Collective Matrix Factorization Hashing for Multimodal Data

By Guiguang Ding, Yuchen Guo, Jile Zhou. 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

614 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a1dfb0d1519ba472ed9e5d93e438b608109010af

How researchers see this paper

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

In Aerospace Engineering

1. Yuxin Peng
2. Wu-Jun Li
3. Qing-Yuan Jiang
4. Fumin Shen
5. Lingxi Xie
6. Li Liu
7. Ling Shao
8. Yuming Shen

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Ling Shao
3. Qi Tian
4. Yi Yang
5. Cheng Deng
6. Luc Van Gool
7. Alan L. Yuille
8. Lingxi Xie

Citations in the corpus

• Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval (2018, methodology): “[8] learned a unified binary code by performing a matrix factorization with a latent factor model.”
• Zero-Shot Sketch-Image Hashing (2018, methodology): “As an extension of conventional data hashing techniques [51, 20, 39, 54, 53], cross-modal hashing [4, 13, 72, 36, 33, 26, 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”
• Self-Supervised Learning from Web Data for Multimodal Retrieval (2019, neutral): “631 CMFH [40] MIRFlickr 0.”
• A Survey of Multi-View Representation Learning (2016, neutral): “[175] put forward collective matrix factorization hashing to learn unified hash codes by CMF with a latent factor model from different modalities of one instance.”
• Creating Something From Nothing: Unsupervised Knowledge Distillation for Cross-Modal Hashing (2020, methodology): “Compared with the supervised counterparts, unsupervised cross-modal hashing methods [8, 45, 13, 36] only relied on the correlation information from the paired data, making it easier to be deployed to other scenarios.”
• Semantics-preserving hashing for cross-view retrieval (2015, methodology): “Following [3, 25], only the top 10 most frequent labels and the corresponding 186,577 annotated instances are kept.”
• An Overview of Cross-Media Retrieval: Concepts, Methodologies, Benchmarks, and Challenges (2017, methodology): “As for the experiments, some small-scale datasets such as Wikipedia (2,866 image/text pairs) and Pascal Sentence (1,000 image/text pairs) are used to evaluate the accuracy of hashing [70], [75], [76], [78], [83].”
• High-Dimensional Sparse Cross-Modal Hashing with Fine-Grained Similarity Embedding (2021, methodology): “Label Consistent Matrix Factorization Hashing (LCMFH) [46] directly utilizes the multi-modal data and leverages labels to guide the hash learning step by label consistent matrix factorization.”
• 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) [68], Semantics-Preservin”
• Deep Cross-Modal Hashing (2016, methodology): “While for CMFH and CCA whose codes are not available, we implement them carefully by ourselves.”
• 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 Comprehensive Survey on Cross-modal Retrieval (2016, methodology): “Ding et al. [64] propose a novel hashing method, which is referred to Collective Matrix Factorization Hashing (CMFH).”