Multi-Velocity Neural Networks for Facial Expression Recognition in Videos
Open accessAbstract
We present a new action recognition deep neural network which adaptively learns the best action velocities in addition to the classification. While deep neural networks have reached maturity for image understanding tasks, we are still exploring network topologies and features to handle the richer environment of video clips. Here, we tackle the problem of multiple velocities in action recognition, and provide state-of-the-art results for facial expression recognition, on known and new collected datasets. We further provide the training steps for our semi-supervised network, suited to learn from huge unlabeled datasets with only a fraction of labeled examples.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Deep learning is used for learning spatial feature representations in human affect recognition.
“Learning spatial feature representations. For images [61], short-term 6 image sequences [62] and audio segments [54], DNNs and especially CNNs are used to learn spatial feature representations.”
From Deep learning for human affect recognition: Insights and new developments (2021) · cites this paper as [62]
Slow fusion treats the time domain like a spatial domain, progressively learning low-level to high-level temporal features, and effectively reduces the amount of parameters required due to temporal depth, allowing for more input frames.
“For example, Gupta et al. [62] used a variant called slow fusion [153], which treats the time domain like a spatial domain, progressively learning low-level to highlevel temporal features. As the amount of parameters required due to the temporal depth of the input is effectively reduced, this allows for more input frames.”
From Deep learning for human affect recognition: Insights and new developments (2021) · cites this paper as [62]
Gupta et al. demonstrated the feasibility of semi-supervised learning for affective computing, achieving promising results using 2777 labeled face videos to learn from the AUTOENCODER dataset of 6.5M unlabeled face video clips.
“Gupta et al. [62] demonstrated the feasibility of semi-supervised learning for affective computing, achieving promising results using 2777 labeled face videos to learn from the AUTOENCODER dataset of 6.5M unlabeled face video clips.”
From Deep learning for human affect recognition: Insights and new developments (2021) · cites this paper as [62]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
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 · see citing works
Joint Fine-Tuning in Deep Neural Networks for Facial Expression Recognition
Jung, H., Lee, S., Yim, J., Park, S., & Kim, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.341 · Cited by 781 · cited 1× · see citing works
“Very recently superior results have been shown [14], [42], [43], [44], [45] using deep neural nets to combine labels and unlabeled data in the same package.”
Background
Flagged first, then by citations
Cited by
Sorted by citations
Deep learning for human affect recognition: Insights and new developments
Rouast, P. V., Adam, M. T. P., & Chiong, R. (2021) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2018.2890471 · Cited by 243 · see citing works
Shoumy, N. J., Ang, L.-M., Seng, K. P., Rahaman, D. M. M., & Zia, T. (2020) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2019.102447 · Cited by 171 · see citing works
- Authors
- Gupta, O., Raviv, D., & Raskar, R.
- Affiliations
- Massachusetts Institute of Technology (US)
- Tel Aviv University (IL)
- Venue
- IEEE Transactions on Affective Computing
- Published
- 2019-04-01
- Volume
- 10
- Issue
- 2
- Pages
- 290-296
- ISSN
- 1949-3045 (ISSN-L)
- 2371-9850
- OpenAlex
- W2624323315
- Cited by
- 17
- References
- 2
- Citations by year
- 2024: 1 · 2023: 1 · 2022: 2 · 2021: 2 · 2020: 3 · 2019: 5 · 2018: 1 · 2017: 2
- FWCI
- 3.92
- Type
- journal article
- Language
- en
- Open access
- green
- hdl.handle.net
- Licence
- Locations
- IEEE Transactions on Affective Computing (publishedVersion)
- DSpace@MIT (Massachusetts Institute of Technology) (submittedVersion, cc-by-nc-sa)
- Topics
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Keywords
- facial expression recognition, video action recognition, semi-supervised learning, unlabeled data
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
