Deep Local Video Feature for Action Recognition
Open accessThe DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
We investigate the problem of representing an entire video using CNN features for human action recognition. End-to-end learning of CNN/RNNs is currently not possible for whole videos due to GPU memory limitations and so a common practice is to use sampled frames as inputs along with the video labels as supervision. However, the global video labels might not be suitable for all of the temporally local samples as the videos often contain content besides the action of interest. We therefore propose to instead treat the deep networks trained on local inputs as local feature extractors. The local features are then aggregated to form global features which are used to assign video-level labels through a second classification stage. We investigate a number of design choices for this local feature approach. Experimental results on the HMDB51 and UCF101 datasets show that a simple maximum pooling on the sparsely sampled local features leads to significant performance improvement.
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
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
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
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
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 1×
“[21, 22, 23] provide insightful analyses on improving two-stream frameworks such as pre-training two-stream CNNs, using smaller learning rates, using deeper networks, etc.”
Background
Cited by
A Comprehensive Survey of Vision-Based Human Action Recognition Methods
Zhang, H.-B., Zhang, Y.-X., Zhong, B., Lei, Q., Yang, L., Du, J.-X., & Chen, D.-S. (2019) · Sensors · doi:10.3390/s19051005 · Cited by 503
“In addition, Lan [86] and Zhou [87] also enhanced the recognition results of TSN. Similarly, based on the idea of 3D (Three Dimension) convolutional networks, many researchers have attempted to extend different 2D convolutional networks to 3D spatiotemporal structures for the learning and recognition of human action f…”
BackgroundHidden Two-Stream Convolutional Networks for Action Recognition
Zhu, Y., Lan, Z., Newsam, S., & Hauptmann, A. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-20893-6_23 · Cited by 278
Self-citationUnsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval
Wu, G., Han, J., Guo, Y., Liu, L., Ding, G., Ni, Q., & Shao, L. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2882155 · Cited by 148
Deep Learning for Video Classification: A Review
Rehman, A., & Belhaouari, S. B. (2021) · doi:10.36227/techrxiv.15172920 · Cited by 17
Metadata
- Authors
- Lan, Z., Zhu, Y., Hauptmann, A. G., & Newsam, S.
- Venue
- 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
- Publisher
- IEEE
- Published
- 2017-07
- Pages
- 1219-1225
- OpenAlex
- W2580899942
- Cited by
- 114
- References
- 4
- FWCI
- 4.69
- 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.