The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
MDLFace: Memorability augmented deep learning for video face recognition
Abstract
Videos have ample amount of information in the form of frames that can be utilized for feature extraction and matching. However, face images in not all of the frames are “memorable” and useful. Therefore, utilizing all the frames available in a video for recognition does not necessarily improve the performance but significantly increases the computation time. In this research, we present a memorability based frame selection algorithm that enables automatic selection of memorable frames for facial feature extraction and matching. A deep learning algorithm is then proposed that utilizes a stack of denoising autoencoders and deep Boltzmann machines to perform face recognition using the most memorable frames. The proposed algorithm, termed as MDLFace, is evaluated on two publicly available video face databases, Youtube Faces and Point and Shoot Challenge. The results show that the proposed algorithm achieves state-of-the-art performance at low false accept rates.
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?
Current evaluations of XAI methods typically analyze peculiarities of the explanation methods without accounting for interaction with the final user.
“A limitation of current evaluations of XAI methods is that they typically analyze peculiarities of the explanation methods without accounting for the interaction with the final user [3, 6, 7].”
From Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence (2023) · cites this paper as [6]
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
Flagged first, then by citations
Research works printed but not linked: 33
- 10.1109/CVPR.2011.5995566 · DOI
- 10.3758/BF03199666 · DOI · Paper page
- 10.1016/j.cviu.2005.02.002 · DOI
- taigman, 2014, Deepface: Closing the gap to human-level performance in face verification, IEEE Conference on Computer Vision and Pattern Recognition
- 10.1109/CVPR.2014.242 · DOI
- 10.1093/cercor/bhl138 · DOI · Paper page
- 10.1142/S0218001412660024 · DOI
- 10.1109/TIFS.2014.2318433 · DOI
- 10.3758/BF03210319 · DOI · Paper page
- 10.1126/science.1127647 · DOI · Paper page
- hinton, 2012, A better way to pretrain deep boltzmann machines, Advances in neural information processing systems, 25, 2447
- isola, 2011, Understanding the intrinsic memorability of images, Advances in neural information processing systems, 2429
- 10.1109/ACCESS.2014.2344667 · DOI
- 10.1109/CVPR.2011.5995721 · DOI
- vincent, 2010, Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion, Journal of Machine Learning Research, 11, 3371
- collobert, 2011, Natural language processing (almost) from scratch, The Journal of Machine Learning Research, 12, 2493
- goh, 2005, The cmu face in action (fia) database, Analysis and Modelling of Faces and Gestures 3723 of Lecture Notes in Computer Science, 255
- gross, 2001, The cmu motion of body (mobo) database, Technical Report CMU-RI-TR 01-18
- salakhutdinov, 2009, Deep boltzmann machines, International Conference on Artificial Intelligence and Statistics, 448
- rifai, 2011, The manifold tangent classifier, Advances in neural information processing systems, 2294
- 10.1109/CVPR.2007.383378 · DOI
- jain, 2005, Handbook of Face Recognition
- seide, 2011, Conversational speech transcription using context-dependent deep neural networks, InterSpeech, 437, 10.21437/Interspeech.2011-169 · DOI
- ross, 2006, Handbook of Multibiometrics (International Series on Biometrics)
- liu, 2003, Video-based face recognition using adaptive hidden markov models, IEEE Conference on Computer Vision and Pattern Recognition, 340
- 10.1109/WMVC.2007.29 · DOI
- 10.1109/TIFS.2012.2223684 · DOI
- bengio, 2007, Greedy layer-wise training of deep networks, Advances in neural information processing systems, 19, 153
- 10.1109/BTAS.2013.6712704 · DOI
- 10.1109/TPAMI.2013.50 · DOI · Paper page
- rrnyi, 1961, On measures of entropy and information, Berkeley Symposium on Mathematical Statistics and Probability, 547
- 10.1371/journal.pone.0099212 · DOI
- 10.1109/CVPRW.2013.33 · DOI
Cited by
Sorted by citations
Ali, S., Abuhmed, T., El-Sappagh, S., Muhammad, K., Alonso-Moral, J. M., Confalonieri, R., Guidotti, R., Del Ser, J., Díaz-Rodríguez, N., & Herrera, F. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101805 · Cited by 1,762
Metadata
- Authors
- Goswami, G., Bhardwaj, R., Singh, R., & Vatsa, M.
- Affiliations
- Indraprastha Institute of Information Technology Delhi (IN)
- Venue
- IEEE International Joint Conference on Biometrics
- Publisher
- IEEE
- Published
- 2014-09
- Pages
- 1-7
- OpenAlex
- W2083708558
- Cited by
- 53
- References
- 1
- Citations by year
- 2024: 2 · 2023: 2 · 2022: 2 · 2021: 6 · 2020: 2 · 2019: 7 · 2018: 9 · 2017: 7 · 2016: 9 · 2015: 6 · 2014: 1
- FWCI
- 4.12
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Joint Conference on Biometrics (IJCB) (publishedVersion)
- Funders
- Department of Electronics and Information Technology, Ministry of Communications and Information Technology
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face and Expression Recognition
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Keywords
- video-based face recognition, frame selection, denoising autoencoder, deep Boltzmann machine, facial feature extraction, facial feature matching, computational efficiency, false acceptance rate
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
