 · DOI
- 10.1145/3132734.3132739 · DOI · Paper page
- 10.1007/978-3-030-01264-9_11 · DOI · Paper page
- 10.1109/CVPR.2016.333 · DOI · Paper page
- 10.1109/TIP.2015.2490551 · DOI
- Müller M., 2007, Technical Report CG-2007-2.
- 10.1109/WACV.2013.6474999 · DOI · Paper page
- 10.1109/CVPR.2013.98 · DOI · Paper page
- 10.1109/TPAMI.2016.2533389 · DOI · Paper page
- 10.1007/978-3-319-10605-2_48 · DOI · Paper page
- 10.1109/CVPR.2012.6247807 · DOI · Paper page
- 10.1007/s11263-015-0816-y · DOI · Paper page
- 10.1109/ICCV.2011.6126349 · DOI · Paper page
- 10.1109/WACV.2015.138 · DOI
- 10.1109/CVPR.2017.498 · DOI
- Simonyan Karen, 2014, Proceedings of the Advances in Neural Information Processing Systems. 568--576
- 10.1609/aaai.v31i1.11212 · DOI · Paper page
- Soomro Khurram, 2012, Amir Roshan Zamir, and Mubarak Shah
- Sung Jaeyong, 2011, Proceedings of the AAAI Conference on Artificial Intelligence. 47--55
- Sung Jaeyong, 2012, Proceedings of the IEEE International Conference on Robotics and Automation. 842--849
- 10.1109/CVPR.2013.341 · DOI · Paper page
- 10.1109/CVPR.2016.484 · DOI · Paper page
- Wang Hongsong, 2017, Proceedings of the IEEE International Conference on Multimedia Expo Workshops. 591--596
- 10.1109/CVPR.2012.6247813 · DOI · Paper page
- 10.1109/CVPR.2014.339 · DOI · Paper page
- 10.1145/2647868.2654912 · DOI
- Wang Limin, 2014, Action recognition and detection by combining motion and appearance features. THUMOS
- 10.1109/CVPR.2013.345 · DOI · Paper page
- 10.1007/978-3-319-10602-1_37 · DOI
- Wang Limin, 2015, CUHK8SIAT submission for THUMOS15 action recognition challenge. THUMOS
- 10.1109/CVPR.2017.678 · DOI · Paper page
- 10.1007/978-3-319-46484-8_2 · DOI · Paper page
- 10.1109/ICCV.2013.406 · DOI
- 10.1109/ICCV.2013.389 · DOI
- 10.1109/CVPR.2015.7299065 · DOI · Paper page
- 10.1145/2733373.2806222 · DOI · Paper page
- Xia Lu, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 20--27
- 10.1109/CVPR.2014.108 · DOI · Paper page
- 10.1145/3038917 · DOI
- 10.1109/CVPRW.2012.6239234 · DOI · Paper page
- 10.1109/ICCV.2013.342 · DOI · Paper page
- 10.1016/j.patcog.2016.05.019 · DOI · Paper page
- 10.1109/TCSVT.2017.2721108 · DOI
- 10.1109/ICCV.2013.442 · DOI
- 10.1609/aaai.v30i1.10451 · DOI · Paper page
- 10.1109/ICCV.2017.316 · DOI · Paper page
Cited by
Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics
Duan, L., Liu, J., Yang, W., Huang, T., & Gao, W. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3016485 · Cited by 260
“The network design follows [149].”
Self-citationMS2L: 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
Self-citationGuo, T., Liu, H., Chen, Z., Liu, M., Wang, T., & Ding, R. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i1.19957 · Cited by 202
“PKU-MMD Dataset (Liu et al. 2020): It contains almost 20,000 action sequences covering 51 action classes.”
Background
Metadata
- Authors
- Liu, J., Song, S., Liu, C., Li, Y., & Hu, Y.
- Venue
- ACM Transactions on Multimedia Computing, Communications, and Applications
- Published
- 2020-05-22
- Volume
- 16
- Issue
- 2
- Pages
- 1-24
- ISSN
- 1551-6857 (ISSN-L)
- 1551-6865
- OpenAlex
- W3033793613
- Cited by
- 95
- References
- 9
- FWCI
- 3.41
- Type
- journal article
- Language
- en
- Open access
- closed
- Funders
- Peking University Tencent Rhino Bird Innovation Fund
- Beijing Natural Science Foundation (4192025)
- Microsoft Research Asia
- National Natural Science Foundation of China (61772043)
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: A Benchmark Dataset and Comparison Study for Multi-modal Human Action Analytics. https://app.cochat.ai/papers/10.1145/3365212
- The paper
- Liu, J., Song, S., Liu, C., Li, Y., & Hu, Y. (2020). A Benchmark Dataset and Comparison Study for Multi-modal Human Action Analytics. ACM Transactions on Multimedia Computing, Communications, and Applications. https://doi.org/10.1145/3365212
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.