Latent semantic sparse hashing for cross-modal similarity search

By Jile Zhou, Guiguang Ding, Yuchen Guo. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2014

478 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/92727ae53fda2c99c3cdac08c443f40c866dff2a

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. Cheng Deng
4. Shiv Ram Dubey
5. Liang Wang
6. Li Liu
7. Wei David Liu
8. Yi Yang

Citations in the corpus

• Joint-modal Distribution-based Similarity Hashing for Large-scale Unsupervised Deep Cross-modal Retrieval (2020, methodology): “Four unsupervised shadow cross-modal hashing methods CVH [17], IMH [29], CMFH [7] and LSSH [47], and three unsupervised deep cross-modalhashingmethodsDBRC [6],UDCMH[39]andDJSRH[30] are selected as the baseline methods to compare with JDSH.”
• A Survey of Multi-View Representation Learning (2016, unknown): “[238] present a latent semantic sparse hashing model by unifying sparse coding and matrix factorization.”
• Pairwise Relationship Guided Deep Hashing for Cross-Modal Retrieval (2017, methodology): “Specifically CCA (Hotelling 1936), CMFH (Ding, Guo, and Zhou 2014), SCM (Zhang and Li 2014), LSSH (Zhou, Ding, and Guo 2014), STMH (Wang et al. 2015), CVH (Kumar and Udupa 2011), SePH (Lin et al. 2015), and DCMH (Jiang and Li 2016) are adopted as baselines.”
• SCH-GAN: Semi-Supervised Cross-Modal Hashing by Generative Adversarial Network (2018, methodology): “Latent Semantic Sparse Hashing (LSSH) [33] is proposed to use sparse coding and matrix factorization to learn separate semantic features for images and text, and then map them into a joint abstract space to reduce semantic difference.”
• Unsupervised Semantic-Preserving Adversarial Hashing for Image Search (2019, background): “Since exact nearest neighbor search is typically time-consuming and unsuitable for large-scale datasets, approximate nearest neighbor (ANN) search [8], [9], which attempts to find the nearest neighbor with a high probability, has been actively studied and successfully applied to many machine learnin”
• Robust Unsupervised Cross-modal Hashing for Multimedia Retrieval (2020, methodology): “Although most existing UCMH methods show promising performances, they can only handle the fully paired data by requiring that all the objects be fully paired or have the one-to-one correspondence among different modalities (as shown in Figure 1(a)) [8, 10, 14, 15, 34, 42, 44, 45, 47].”
• Two-Stream Deep Hashing With Class-Specific Centers for Supervised Image Search (2020, background): “However, approximate nearest neighbor search (ANN-search), which attempts to find the nearest neighbor with a high probability under a sublinear or even constant time complexity, has been actively studied and successfully applied to many machine learning and data mining problems [19], [26]–[28].”
• Learning Discriminative Binary Codes for Large-scale Cross-modal Retrieval (2017, methodology): “art cross-modal hashing methods, including unsupervised ones LSSH [14], CMFH [15], CCA-ACQ [23], and supervised ones CRH [27], SCM [28], SEPH [29].”
• Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval (2018, background): “Unsupervised hashing methods [8, 34, 38, 46] learn hashing functions by discovering the inter-modality and intra-modality information belonging to the unlabeled training data.”
• Triplet-Based Deep Hashing Network for Cross-Modal Retrieval (2018, methodology): “Up to now, many hashing-based cross-modal retrieval methods with shallow architectures have been proposed, such as inter-media hashing (IMH) [18], multimodal latent binary embedding (MLBE) [19], collective matrix factorization hashing (CMFH) [20], latent semantic sparse hashing(LSSH) [21], cross-mod”
• An Overview of Cross-Media Retrieval: Concepts, Methodologies, Benchmarks, and Challenges (2017, methodology): “However, existing works such as [78]–[83] only involve the retrieval between data of two media types (mainly image and text).”
• 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.”
• Shared Predictive Cross-Modal Deep Quantization (2018, unknown): “Actually, cross-modal retrieval has been widely studied in recent years [15]–[22].”
• High-Dimensional Sparse Cross-Modal Hashing with Fine-Grained Similarity Embedding (2021, background): “2 Sparse Hashing It is worth noting that, sparse hashing in this paper means highdimensional sparse binary coding, rather than applying sparse constraints of dictionary learning in dense hashing [23, 48, 55].”
• Deep Sketch Hashing: Fast Free-Hand Sketch-Based Image Retrieval (2017, methodology): “In fact, among various hashing methods, cross-modality hashing [31, 68, 72, 26, 32, 2, 57, 75, 71, 10, 23, 5, 4], which learns binary codes by preserving the correlations between heterogeneous representations from different modalities, are more related to SBIR problems.”
• A Comprehensive Survey on Cross-modal Retrieval (2016, methodology): “Linear modeling CVH [60], IMH [61], PDH [62], LCMH [63], CMFH [64], LSSH [65] Nonlinear modeling MSAE [66], DMHOR [67] Pairwise based methods Linear modeling CMSSH [68], CRH [69], IMVH [70], QCH[71] RaHH [72], HTH [73] Nonlinear modeling MLBE [74], PLMH [75], MM-NN [76], CHN [77] Supervised methods…”