VLAD3: Encoding Dynamics of Deep Features for Action Recognition
The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Previous approaches to action recognition with deep features tend to process video frames only within a small temporal region, and do not model long-range dynamic information explicitly. However, such information is important for the accurate recognition of actions, especially for the discrimination of complex activities that share sub-actions, and when dealing with untrimmed videos. Here, we propose a representation, VLAD for Deep Dynamics (VLAD3), that accounts for different levels of video dynamics. It captures short-term dynamics with deep convolutional neural network features, relying on linear dynamic systems (LDS) to model medium-range dynamics. To account for long-range inhomogeneous dynamics, a VLAD descriptor is derived for the LDS and pooled over the whole video, to arrive at the final VLAD3representation. An extensive evaluation was performed on Olympic Sports, UCF101 and THUMOS15, where the use of the VLAD3representation leads to state-of-the-art results.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 2×
“This includes methods based on recurrent neural networks (RNNs) [6], or variants such as the long short-term memory (LSTM) of [9].”
BackgroundMethodLarge-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 5×
“While the long-range dynamics hypothesis has motivated the deployment of methods such as LSTM [4] or pooling of deep features along motion trajectories [33], the modeling of the long-range dynamics of deep learning features has so far received limited attention in the vision literature.”
BackgroundInfluentialHigh-dimensional signature compression for large-scale image classification
Sanchez, J., & Perronnin, F. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995504 · Cited by 272 · cited 1×
“Over the last decade, the dominant representation for both problems was the bag-of-words model, combining histograms of descriptors such as HoG or HoF and pooling over space-time volumes [24, 32].”
Background
Cited by
A review of Convolutional-Neural-Network-based action recognition
Yao, G., Lei, T., & Zhong, J. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.05.018 · Cited by 437
Self-Supervised Video Representation Learning with Odd-One-Out Networks
Fernando, B., Bilen, H., Gavves, E., & Gould, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.607 · Cited by 421
“There has also been unsupervised temporal feature encoding methods to capture the structure of videos for action classification [13, 14, 15, 29, 36].”
Computer vision-based hand gesture recognition for human-robot interaction: a review
Qi, J., Ma, L., Cui, Z., & Yu, Y. (2024) · Complex & Intelligent Systems · doi:10.1007/s40747-023-01173-6 · Cited by 267
Ambient 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
“[71] (2016) Recognition of activities of daily living Vector of locally aggregated descriptor features were applied to analyze deep dynamics of the activities and later combined with deep convolutional neural networks.”
MethodMulti-Modality Multi-Task Recurrent Neural Network for Online Action Detection
Liu, J., Li, Y., Song, S., Xing, J., Lan, C., & Zeng, W. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2799968 · Cited by 62
Self-citation
Metadata
- Authors
- Li, Y., Li, W., Mahadevan, V., & Vasconcelos, N.
- Venue
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2016-06
- Pages
- 1951-1960
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2465313502
- Cited by
- 83
- References
- 6
- FWCI
- 4.93
- Type
- conference paper
- 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.