Multimodal Keyless Attention Fusion for Video Classification
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
The problem of video classification is inherently sequential and multimodal, and deep neural models hence need to capture and aggregate the most pertinent signals for a given input video. We propose Keyless Attention as an elegant and efficient means to more effectively account for the sequential nature of the data. Moreover, comparing a variety of multimodal fusion methods, we find that Multimodal Keyless Attention Fusion is the most successful at discerning interactions between modalities. We experiment on four highly heterogeneous datasets, UCF101, ActivityNet, Kinetics, and YouTube-8M to validate our conclusion, and show that our approach achieves highly competitive results. Especially on large-scale data, our method has great advantages in efficiency and performance. Most remarkably, our best single model can achieve 77.0% in terms of the top-1 accuracy and 93.2% in terms of the top-5 accuracy on the Kinetics validation set, and achieve 82.2% in terms of GAP@20 on the official YouTube-8M test set.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
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
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
Two-Stream Convolutional Networks for Action Recognition in Videos
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1406.2199 · Cited by 6,756
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
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11231 · Cited by 4,636 · cited 1×
“For Kinetics, we extract RGB and flow features using InceptionResNet-v2 (Szegedy et al. 2016) and extract audio features with a VGG-16 (Simonyan and Zisserman 2014a).”
MethodUcf101: A dataset of 101 human actions classes from videos in the wild
Soomro, K., Zamir, A. R., & Shah, M. (2012) · arXiv · doi:10.48550/arxiv.1212.0402 · Cited by 4,575
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
ActivityNet: 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
Unsupervised Learning of Video Representations using LSTMs
Srivastava, N., Mansimov, E., & Salakhutdinov, R. (2015) · arXiv · doi:10.48550/arxiv.1502.04681 · Cited by 1,861
A Duality Based Approach for Realtime TV-L 1 Optical Flow
Zach, C., Pock, T., & Bischof, H. (2007) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-74936-3_22 · Cited by 1,658 · cited 1×
“To overcome the shortcomings of 2D CNNs and better account for spatio-temporal information, the optical flow method (Zach, Pock, and Bischof 2007) was proposed to consider the variation in the surrounding frames.”
MethodAction 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×
“…2013; Peng et al. 2016) as well as deep learning approaches (Zhang et al. 2016; Simonyan and Zisserman 2014b; Sun et al. 2015; Li et al. 2016; Wang, Qiao, and Tang 2015; Feichtenhofer, Pinz, and Zisserman 2016; Tran et al. 2015; Wang et al. 2016a; Feichtenhofer, Pinz, and Wildes 2016;…”
BackgroundMultiple Object Recognition with Visual Attention
Ba, J., Mnih, V., & Kavukcuoglu, K. (2014) · arXiv · doi:10.48550/arxiv.1412.7755 · Cited by 808
Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
Hara, K., Kataoka, H., & Satoh, Y. (2017) · 2017 IEEE International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw.2017.373 · Cited by 726 · cited 1×
“On Kinetics, we compare it with recently published results (Tran et al. 2015; Hara, Kataoka, and Satoh 2017; Carreira and Zisserman 2017).”
Result
Cited by
Deep Multimodal Representation Learning: A Survey
Guo, W., Wang, J., & Wang, S. (2019) · IEEE Access · doi:10.1109/access.2019.2916887 · Cited by 535
EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition
Kazakos, E., Nagrani, A., Zisserman, A., & Damen, D. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00559 · Cited by 302
MFAS: Multimodal Fusion Architecture Search
Perez-Rua, J.-M., Vielzeuf, V., Pateux, S., Baccouche, M., & Jurie, F. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00713 · Cited by 193
Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification
You, R., Guo, Z., Cui, L., Long, X., Bao, Y., & Wen, S. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6964 · Cited by 187
Self-citationHear Me out: Fusional Approaches for Audio Augmented Temporal Action Localization
Bagchi, A., Mahmood, J., Fernandes, D., & Sarvadevabhatla, R. (2022) · Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications · doi:10.5220/0010832700003124 · Cited by 29
Metadata
- Authors
- Long, X., Gan, C., Melo, G., Liu, X., Li, Y., Li, F., & Wen, S.
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2018-04-27
- Volume
- 32
- Issue
- 1
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2789221157
- Cited by
- 122
- References
- 17
- FWCI
- 4.38
- Type
- conference paper
- Language
- en
- Open access
- diamond
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.