Linear cross-modal hashing for efficient multimedia search

By Xiaofeng Zhu, Zi-Liang Huang, Heng Tao Shen, Xin Zhao. ACM Multimedia, 2013

297 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ddb3cb017d3f82b4ff700dc7cda63be90b9c1c7c

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. Qi Tian
5. Ling Shao
6. Jiashi Feng
7. Xiaogang Wang
8. Jingdong Wang

Citations in the corpus

• 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].”
• Discriminative coupled dictionary hashing for fast cross-media retrieval (2014, methodology): “Cross-media hashing is a new research area and there has been only limited research efforts focusing on it so far [3, 9, 28, 29, 15, 30, 25].”
• 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].”
• Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization (2018, methodology): “Many learning-based hashing algorithms have been developed according to different scenarios, including the supervised methods [22], [30], [37], [40], [47], unsupervised methods [10], [12], [29], [31], [49] and cross-modal hashing methods [17], [24], [53], [58], etc.”
• Hashing for Similarity Search: A Survey (2014, background): “This topic is attracting a lot of research efforts, such as collaborative hashing [85], and cross-media hashing [120], [121], [152].”
• Adversarial Cross-Modal Retrieval (2017, methodology): “The binary approaches, also referred to as cross-modal hashing are more geared towards retrieval efficiency and aim at mapping the items of different modalities into a common binary Hamming space [24, 27, 34, 42].”
• A Survey of Multi-View Representation Learning (2016, unknown): “[149] introduce linear cross-modal hashing (LCMH), which adopts a “two-stage” strategy to learn cross-view hashing functions.”
• Efficient kNN classification algorithm for big data (2016, methodology): “These methods were mainly applied for fast search [17,18], dimension reduction [19,20], and improving the efficiency of the algorithms.”
• Efficient kNN Classification With Different Numbers of Nearest Neighbors (2018, background): “Usually, (2) is called ridge regression [23], [31] with a close solution W = (XT X + ρI)−1XT X.”
• A Comprehensive Survey on Cross-modal Retrieval (2016, methodology): “Zhu et al. [63] propose a novel hashing method, named linear cross-modal hashing (LCMH), to enable scalable indexing for 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.”
• Semantics-preserving hashing for cross-view retrieval (2015, background): “Recently, various hashing methods for cross-view retrieval have been proposed, including unsupervised ones [27, 14, 3, 25] and supervised ones [1, 9, 24, 23, 18, 17, 26, 19].”
• Correlation Hashing Network for Efficient Cross-Modal Retrieval (2016, methodology): “Following prior works [36, 28], we prune the original NUSWIDE dataset to form a new dataset consisting of 195,834 image-text pairs that belong to one of the 21 most frequent concepts.”
• Learning in high-dimensional multimedia data: the state of the art (2015, background): “Very recently, hashing [108,113,106,82,114,105,79,21, 116,115] has attracted enormous attention from different research areas to achieve fast similarity search due to its high efficiency in terms of the storage and computational cost.”
• Robust Joint Graph Sparse Coding for Unsupervised Spectral Feature Selection (2017, unknown): “For example, an 1-norm regularizer [43], [44], [48] leads to the element sparsity and an 2,1-norm regularizer [49] results in the group sparsity, while a mixed-norm regularizer combining an 1-norm with an 2,1-norm [50] produces the mixed sparsity.”