Zero-Shot Event Detection Using Multi-modal Fusion of Weakly Supervised Concepts
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Current state-of-the-art systems for visual content analysis require large training sets for each class of interest, and performance degrades rapidly with fewer examples. In this paper, we present a general framework for the zeroshot learning problem of performing high-level event detection with no training exemplars, using only textual descriptions. This task goes beyond the traditional zero-shot framework of adapting a given set of classes with training data to unseen classes. We leverage video and image collections with free-form text descriptions from widely available web sources to learn a large bank of concepts, in addition to using several off-the-shelf concept detectors, speech, and video text for representing videos. We utilize natural language processing technologies to generate event description features. The extracted features are then projected to a common high-dimensional space using text expansion, and similarity is computed in this space. We present extensive experimental results on the large TRECVID MED [26] corpus to demonstrate our approach. Our results show that the proposed concept detection methods significantly outperform current attribute classifiers such as Classemes [34], ObjectBank [21], and SUN attributes[28] . Further, we find that fusion, both within as well as between modalities, is crucial for optimal performance.
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
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955
Speeded-Up Robust Features (SURF)
Bay, H., Ess, A., Tuytelaars, T., & Van Gool, L. (2008) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2007.09.014 · Cited by 13,557
Davis, S., & Mermelstein, P. (1980) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1980.1163420 · Cited by 5,465
Improving the Fisher Kernel for Large-Scale Image Classification
Perronnin, F., Sánchez, J., & Mensink, T. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_11 · Cited by 2,588 · cited 1×
“We then consider the Fisher vector encoding as proposed in [29] and represent each video by the normalized gradients of the GMM log-likelihood Gk X ∈ R and Gk X ∈ R with respect to the Gaussian mean μk and standard deviation parameters σk, respectively.”
MethodDense Trajectories and Motion Boundary Descriptors for Action Recognition
Wang, H., Kläser, A., Schmid, C., & Liu, C.-L. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-012-0594-8 · Cited by 1,669
Image Classification with the Fisher Vector: Theory and Practice
Sánchez, J., Perronnin, F., Mensink, T., & Verbeek, J. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0636-x · Cited by 1,498 · cited 1×
“Possible coding techniques include Hard Quantization [7], Soft Quantization [36], Sparse Coding [5] and Fisher Vectors [32], using a codebook trained in an unsupervised manner from a large set of feature vectors.”
Method
Cited by
Learning Deep Representations of Fine-Grained Visual Descriptions
Reed, S., Akata, Z., Lee, H., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.13 · Cited by 760
Zero-Shot Learning via Semantic Similarity Embedding
Zhang, Z., & Saligrama, V. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.474 · Cited by 629
“The target domain is described by a joint distribution of images/videos and labels [16, 41].”
BackgroundDeep Multimodal Representation Learning: A Survey
Guo, W., Wang, J., & Wang, S. (2019) · IEEE Access · doi:10.1109/access.2019.2916887 · Cited by 535
A Survey of Zero-Shot Learning: Settings, Methods, and Applications
Wang, W., Zheng, V. W., Yu, H., & Miao, C. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3293318 · Cited by 528
“In retrieval problems, zero-shot event detection (also called zeroexample event detection) [15, 21, 30, 153] aims to retrieve relevant videos based on the text descriptions or just by the name of the event.”
BackgroundZero-Shot Learning via Joint Latent Similarity Embedding
Zhang, Z., & Saligrama, V. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.649 · Cited by 336
DevNet: A Deep Event Network for multimedia event detection and evidence recounting
Gan, C., Wang, N., Yang, Y., Yeung, D.-Y., & Hauptmann, A. G. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298872 · Cited by 312
Objects2action: Classifying and Localizing Actions without Any Video Example
Jain, M., Gemert, J. C. V., Mensink, T., & Snoek, C. G. M. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.521 · Cited by 142
Event-based media processing and analysis: A survey of the literature
Tzelepis, C., Ma, Z., Mezaris, V., Ionescu, B., Kompatsiaris, I., Boato, G., Sebe, N., & Yan, S. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2016.05.005 · Cited by 49
A Multi-Modal Fusion Method Based on Higher-Order Orthogonal Iteration Decomposition
Liu, F., Chen, J., Tan, W., & Cai, C. (2021) · Entropy · doi:10.3390/e23101349 · Cited by 13
Metadata
- Authors
- Wu, S., Bondugula, S., Luisier, F., Zhuang, X., & Natarajan, P.
- Venue
- 2014 IEEE Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2014-06
- Pages
- 2665-2672
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2021899621
- Cited by
- 111
- References
- 7
- FWCI
- 10.81
- 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.