Learning from Collective Intelligence: Feature Learning Using Social Images and Tags
The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Feature representation for visual content is the key to the progress of many fundamental applications such as annotation and cross-modal retrieval. Although recent advances in deep feature learning offer a promising route towards these tasks, they are limited in application domains where high-quality and large-scale training data are expensive to obtain. In this article, we propose a novel deep feature learning paradigm based on social collective intelligence, which can be acquired from the inexhaustible social multimedia content on the Web, in particular, largely social images and tags. Differing from existing feature learning approaches that rely on high-quality image-label supervision, our weak supervision is acquired by mining the visual-semantic embeddings from noisy, sparse, and diverse social image collections. The resultant image-word embedding space can be used to (1) fine-tune deep visual models for low-level feature extractions and (2) seek sparse representations as high-level cross-modal features for both image and text. We offer an easy-to-use implementation for the proposed paradigm, which is fast and compatible with any state-of-the-art deep architectures. Extensive experiments on several benchmarks demonstrate that the cross-modal features learned by our paradigm significantly outperforms others in various applications such as content-based retrieval, classification, and image captioning.
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
DeepWalk: online learning of social representations
Perozzi, B., Al-Rfou, R., & Skiena, S. (2014) · Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2623330.2623732 · Cited by 10,123 · cited 6×
“However, in order to demonstrate the motivation of why Perozzi et al. [2014] use the model in Mikolov et al. [2013], they only proved that the node pairwise distribution is similar to the word power-law distribution in natural language.”
BackgroundMethodInfluentialShow and tell: A neural image caption generator
Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298935 · Cited by 6,318
Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L.-J., Shamma, D. A., et al. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-016-0981-7 · Cited by 5,107
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019 · cited 1×
“Although deep learning features have been shown to outperform hand-engineered features on many vision benchmarks [Donahue et al. 2014; Razavian et al. 2014], there is limited research on how to further fine-tune the features for specific domains, especially for the social multimedia in the wild.”
BackgroundNUS-WIDE: a real-world web image database from National University of Singapore
Chua, T.-S., Tang, J., Hong, R., Li, H., Luo, Z., & Zheng, Y. (2009) · Proceedings of the ACM International Conference on Image and Video Retrieval · doi:10.1145/1646396.1646452 · Cited by 3,025 · cited 15×
“For example, as shown in Figure 1(a), diverse tags such as “office,” “chair,” and “desk” may be used to describe the image; “dog park” is The embedding is learned on SBU but we report the test results on NUSWIDE.”
BackgroundMethodInfluentialSelf-citationHogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
Niu, F., Recht, B., Re, C., & Wright, S. J. (2011) · arXiv · doi:10.48550/arxiv.1106.5730 · Cited by 1,211
Image retrieval using scene graphs
Johnson, J., Krishna, R., Stark, M., Li, L.-J., Shamma, D. A., Bernstein, M. S., & Fei-Fei, L. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298990 · Cited by 1,101
Local Graph Partitioning using PageRank Vectors
Andersen, R., Chung, F., & Lang, K. (2006) · 2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06) · doi:10.1109/focs.2006.44 · Cited by 967
Cited by
A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications
Cai, H., Zheng, V. W., & Chang, K. C.-C. (2018) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2018.2807452 · Cited by 2,034
Visual Translation Embedding Network for Visual Relation Detection
Zhang, H., Kyaw, Z., Chang, S.-F., & Chua, T.-S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.331 · Cited by 586
Self-citationVideo Question Answering via Gradually Refined Attention over Appearance and Motion
Xu, D., Zhao, Z., Xiao, J., Wu, F., Zhang, H., He, X., & Zhuang, Y. (2017) · Proceedings of the 25th ACM international conference on Multimedia · doi:10.1145/3123266.3123427 · Cited by 429
Self-citationYu, H., Yang, L. T., Zhang, Q., Armstrong, D., & Deen, M. J. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.04.157 · Cited by 412
Depression Detection via Harvesting Social Media: A Multimodal Dictionary Learning Solution
Shen, G., Jia, J., Nie, L., Feng, F., Zhang, C., Hu, T., Chua, T.-S., & Zhu, W. (2017) · Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/536 · Cited by 383
Self-citation
Metadata
- Authors
- Zhang, H., Shang, X., Luan, H., Wang, M., & Chua, T.-S.
- Venue
- ACM Transactions on Multimedia Computing, Communications, and Applications
- Published
- 2016-11-02
- Volume
- 13
- Issue
- 1
- Pages
- 1-23
- ISSN
- 1551-6857 (ISSN-L)
- 1551-6865
- OpenAlex
- W2546529582
- Cited by
- 113
- References
- 10
- FWCI
- 18.26
- Type
- journal article
- 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.