Inter-media hashing for large-scale retrieval from heterogeneous data sources

By Jingkuan Song, Yang Yang, Yi Yang, Zi-Liang Huang, Heng Tao Shen. ACM SIGMOD Conference, 2013

616 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/570689c91d8f663458319a53e4a48759e10263e9

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. Ling Shao
3. Yi Yang
4. Luc Van Gool
5. Qi Tian
6. Jiashi Feng
7. Alan L. Yuille
8. Ming-Hsuan Yang

Citations in the corpus

• SCH-GAN: Semi-Supervised Cross-Modal Hashing by Generative Adversarial Network (2018, background): “Representative unsupervised cross-modal hashing methods including Cross-view hashing (CVH) [11], Inter-Media Hashing (IMH) [12], Predictable Dual-View Hashing (PDH) [13] and Collective Matrix Factorization Hashing (CMFH) [14].”
• Optimized Cartesian K-Means (2014, neutral): “C V ] 16 M ay 2 01 4 Index Terms—Clustering, Cartesian product, Nearest neighbor search ✦”
• Creating Something From Nothing: Unsupervised Knowledge Distillation for Cross-Modal Hashing (2020, background): “[32] proposed inter-media hashing to establish a common Hamming space by maintaining inter-media and intra-media consistency.”
• Shared Predictive Cross-Modal Deep Quantization (2018, positive): “Intermedia hashing [43] and cross-view hashing (CVH) [24] extend spectral hashing to multimodal setting.”
• Learning in high-dimensional multimedia data: the state of the art (2015, background): “Typical supervised hashing methods include Semantic Hashing [72], Minimal Loss Hashing (MLH) [64], Linear Discriminant Analysis Hashing (LDAHash) [84], Kernelized Super-vised Hashing (KSH) [52], Order Preserving Hashing (OPH) [91], etc. Supervised hashing is expected to achieve better result quality”
• Semantics-preserving hashing for cross-view retrieval (2015, methodology): “…can be roughly classified into two categories: single-view hashing [16, 21, 4, 11, 6, 13, 8, 22, 10] and multi-view hashing [1, 9, 20, 24, 23, 18, 27, 14, 3, 25, 17, 26, 19], with the former focusing on data with a single view while the latter focusing on that with multiple views, e.g . a news…”
• 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 Learning to Hash (2016, background): “This topic is attracting a lot of research efforts nowadays, such as collaborative hashing [89], [167], collaborative quantization [173], and cross-media hashing [134], [135], [178], [161], [83].”
• A Survey of Multi-View Representation Learning (2016, neutral): “[131] introduce an”
• Deep Bayesian Hashing with Center Prior for Multi-modal Neuroimage Retrieval (2020, methodology): “Based on the availability of supervisory signals, existing methods can be roughly categorized into two groups: (1) unsupervised hashing [24] that learns hash functions based on original data structures and distributions; and (2) supervised hashing [25] that learns hash functions by exploiting…”
• Deep Visual-Semantic Hashing for Cross-Modal Retrieval (2016, methodology): “Typical learning criteria include reconstruction error minimization [8, 37], similarity preservation as graph-based hashing [22, 33], and quantization error minimization as correlation quantization [39, 29].”
• Zero-Shot Sketch-Image Hashing (2018, background): “General cross-modal binary representation learning methods [4, 13, 71, 34, 57, 43, 37, 27, 6, 62, 18, 54, 65, 5, 42] target to map large-scale heterogeneous data with low computational cost.”
• Learning Cross-Modal Common Representations by Private–Shared Subspaces Separation (2020, result): “Actually, a group of other studies [29], [37]–[41] concentrate on the effi-ciency of cross-modal retrieval and target to learn binary common representations.”