Multimodal semi-supervised learning for image classification

By Matthieu Guillaumin, Jakob Verbeek, Cordelia Schmid. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010

434 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e0f49caabbf79ffda35432219bb0ec9b41753dff

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Trevor Darrell
2. Yoshua Bengio
3. Mohit Bansal
4. Quoc V. Le
5. Yi Yang
6. Andrew Zisserman
7. Ruslan Salakhutdinov
8. Bernt Schiele

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Xiaogang Wang
3. Yi Yang
4. Dacheng Tao
5. Ming-Hsuan Yang
6. Andrew Zisserman
7. Trevor Darrell
8. Andrea Vedaldi

Citations in the corpus

• Topic Modeling of Multimodal Data: An Autoregressive Approach (2014, background): “Multimodal data modeling, which combines information from different sources, is increasingly attracting attention in computer vision [1, 2, 3, 4, 5, 6, 7].”
• Multimodal learning with deep Boltzmann machines (2012, background): “[3], based on multiple kernel learning framework, further demonstrated that an additional text modality can improve the accuracy of SVMs on various object recognition tasks.”
• A Multi-View Embedding Space for Modeling Internet Images, Tags, and Their Semantics (2012, methodology): “Like Guillaumin et al. (2010), we use the linear kernel for T , which corresponds to counting the number of common tags between two images.”
• Cluster Canonical Correlation Analysis (2014, methodology): “The images were provided by the Pascal challenge [6] and the text annotations were collected in [8].”
• Discriminative Transfer Learning with Tree-based Priors (2013, neutral): “609 Multiple Kernel Learning SVMs [7] 0.”
• Author manuscript, published in "International Journal of Computer Vision (2013)" International Journal of Computer Vision manuscript No. (will be inserted by the editor) Image Classification with the Fisher Vector: Theory and Practice (2013, positive): “Also the SIFT only FV is among the best performing descriptors.”
• A Unified Framework for Multimodal Domain Adaptation (2018, background): “A semi-supervised learning approach is proposed in [20] which exploits the information contained in the tags associated with unlabeled images.”
• Exploring Context and Content Links in Social Media: A Latent Space Method (2012, background): “Analysis and inference with multimodal data [2], [13], [19] is one of most important research topics in computer vision and patter recognition areas.”
• Improving Neural Networks with Dropout (2013, methodology): “Dropout with pretrained models achieves state-of-the-art results, outperforming the best previously published results on this dataset that were obtained with an Multiple Kernel Learning based SVM model [4].”
• Object-Centric Spatial Pooling for Image Classification (2012, methodology): “1 We make use of only one type of low-level image descriptor in contrast to [9, 31],”
• Improving Image-Sentence Embeddings Using Large Weakly Annotated Photo Collections (2014, background): “to multi-view learning [13, 7], transfer learning [14–16], and methods that use Internet data to help recognition [17–21].”
• Label Propagation for Deep Semi-Supervised Learning (2019, background): “The same holds for SSL in image classi-fication [10, 16, 4, 37].”