Filters








13,304 Hits in 7.8 sec

Large Scale Image Indexing Using Online Non-negative Semantic Embedding [chapter]

Jorge A. Vanegas, Fabio A. González
<span title="">2013</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
The principal advantage of the proposed method is its formulation as an online learning algorithm, which can scale to deal with large image collections.  ...  This paper presents a novel method to address the problem of indexing a large set of images taking advantage of associated multimodal content such as text or tags.  ...  Online Non-negative Semantic Embedding Model When the image associated text has a rich and clean semantic interpretation (e.g. tags provided by experts), the text representation may be used directly as  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-41822-8_46">doi:10.1007/978-3-642-41822-8_46</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cnsejphfuzgmtmmpnejkjwo5ya">fatcat:cnsejphfuzgmtmmpnejkjwo5ya</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20181030090024/https://link.springer.com/content/pdf/10.1007%2F978-3-642-41822-8_46.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f6/91/f6916232af64971d17c10918c6bd745d7cd1211c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-41822-8_46"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Image Retrieval using Sparse Codewords with Cryptography for Enhanced Security

Munmun N. Bhagat, Prof. B. B. Gite
<span title="">2014</span> <i title="IOSR Journals"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vabuspdninc75epczdurccts4u" style="color: black;">IOSR Journal of Computer Engineering</a> </i> &nbsp;
In this work, semantic codewords for face retrieval are constructed by using semantic cues of the face image to improve content based face image retrieval.  ...  In this paper, automatically detected human attributes are used to enhance the performance of content based face image retrieval.  ...  Introduction In this paper, the challenge of large scale face image retrieval is getting addressed.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.9790/0661-16252226">doi:10.9790/0661-16252226</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3dbxk4jpqff33bl5hl4nfkc3du">fatcat:3dbxk4jpqff33bl5hl4nfkc3du</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180602030209/http://www.iosrjournals.org/iosr-jce/papers/Vol16-issue2/Version-5/E016252226.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c7/fc/c7fc3db9fff12fa1a35c5a048fee3a6269980bfc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.9790/0661-16252226"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Scalable Face Image Retrieval Using Attribute-Enhanced Sparse Codewords

Bor-Chun Chen, Yan-Ying Chen, Yin-Hsi Kuo, Winston H. Hsu
<span title="">2013</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/sbzicoknnzc3tjljn7ifvwpooi" style="color: black;">IEEE transactions on multimedia</a> </i> &nbsp;
large-scale face retrieval.  ...  Index Terms-Content-based image retrieval, face image, human attributes.  ...  The similar idea is proposed in [6] using fisher vectors with attributes for large-scale image retrieval, but they use early fusion to combine the attribute scores.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tmm.2013.2242460">doi:10.1109/tmm.2013.2242460</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/b7qhfd2hbjeulalkpvc3ntxlcu">fatcat:b7qhfd2hbjeulalkpvc3ntxlcu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829090653/http://www.leonsoftsolutions.com/ieeepapers/imageprocessing/imgpro16.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b3/1f/b31f90fa158c218681cfef0d2420e36284bca3c5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tmm.2013.2242460"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Visual Search at Alibaba

Yanhao Zhang, Pan Pan, Yun Zheng, Kang Zhao, Yingya Zhang, Xiaofeng Ren, Rong Jin
<span title="">2018</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/fqqihtxlu5bvfaqxjyvqcob35a" style="color: black;">Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery &amp; Data Mining - KDD &#39;18</a> </i> &nbsp;
The binary index engine is designed to scale up indexing without compromising recall and precision.  ...  We take advantage of large image collection of Alibaba and state-of-the-art deep learning techniques to perform visual search at scale.  ...  The merit of non-clicked images nonclick is that they are usually hard negatives, meaning they are similar to query image with different product.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3219819.3219820">doi:10.1145/3219819.3219820</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/kdd/ZhangPZZZRJ18.html">dblp:conf/kdd/ZhangPZZZRJ18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/caa42i3xmzfxhiddso5sjq6czy">fatcat:caa42i3xmzfxhiddso5sjq6czy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190216063013/https://static.aminer.cn/upload/pdf/1560/1457/569/5b67b45517c44aac1c86086d.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e4/c6/e4c66da61a2343591940c71aa547e5566dfaa38b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3219819.3219820"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

A weakly supervised adaptive triplet loss for deep metric learning [article]

Xiaonan Zhao, Huan Qi, Rui Luo, Larry Davis
<span title="2019-09-27">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The method uses weakly labeled product description data to implicitly determine fine grained semantic classes, avoiding the need to annotate large amounts of training data.  ...  We address the problem of distance metric learning in visual similarity search, defined as learning an image embedding model which projects images into Euclidean space where semantically and visually similar  ...  Acknowledgement We thank Lailin Chen, Wei Xia, Imry Kissos, Patricia Gutierrez, Angels Borras, Etan Khanal for useful discussions, and Axel Vidales, Ben Barnes, Amy Essene, Chris Mills, Gabriel Blanco  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.12939v1">arXiv:1909.12939v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3pxzexbuzzfj5b3hgcc233zza4">fatcat:3pxzexbuzzfj5b3hgcc233zza4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825231256/https://arxiv.org/pdf/1909.12939v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cd/8f/cd8fda174538637b4ca2ab41cda2e936f50e4743.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.12939v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Fashion Outfit Complementary Item Retrieval [article]

Yen-Liang Lin, Son Tran, Larry S. Davis
<span title="2020-03-04">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our subspace conditional factors are item categories, not target item images such as in [15] , which enables us to carry out individual item feature extraction for large scale indexing and retrieval.  ...  Our system is designed for large scale retrieval. We present our framework for indexing and outfit item retrieval in Section 3.3.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.08967v2">arXiv:1912.08967v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dh2dcsm3yfbn5hgz42m3k4nq2q">fatcat:dh2dcsm3yfbn5hgz42m3k4nq2q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200320120156/https://arxiv.org/pdf/1912.08967v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6d/2f/6d2f383879e686ed17c98b367e931c4aba111028.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.08967v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Embedding-based Product Retrieval in Taobao Search [article]

Sen Li, Fuyu Lv, Taiwei Jin, Guli Lin, Keping Yang, Xiaoyi Zeng, Xiao-Ming Wu, Qianli Ma
<span title="2021-06-17">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Retrieving the most relevant products from a large-scale corpus while preserving personalized user characteristics remains an open question.  ...  Therefore, we propose a novel and practical embedding-based product retrieval model, named Multi-Grained Deep Semantic Product Retrieval (MGDSPR).  ...  large-scale online retrieval system.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.09297v1">arXiv:2106.09297v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hszryrbkoffddlv6emrpbm6rsy">fatcat:hszryrbkoffddlv6emrpbm6rsy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210620001723/https://arxiv.org/pdf/2106.09297v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/db/54/db5485492a014a49c652e83571063b79f0b9c702.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.09297v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

VLDeformer: Vision-Language Decomposed Transformer for Fast Cross-Modal Retrieval [article]

Lisai Zhang and Hongfa Wu and Qingcai Chen and Yimeng Deng and Zhonghua Li and Dejiang Kong and Zhao Cao and Joanna Siebert and Yunpeng Han
<span title="2021-11-25">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
VLDeformer also outperforms state-of-the-art visual-semantic embedding methods on COCO and Flickr30k.  ...  The latter stage plays the role of single modal indexing, which is to some extent like the term indexing of a text SE.  ...  We use an objective as Eq. 1 to pull semantically close images representation r j v to the text representation r i t and push non-close samples apart: L t c = − log e cos(r i t ,r i v )/τ Σ N j=1 (e cos  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.11338v3">arXiv:2110.11338v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nz55dm26ifh43jqchsnt3xd3km">fatcat:nz55dm26ifh43jqchsnt3xd3km</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211110161627/https://arxiv.org/pdf/2110.11338v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/64/2c/642c24d83764dccb0426c5ffd03b12e20a2817c3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.11338v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Understanding Pixel-level 2D Image Semantics with 3D Keypoint Knowledge Engine

Yang You, Chengkun Li, Yujing Lou, Zhoujun Cheng, Liangwei Li, Lizhuang Ma, Weiming Wang, Cewu Lu
<span title="2021-04-13">2021</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3px634ph3vhrtmtuip6xznraqi" style="color: black;">IEEE Transactions on Pattern Analysis and Machine Intelligence</a> </i> &nbsp;
In order to obtain reliable 3D semantic labels that are absent in current image datasets, we build a large scale keypoint knowledge engine called KeypointNet, which contains 103,450 keypoints and 8,234  ...  In this paper, we propose a new method on predicting image corresponding semantics in 3D domain and then projecting them back onto 2D images to achieve pixel-level understanding.  ...  In practice, this loss is optimized in an online batch estimation, with hardest negative pair selection.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2021.3072659">doi:10.1109/tpami.2021.3072659</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33848241">pmid:33848241</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fw67ych3cfeihnhtsxuqxfxrra">fatcat:fw67ych3cfeihnhtsxuqxfxrra</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211128072403/https://arxiv.org/pdf/2111.10817v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/81/05/8105eeb434d36f7e3ef05a5b923c3c913145d0f2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2021.3072659"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Online Matrix Factorization for Space Embedding Multilabel Annotation [chapter]

Sebastian Otálora-Montenegro, Santiago A. Pérez-Rubiano, Fabio A. González
<span title="">2013</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
The paper presents an online matrix factorization algorithm for multilabel learning.  ...  An important characteristic of the novel method is its scalability, which is a consequence of its formulation as an online learning algorithm.  ...  Semántica Latente", "Diseño e implementación de un sistema de cómputo sobre recursos heterogéneos para la identificación de estructuras atmosféricas en predicción climatológica" and LACCIR "Multimodal Image  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-41822-8_43">doi:10.1007/978-3-642-41822-8_43</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mfeovm7pnneetmmit5hj2rxlkq">fatcat:mfeovm7pnneetmmit5hj2rxlkq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190503070646/https://link.springer.com/content/pdf/10.1007%2F978-3-642-41822-8_43.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8d/ea/8dea060f85e41658822ddba5a862ee35d7cd9633.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-41822-8_43"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Towards Zero-shot Cross-lingual Image Retrieval and Tagging [article]

Pranav Aggarwal, Ritiz Tambi, Ajinkya Kale
<span title="2021-09-15">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We also demonstrate how a cross-lingual model can be used for downstream tasks like multi-lingual image tagging in a zero shot manner.  ...  We present a simple yet practical approach for building a cross-lingual image retrieval model which trains on a monolingual training dataset but can be used in a zero-shot cross-lingual fashion during  ...  Model Architecture Most industry use cases involving images will have a pre-trained image embeddings model. It is expensive to build and index new embeddings per use case.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.07622v1">arXiv:2109.07622v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hvegymlhybgjhjqgj3ysnljmlu">fatcat:hvegymlhybgjhjqgj3ysnljmlu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210918162936/https://arxiv.org/pdf/2109.07622v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8d/ec/8dec71f33dbdb5a4c9819c7893b12670069d743f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.07622v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Multi-modal joint embedding for fashion product retrieval

A. Rubio, LongLong Yu, E. Simo-Serra, F. Moreno-Noguer
<span title="">2017</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/anlh4tvwprcrtoxv5d4h6a7rye" style="color: black;">2017 IEEE International Conference on Image Processing (ICIP)</a> </i> &nbsp;
We train this embedding using large-scale real world e-commerce data by both minimizing the similarity between related products and using auxiliary classification networks to that encourage the embedding  ...  to have semantic meaning.  ...  The class labels are used for the classification losses and for randomly sampling negatives for training the embedding.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icip.2017.8296311">doi:10.1109/icip.2017.8296311</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icip/RubioYSM17.html">dblp:conf/icip/RubioYSM17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wi4onryz6rcfxnc2e5jcrslzym">fatcat:wi4onryz6rcfxnc2e5jcrslzym</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180722180226/https://upcommons.upc.edu/bitstream/handle/2117/116309/1904-Multi-Modal-Joint-Embedding-for-Fashion-Product-Retrieval.pdf;jsessionid=30FF77CC43E1532D55F35B6F46774E28?sequence=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/bb/2f/bb2f61a057bbf176e402d171d79df2635ccda9f6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icip.2017.8296311"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Graph-RISE: Graph-Regularized Image Semantic Embedding [article]

Da-Cheng Juan, Chun-Ta Lu, Zhen Li, Futang Peng, Aleksei Timofeev, Yi-Ting Chen, Yaxi Gao, Tom Duerig, Andrew Tomkins, Sujith Ravi
<span title="2019-02-14">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we present Graph-Regularized Image Semantic Embedding (Graph-RISE), a large-scale neural graph learning framework that allows us to train embeddings to discriminate an unprecedented O(40M  ...  Graph-RISE outperforms state-of-the-art image embedding algorithms on several evaluation tasks, including image classification and triplet ranking.  ...  We also thank Expander, Image Understanding and several related teams for the technical support.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.10814v1">arXiv:1902.10814v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m5a6vg7yz5g5bcayu3st7lua2m">fatcat:m5a6vg7yz5g5bcayu3st7lua2m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191027100029/https://arxiv.org/pdf/1902.10814v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f8/83/f883427cda5d3b02f0087e48985e4d820d0d8038.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.10814v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval [article]

Siqi Sun, Yen-Chun Chen, Linjie Li, Shuohang Wang, Yuwei Fang, Jingjing Liu
<span title="2021-04-11">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
These large-scale pre-trained models, although successful, fatefully suffer from slow inference speed due to enormous computation cost mainly from cross-modal attention in Transformer architecture.  ...  When applied to real-life applications, such latency and computation demand severely deter the practical use of pre-trained models.  ...  Without crossattention, our method outperforms non-pre-training approaches by large margins on all metrics.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.08784v2">arXiv:2103.08784v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/omiurfpl6rchdly32nkgdlgezq">fatcat:omiurfpl6rchdly32nkgdlgezq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210321075409/https://arxiv.org/pdf/2103.08784v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a1/af/a1af9132e0e0b2ca4c7b5bd15352aba274aec086.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.08784v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

SSDH: Semi-supervised Deep Hashing for Large Scale Image Retrieval

Jian Zhang, Yuxin Peng
<span title="">2017</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jqw2pm7kwvhchpdxpcm5ryoic4" style="color: black;">IEEE transactions on circuits and systems for video technology (Print)</a> </i> &nbsp;
Hashing methods have been widely used for efficient similarity retrieval on large scale image database.  ...  exploit both labeled and unlabeled data, in which we propose an online graph construction method to benefit from the evolving deep features during training to better capture semantic neighbors.  ...  Index Terms-Semi-supervised deep hashing, online graph construction, underlying data structures, large scale image retrieval. I.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tcsvt.2017.2771332">doi:10.1109/tcsvt.2017.2771332</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jbijzttotfap7ik5ngxv3xusyq">fatcat:jbijzttotfap7ik5ngxv3xusyq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200830101510/https://arxiv.org/pdf/1607.08477v2.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/52/24/52243973b859cd61ef439a23d84e7d0cfd72f8d1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tcsvt.2017.2771332"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 13,304 results