Semantics-preserving hashing for cross-view retrieval

By Zijia Lin, Guiguang Ding, Mingqing Hu, Jianmin Wang. Computer Vision and Pattern Recognition, 2015

497 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/69cfc91c93b6289a6fe0950b0adefcb7d01c5ce1

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

Citations in the corpus

High-Dimensional Sparse Cross-Modal Hashing with Fine-Grained Similarity Embedding (2021, background): “It treats a pair as similar if they share at least one common label [19, 28, 31, 37].”
Shared Predictive Cross-Modal Deep Quantization (2018, unknown): “Since, SePH is a kernel-based method, we use RBF kernel and take 500 randomly selected points as kernel bases by following its authors’ suggestion.”
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.”
Deep Bayesian Hashing with Center Prior for Multi-modal Neuroimage Retrieval (2020, methodology): “…ﬁve state-of-the-art cross-modal hashing methods based on traditional machine learning techniques, including ACQ [34], STMH [33], CVH [25], SEPH [27], and SCM [36] and then compared with three recently proposed deep learning methods for cross-modal hashing, including PGDH [38], DCMH [37], and…”
Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval (2018, methodology): “Supervised hashing methods [2, 4, 14, 16, 39, 40, 44] aim to exploit available supervised information (such as labels or the semantic affinities of training data) to improve performance.”
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”
A Comprehensive Survey on Cross-modal Retrieval (2016, methodology): “SePH [81], CAH [82], DCMH [83] in which cross-modal similarity search is fast.”
RGB-Infrared Cross-Modality Person Re-identification (2017, background): “one includes subspace learning methods [25, 30, 60] and deep learning frameworks [45, 6, 14, 12], while the latter one includes linear models [39, 36, 59, 51] and non-linear models [27, 50, 31].”
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].”
Joint-modal Distribution-based Similarity Hashing for Large-scale Unsupervised Deep Cross-modal Retrieval (2020, methodology): “For the supervised meth-ods [2, 3, 9, 15, 18, 19, 40, 42, 45], manually-annotated labels, requiring expensive human cost and computation, are leveraged to construct the similarity matrices and supervise hash code generation.”
Self-Supervised Learning from Web Data for Multimodal Retrieval (2019, methodology): “Following the experimental protocol in [35, 36, 37, 38] tags that appear less than 20 times are first removed and then instances without tags or annotations are removed.”
Pairwise Relationship Guided Deep Hashing for Cross-Modal Retrieval (2017, methodology): “Since SePH is a kernel-based method, we use RBF kernel and randomly select 500 points as kernel bases following by the authors’ suggestions.”
SCH-GAN: Semi-Supervised Cross-Modal Hashing by Generative Adversarial Network (2018, methodology): “• SePH [19] is a two-step supervised hashing methods, it ﬁrstly transforms the given semantic matrix of training data into a probability distribution and approximates it with learned hash codes in Hamming space via minimizing the KL-divergence.”
Deep Cross-Modal Hashing (2016, methodology): “Six state-of-the-art cross-modal hashing methods are adopted as baselines for comparison, including SePH [22], STMH [33], SCM [35], CMFH [7], CCA [11] and DVSH [3].”
Deep Sketch Hashing: Fast Free-Hand Sketch-Based Image Retrieval (2017, methodology): “Finally, similar to [31, 10], we late-fuse the C1-Net (Bottom) and C2-Net (Middle) into a unified binary coding layer hash C1 so that the learned codes can fully benefit from both natural images and their corresponding sketch-tokens.”
Learning in high-dimensional multimedia data: the state of the art (2015, methodology): “A comparison with the state-of-the art single modality and multiple modalities hash learning methods is shown in [51].”
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”