Filters








19,263 Hits in 5.9 sec

Top Rank Supervised Binary Coding for Visual Search

Dongjin Song, Wei Liu, Rongrong Ji, David A. Meyer, John R. Smith
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
It has been demonstrated that supervised binary coding techniques that leverage supervised information can significantly enhance the coding quality, and hence greatly benefit visual search tasks.  ...  In this paper, we propose a novel supervised binary coding approach, namely Top Rank Supervised Binary Coding (Top-RSBC), which explicitly focuses on optimizing the precision of top positions in a Hamming-distance  ...  Conclusion In this paper, we proposed a novel supervised binary coding technique, dubbed Top Rank Supervised Binary Coding (Top-RSBC), to conduct large-scale visual search.  ... 
doi:10.1109/iccv.2015.223 dblp:conf/iccv/SongLJMS15 fatcat:hfmwlqwftbdipbo7ahtj2dahz4

Deep hashing for compact binary codes learning

Venice Erin Liong, Jiwen Lu, Gang Wang, Pierre Moulin, Jie Zhou
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we propose a new deep hashing (DH) approach to learn compact binary codes for large scale visual search.  ...  To further improve the discriminative power of the learned binary codes, we extend DH into supervised DH (SDH) by including one discriminative term into the objective function of DH which simultaneously  ...  They applied the stacked Restricted Boltzmann Machine (RBM) learn compact binary codes for visual search.  ... 
doi:10.1109/cvpr.2015.7298862 dblp:conf/cvpr/LiongLWMZ15 fatcat:p5kqjzxibbfopk7mzt7w4uuike

Deep learning of binary hash codes for fast image retrieval

Kevin Lin, Huei-Fang Yang, Jen-Hao Hsiao, Chu-Song Chen
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Unlike other supervised methods that require pair-wised inputs for binary code learning, our method learns hash codes and image representations in a point-wised manner, making it suitable for large-scale  ...  Approximate nearest neighbor search is an efficient strategy for large-scale image retrieval.  ...  Our method for learning binary codes is described in detail as follows.  ... 
doi:10.1109/cvprw.2015.7301269 dblp:conf/cvpr/LinYHC15 fatcat:ldzjg37xlvg3tchpjfvvdpdhvm

Lost in binarization

Yu-Gang Jiang, Jun Wang, Shih-Fu Chang
2011 Proceedings of the 1st ACM International Conference on Multimedia Retrieval - ICMR '11  
State-of-the-art techniques often embed high-dimensional visual features into low-dimensional Hamming space, where search can be performed in real-time based on Hamming distance of compact binary codes  ...  We achieve this goal by firstly offline learning bit weights of the binary codes for a diverse set of predefined semantic concept classes.  ...  Zhenguo Li for his help on this work.  ... 
doi:10.1145/1991996.1992012 dblp:conf/mir/JiangWC11 fatcat:bq57s2pvgjgklac5vhea7q7qgi

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  
for visual search.  ...  In this paper, we explore to holistically exploit the deep learning-based hashing methods for more robust and instant mobile visual search.  ...  However, the exited hash based methods for mobile visual search all try to compress the exited classical handcrafted features into binary code.  ... 
doi:10.1186/s13640-017-0167-4 fatcat:vcdhjjbe6jai7hyigxstihcega

Rank Preserving Hashing for Rapid Image Search

Dongjin Song, Wei Liu, David A. Meyer, Dacheng Tao, Rongrong Ji
2015 2015 Data Compression Conference  
It has been shown that hashing techniques which leverage supervised information can significantly enhance performance, and thus greatly benefit visual search tasks.  ...  Typically, a modern hashing method uses a set of hash functions to compress data samples into compact binary codes.  ...  This indicates that modeling the supervised rank information appropriately can significantly improve the top-k image search accuracy.  ... 
doi:10.1109/dcc.2015.85 dblp:conf/dcc/SongLMTJ15 fatcat:wu5roracw5bpdgtc72rvduennm

Visual Search at eBay

Fan Yang, Ajinkya Kale, Yury Bubnov, Leon Stein, Qiaosong Wang, Hadi Kiapour, Robinson Piramuthu
2017 Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '17  
Supervised approach for optimized search limited to top predicted categories and also for compact binary signature are key to scale up without compromising accuracy and precision.  ...  In this paper, we propose a novel end-to-end approach for scalable visual search infrastructure.  ...  by a supervised binary hashing technique proposed by Lin et al  ... 
doi:10.1145/3097983.3098162 dblp:conf/kdd/YangKBSWKP17 fatcat:s6v4wd3r7fgp5eiywcohonhjsa

Rapid Clothing Retrieval via Deep Learning of Binary Codes and Hierarchical Search

Kevin Lin, Huei-Fang Yang, Kuan-Hsien Liu, Jen-Hao Hsiao, Chu-Song Chen
2015 Proceedings of the 5th ACM on International Conference on Multimedia Retrieval - ICMR '15  
We develop a hierarchical deep search framework to tackle this problem. We use a pretrained network model that has learned rich mid-level visual representations in module 1.  ...  Experiments demonstrate the potential of our proposed framework for clothing retrieval in a large corpus.  ...  The latent layer weights can be viewed as evolved from the LSH approach (that uses random projection for binary coding) to a more favorable projection via supervision.  ... 
doi:10.1145/2671188.2749318 dblp:conf/mir/LinYLHC15 fatcat:6tgk7yfj4rbghe5lca6uvzkhzq

Deep Progressive Hashing for Image Retrieval

Jiale Bai, Bingbing Ni, Minsi Wang, Yang Shen, Hanjiang Lai, Chongyang Zhang, Lin Mei, Chuanping Hu, Chen Yao
2017 Proceedings of the 2017 ACM on Multimedia Conference - MM '17  
., LSTM structure, the binary codes generated from later output nodes naturally inherit information aggregated from previously codes while explore novel information from the extended salient region, and  ...  Inspired by human's nonsalient-to-salient perception path, the proposed hashing scheme generates a series of binary codes based on progressively expanded salient regions.  ...  Representing the image with binary codes (known as Hashing [5, 6, 16, 24, 26] ), is an efficient method for image search, which maps images with similar semantic information to binary codes with small  ... 
doi:10.1145/3123266.3123280 dblp:conf/mm/BaiNWSLZMHY17 fatcat:zmcavxe6bzcu5dtr4kkyqetnxu

A Comprehensive Survey on Image Search Using Binary Hash Codes
IJARCCE - Computer and Communication Engineering

SHROFF RAHUL D, DHAGE JAYKUMAR S
2014 IJARCCE  
Effective content based Image Search based on hash codes is a very acceptable for efficient similarity search, due to its query time and storage efficiency.  ...  And also discussed concept of weighted Hamming distance, which improve ranking performance of binary hash code so that result images can be ranked at fined grained level.  ...  Though hashing proved to be effective for visual similar search in several existing works, they lack in providing a good ranking which is vital for image search.  ... 
doi:10.17148/ijarcce.2014.31123 fatcat:4jmh6apfnbb7ng3sg3wx5cenqe

Deep supervised hashing for gait retrieval

Shohel Sayeed, Pa Pa Min, Thian Song Ong
2021 F1000Research  
Therefore, our DGRH model combines gait feature learning with binary hash codes.  ...  Due to recent growth in the use of gait biometrics across surveillance systems, the ability to rapidly search for the required data has become an emerging need.  ...  The common methods for searching hash-based codes are the Hash lookup table and the Hamming ranking.  ... 
doi:10.12688/f1000research.51368.1 pmid:35814625 pmcid:PMC9237558 fatcat:idteaoukxndb3i36fvgteyyewi

SUBIC: A supervised, structured binary code for image search [article]

Himalaya Jain, Joaquin Zepeda, Patrick Pérez, Rémi Gribonval
2017 arXiv   pre-print
We hence propose herein a novel method to make deep convolutional neural networks produce supervised, compact, structured binary codes for visual search.  ...  For large-scale visual search, highly compressed yet meaningful representations of images are essential.  ...  Top ten ranked images retrieved from Cifar-10 for the query on the left when using 12-bit (top) and 48-bit (bottom) SUBIC.  ... 
arXiv:1708.02932v1 fatcat:hzaxdpj3r5cdlpx5aoc3j26b34

Deep Visual-Semantic Quantization for Efficient Image Retrieval

Yue Cao, Mingsheng Long, Jianmin Wang, Shichen Liu
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Compact coding has been widely applied to approximate nearest neighbor search for large-scale image retrieval, due to its computation efficiency and retrieval quality.  ...  Comprehensive empirical evidence shows that DVSQ can generate compact binary codes and yield state-of-the-art similarity retrieval performance on standard benchmarks.  ...  Big Data System Software (NEL-BDSS), and Tsinghua National Lab for Information Science and Technology (TNList) Projects.  ... 
doi:10.1109/cvpr.2017.104 dblp:conf/cvpr/CaoL0L17 fatcat:jgzhlmcoeraqblejcdeoeovh6i

Learning to Hash with Partial Tags: Exploring Correlation between Tags and Hashing Bits for Large Scale Image Retrieval [chapter]

Qifan Wang, Luo Si, Dan Zhang
2014 Lecture Notes in Computer Science  
Similarity search is an important technique in many large scale vision applications. Hashing approach becomes popular for similarity search due to its computational and memory efficiency.  ...  However, tag information is not fully exploited in existing unsupervised and supervised hashing methods especially when only partial tags are available.  ...  This work is also partially supported by the Center for Science of Information (CSoI), an NSF Science and Technology Center, under grant agreement CCF-0939370.  ... 
doi:10.1007/978-3-319-10578-9_25 fatcat:bxdqht5y3raohlgixeta5gzwqq

Query-Adaptive Image Search With Hash Codes

Yu-Gang Jiang, Jun Wang, Xiangyang Xue, Shih-Fu Chang
2013 IEEE transactions on multimedia  
Scalable image search based on visual similarity has been an active topic of research in recent years.  ...  This is achieved by firstly offline learning bitwise weights of the hash codes for a diverse set of predefined semantic concept classes.  ...  Performance gains (over the baseline traditional ranking) are marked on top of the query-adaptive search results.  ... 
doi:10.1109/tmm.2012.2231061 fatcat:fgzcslz66zh7lck2si7fvdwsoe
« Previous Showing results 1 — 15 out of 19,263 results