Data fusion through cross-modality metric learning using similarity-sensitive hashing

By Michael M. Bronstein, A. Bronstein, Fabrice Michel, Nikos Paragios. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010

482 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c5a92ab927e28218f844d2e2eaed18119b4e947e

How researchers see this paper

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

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Yi Yang
3. Luc Van Gool
4. Ling Shao
5. Qi Tian
6. Xiaogang Wang
7. Ming-Hsuan Yang
8. Alan L. Yuille

Citations in the corpus

• SCH-GAN: Semi-Supervised Cross-Modal Hashing by Generative Adversarial Network (2018, methodology): “• CMSSH [35] models hashing learning as a classification problem, and it is learned in a boosting manner.”
• Pairwise Relationship Guided Deep Hashing for Cross-Modal Retrieval (2017, methodology): “In recent years, various hashing methods have been proposed for CMH, which can be roughly classified into unsupervised methods (Ding, Guo, and Zhou 2014; Song et al. 2013; Zhou, Ding, and Guo 2014) and supervised methods (Bronstein et al. 2010; Kumar and Udupa 2011).”
• A Survey on Deep Learning for Multimodal Data Fusion (2020, background): “…mining, aims to integrate the data of different distributions, sources, and types into a global space in which both intermodality and cross-modality can be represented in a uniform manner (Bramon et al., 2012; Bronstein, Bronstein, Michel, & Paragios, 2010; Poria, Cambria, Bajpai, & Hussain, 2017).”
• Deformable medical image registration: setting the state of the art with discrete methods. (2011, background): “The underlying idea is to map one set of observations to another using a linear or non-linear mapping learned from training examples (33).”
• Zero-Shot Sketch-Image Hashing (2018, methodology): “As an extension of conventional data hashing techniques [20, 51, 21, 53], cross-modal hashing [4, 13, 71, 37, 34, 27, 5, 6] show great potential in retrieving heterogeneous data with high efficiency due to the computationally cheap Hamming space matching, which is recently adopted to large-scale…”
• Deep Sketch Hashing: Fast Free-Hand Sketch-Based Image Retrieval (2017, methodology): “Moreover, DSH is also compared with state-of-theart cross-modality hashing techniques: Collective Matrix Factorization Hashing (CMFH) [10], Cross-Modal SemiSupervised Hashing (CMSSH) [2], Cross-View Hashing (CVH) [26], Semantic Correlation Maximization (SCMSeq and SCM-Orth) [64], Semantics-Preservin”
• Creating Something From Nothing: Unsupervised Knowledge Distillation for Cross-Modal Hashing (2020, methodology): “From this perspective, the supervised CMH methods [1, 25, 22, 34, 44], receiving additional supervision, often produce more accurate results, and the unsupervised counterparts, while achieving lower performance, are relatively easier to deploy to real-world scenarios.”
• Shape google: Geometric words and expressions for invariant shape retrieval (2011, methodology): “Finally, another promising direction is the use of mul­timodal hashing [Bronstein et al. 2010e] to cope with the problem of cross-representation retrieval and different versions of vocabularies.”
• Linear cross-modal hashing for efficient multimedia search (2013, unknown): “Keywords Cross-modal, hashing, index, multimedia search”
• Cross-Modal Retrieval With CNN Visual Features: A New Baseline (2017, background): “To address the problem of prohibitively expensive nearest neighbor search, some hashingbased approaches [3], [26], [28], [43], [44], [59], [65], [67], [69], [70] to large scale similarity search have drawn much interest from the cross-modal retrieval community.”
• Deep Visual-Semantic Hashing for Cross-Modal Retrieval (2016, methodology): “Typical learning methods include metric learning [4, 25], neural network [30], and correlation analysis [43, 39].”
• Learning Discriminative Binary Codes for Large-scale Cross-modal Retrieval (2017, methodology): “, unsupervised methods [12], [14], [15], [23]–[25] and supervised methods [26]–[31].”
• Unsupervised Semantic-Preserving Adversarial Hashing for Image Search (2019, background): “Therefore more attention is being paid to hash-based methods [20], [21], [23], [31]–[36], which have relative low storage cost and a fast query speed.”
• Cross-Modal Similarity Learning: A Low Rank Bilinear Formulation (2014, methodology): “…the deep neural network (Ngiam et al. 2011; Srivastava and Salakhutdinov 2012), domain transfer (Duan, Xu, and Tsang 2012; Kulis, Saenko, and Dar-rell 2011; Socher et al. 2013), etc. (Bronstein et al. 2010; Jia, Salzmann, and Darrell 2011; Zhuang and Hoi 2011; Zhuang et al. 2013; Gong et al. 2014).”
• Learning to Hash for Indexing Big Data—A Survey (2015, background): “In addition, this emerging hash learning framework can be exploited for some general machine learning and data mining tasks, including cross-modality data fusion [139], large-scale optimization [140], largescale classification and regression [141], collaborative filtering [142], and recommendation [”
• Multimodal Machine Learning: A Survey and Taxonomy (2017, background): “The idea of cross-modal hashing is to create such codes for cross-modal retrieval [27], [93], [113].”
• Deep Bayesian Hashing with Center Prior for Multi-modal Neuroimage Retrieval (2020, background): “Supervised cross-modal hashing methods [25], [35] can explore the semantic information to enhance data correlation across different modalities, thus usually achieving superior performance compared to their unsupervised counterparts.”