Filters








1,098 Hits in 6.4 sec

Learning Affine Robust Binary Codes Based on Locality Preserving Hash [chapter]

Wei Zhang, Ke Gao, Dongming Zhang, Jintao Li
2013 Lecture Notes in Computer Science  
We propose locality preserving hash (LPH) to learn affine robust binary codes.  ...  Supervised hashing methods exploit labeled data to learn binary codes based on visual or semantic similarity, which are usually slow to train and consider global structure of data.  ...  Fig. 1 . 1 An illustration of affine robust binary codes learned by locality preserving hash (LPH) in local structure (d), compared with binary codes learned in global structure (c).  ... 
doi:10.1007/978-3-642-35725-1_24 fatcat:eqtv4htxzja6hpmrzajszsukfi

Fast Person Re-identification via Cross-Camera Semantic Binary Transformation

Jiaxin Chen, Yunhong Wang, Jie Qin, Li Liu, Ling Shao
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Finally, a joint learning framework is proposed for simultaneous subspace projection learning and binary coding based on discrete alternating optimization.  ...  Subsequently, a binary coding scheme is proposed via seamlessly incorporating both the semantic pairwise relationships and local affinity information.  ...  This indicates that the learned binary codes are forced to preserve both the semantic information and local affinity in the embedded subspace, by reducing the loss ℓ H (B, P) in (5) .  ... 
doi:10.1109/cvpr.2017.566 dblp:conf/cvpr/ChenWQLS17 fatcat:puw5onogmvgf5nt56fnakx7awa

Asymmetric Discrete Graph Hashing

Xiaoshuang Shi, Fuyong Xing, Kaidi Xu, Manish Sapkota, Lin Yang
2017 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
binary codes.  ...  building an asymmetric affinity matrix to learn compact binary codes.Specifically, we utilize two different instead of identical discrete matrices to better preserve the similarity of the graph with short  ...  To learn compact binary codes, an increasing number of methods focus on learning data-dependent hashing functions with available training data.  ... 
doi:10.1609/aaai.v31i1.10831 fatcat:6jfc4pgilvhgncsffbpjy5f7yi

Deep learning hashing for mobile visual search

Wu Liu, Huadong Ma, Heng Qi, Dong Zhao, Zhineng Chen
2017 EURASIP Journal on Image and Video Processing  
Firstly, we present a comprehensive survey of the existed deep learning based hashing methods, which showcases their remarkable power of automatic learning highly robust and compact binary code representation  ...  In this paper, we explore to holistically exploit the deep learning-based hashing methods for more robust and instant mobile visual search.  ...  Besides, to mitigate the information loss from binary codes, based on the hashed binary codes transmitted to the server, Kuo et al.  ... 
doi:10.1186/s13640-017-0167-4 fatcat:vcdhjjbe6jai7hyigxstihcega

SADIH: Semantic-Aware DIscrete Hashing

Zheng Zhang, Guo-sen Xie, Yang Li, Sheng Li, Zi Huang
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
and discriminative hashing function learning.  ...  category information of data are not well-explored to learn discriminative hash functions.  ...  Based on the asymmetric hashing learning (Shrivastava and Li 2014) , we replace one of the binary codes B in (1), and consider its robust model min B,W lS − V T B 21 s.t.  ... 
doi:10.1609/aaai.v33i01.33015853 fatcat:6ypjbpi2nbcqbpf3anfpfmhts4

Unsupervised Multi-modal Hashing for Cross-modal retrieval [article]

Jun Yu, Xiao-Jun Wu
2020 arXiv   pre-print
In this paper, we propose a novel unsupervised hashing learning method to cope with this open problem to directly preserve the manifold structure by hashing.  ...  Besides, the '2;1-norm constraint is imposed on the projection matrices to learn the discriminative hash function for each modality.  ...  Robust Cross-view Hashing (RCH) [21] learns a common Hamming space in which the binary codes of the paired different modalities are as consistent as possible.  ... 
arXiv:1904.00726v4 fatcat:6vupsinllvfh7ivzg2gozz7ffa

Distance Preserving Marginal Hashing for image retrieval

Li Wu, Kang Zhao, Hongtao Lu, Zhen Wei, Baoliang Lu
2015 2015 IEEE International Conference on Multimedia and Expo (ICME)  
One exception is the Local Linear Spectral Hashing (LLSH), which introduces negative values into the local affinity matrix to map nonneighbor images to non-similar codes.  ...  Furthermore, we adopt an efficient sequential procedure to learn the hashing functions.  ...  LLSH introduces negative values into the local affinity matrix and judges neighbors and non-neighbors based on a threshold which is the 10th percentile distance in A calculated with L 2 norm.  ... 
doi:10.1109/icme.2015.7177523 dblp:conf/icmcs/WuZLWL15 fatcat:5xx5l57lb5gz7hx2sljd7lgohq

Hashing with Mutual Information [article]

Fatih Cakir, Kun He, Sarah Adel Bargal, Stan Sclaroff
2018 arXiv   pre-print
We propose a novel supervised hashing method based on optimizing an information-theoretic quantity: mutual information.  ...  We study the problem of learning binary vector embeddings under a supervised setting, also known as hashing.  ...  The binary inference step yields hash codes that best preserve the similarity.  ... 
arXiv:1803.00974v2 fatcat:kjtggal2zfappijtd4gc7st7gu

Anchor Graph Structure Fusion Hashing for Cross-Modal Similarity Search [article]

Lu Wang, Jie Yang, Masoumeh Zareapoor, Zhonglong Zheng
2022 arXiv   pre-print
Besides, AGSFH preserves the anchor fusion affinity into the common binary Hamming space. Furthermore, a discrete optimization framework is designed to learn the unified binary codes.  ...  Based on the anchor graph structure fusion matrix, AGSFH attempts to directly learn an intrinsic anchor graph, where the structure of the intrinsic anchor graph is adaptively tuned so that the number of  ...  Hypergraph-based Discrete Hashing (BGDH) [18] obtains the binary codes with learning hypergraph and binary codes simultaneously.  ... 
arXiv:2202.04327v1 fatcat:oxdytmhxyzavnetqbobl4dueka

K-Means Hashing: An Affinity-Preserving Quantization Method for Learning Binary Compact Codes

Kaiming He, Fang Wen, Jian Sun
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
We propose a novel Affinity-Preserving K-means algorithm which simultaneously performs k-means clustering and learns the binary indices of the quantized cells.  ...  binary codes.  ...  In this paper, we focus on learning binary compact codes with Hamming distance computation.  ... 
doi:10.1109/cvpr.2013.378 dblp:conf/cvpr/HeWS13 fatcat:apavshm5mfbtpceug2ffxpif7m

SADIH: Semantic-Aware DIscrete Hashing [article]

Zheng Zhang, Guo-sen Xie, Yang Li, Sheng Li, Zi Huang
2019 arXiv   pre-print
and discriminative hashing function learning.  ...  category information of data are not well-explored to learn discriminative hash functions.  ...  Based on the asymmetric hashing learning (Shrivastava and Li 2014), we replace one of the binary codes B in (1), and consider its robust model min B,W lS − V T B 21 s.t.  ... 
arXiv:1904.01739v2 fatcat:lh2la3lngzf3dlki7jfwdd2hr4

Robust Hashing for Multi-View Data: Jointly Learning Low-Rank Kernelized Similarity Consensus and Hash Functions [article]

Lin Wu, Yang Wang
2016 arXiv   pre-print
Learning hash functions/codes for similarity search over multi-view data is attracting increasing attention, where similar hash codes are assigned to the data objects characterizing consistently neighborhood  ...  To learn robust hash functions, a latent low-rank kernel function is used to construct hash functions in order to accommodate linearly inseparable data.  ...  By contrast, we propose to jointly learn hash codes by preserving local similarities in multiple views while being robust to errors.  ... 
arXiv:1611.05521v1 fatcat:vtnotaqms5dd5b4vklca4sevzu

Unsupervised Deep Cross-modality Spectral Hashing [article]

Tuan Hoang and Thanh-Toan Do and Tam V. Nguyen and Ngai-Man Cheung
2020 arXiv   pre-print
This paper presents a novel framework, namely Deep Cross-modality Spectral Hashing (DCSH), to tackle the unsupervised learning problem of binary hash codes for efficient cross-modal retrieval.  ...  The framework is a two-step hashing approach which decouples the optimization into (1) binary optimization and (2) hashing function learning.  ...  binary codes that well preserve the local structures of datasets.  ... 
arXiv:2008.00223v3 fatcat:i2xbdck5gncinhai362j2xnmpu

Local Feature Hashing with Binary Autoencoder for Face Recognition

Jing Chen, Yunxiao Zu
2020 IEEE Access  
In this work, we develop an effective learning-based hashing model, namely local feature hashing with binary auto-encoder (LFH-BAE), to directly learn local binary descriptors in the Hamming space.  ...  Next, we propose an effective alternating algorithm based on the augmented Lagrange method (ALM) to solve these sub-problems, which helps to generate strong discriminative and excellent robust binary codes  ...  feature learning, 2) feature representation based on autoencoders, and 3) binary hashing.  ... 
doi:10.1109/access.2020.2973472 fatcat:ip2ui5lmbbavnn7hetwwsdp4mi

Cross-Modal Retrieval for CPSS Data

Fangming Zhong, Guangze Wang, Zhikui Chen, Feng Xia, Geyong Min
2020 IEEE Access  
The hashing based methods have been widely studied in building bilateral semantic associations of binary codes for cross-model retrieval.  ...  In this paper, we propose a nonlinear discrete cross-modal hashing (NDCMH) method based on concise binary classification for CPSS data which fully investigates the nonlinear relationship embedding, discrete  ...  Yan and Wang [2] presented a supervised robust discrete multimodal hashing (SRDMH), where the label information is preserved in the final binary codes, and a flexible 2,p loss with nonlinear embedding  ... 
doi:10.1109/access.2020.2967594 fatcat:nr4ghjvhi5c3vpg2ml4eq7x3ga
« Previous Showing results 1 — 15 out of 1,098 results