Multimodal Graph-Based Reranking for Web Image Search

By Meng Wang, Hao Li, Dacheng Tao, Ke Lu, Xindong Wu. 2012

366 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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. Xiangnan He
2. Tat-seng Chua
3. Xiang Wang
4. Liqiang Nie
5. Meng Wang
6. Hanwang Zhang
7. Richang Hong
8. Dacheng Tao

In Computer Vision and Pattern Recognition

1. Yi Yang
2. Dacheng Tao
3. Tat-seng Chua
4. Qi Tian
5. Luc Van Gool
6. Liang Zheng
7. Xiangnan He
8. Xiaogang Wang

Citations in the corpus

• Neural Collaborative Filtering (2017, methodology): “To build a multi-media recommender system, we need to develop effective methods to learn from multi-view and multi-modal data [13, 40].”
• Complementary Incremental Hashing With Query-Adaptive Re-Ranking for Image Retrieval (2020, methodology): “There are also some retrieval methods employing re-ranking and query-adaptive techniques to further improve their retrieval performance [19]–[24].”
• Learning to Rank Using User Clicks and Visual Features for Image Retrieval (2015, methodology): “5) Multiview Graph-Based Learning for Web Image Reranking [29]: Visual reranking is conducted based on the initial ranking result in this method, which we call MCR.”
• Learning of Multimodal Representations With Random Walks on the Click Graph (2016, methodology): “, [13], [21], [22]) which help re-rank the initial returned list to make a better relevance score.”
• Video Question Answering via Attribute-Augmented Attention Network Learning (2017, background): “Currently, most of the existing visual question answering methods mainly focuson the problem of static image question answering [1, 10–12, 15, 17].”
• An Attribute-Assisted Reranking Model for Web Image Search (2015, background): “The average relevance scores at different ranking positions and the fitted curve [26].”
• Attentive Collaborative Filtering: Multimedia Recommendation with Item- and Component-Level Attention (2017, background): “For example, several efforts have been dedicated to conduct the video recommendation utilizing different context information, such as the multi-modal relevance [26, 34], cross-domain knowledge [11, 14] and latent attributes feature [12, 44].”
• Deep Multimodal Distance Metric Learning Using Click Constraints for Image Ranking (2017, methodology): “The learning to rank method of RankSVM [58] was applied with click features to present their performance, and the reranking methods [59] were operated based on the outcome of RankSVM.”
• Query-adaptive late fusion for image search and person re-identification (2015, methodology): “Another good practise consists in propagating the rank list along nodes in a graph [17, 32, 35].”
• Deep Item-based Collaborative Filtering for Top-N Recommendation (2018, background): “With such an important role in online information systems, recommendation has become an active topic of research and attracted increasing attention in information-retrieval and data-mining communities [16, 39, 41, 45].”