Filters








252 Hits in 6.2 sec

Cross-modal Subspace Learning for Fine-grained Sketch-based Image Retrieval [article]

Peng Xu, Qiyue Yin, Yongye Huang, Yi-Zhe Song, Zhanyu Ma, Liang Wang, Tao Xiang, W. Bastiaan Kleijn, Jun Guo
<span title="2017-05-28">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we introduce and compare a series of state-of-the-art cross-modal subspace learning methods and benchmark them on two recently released fine-grained SBIR datasets.  ...  Sketch-based image retrieval (SBIR) is challenging due to the inherent domain-gap between sketch and photo.  ...  Experimental Results and Discussions Datasets In this section, we will apply the aforementioned cross-modal subspace learning methods on two recently released fine-grained sketch-based image retrieval  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.09888v1">arXiv:1705.09888v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/amgvdpunhfcdth7cuovobgdqn4">fatcat:amgvdpunhfcdth7cuovobgdqn4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191021034612/https://arxiv.org/pdf/1705.09888v1.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/9e/0e/9e0e927091acbbebd4036f1a7290b65c94bc241a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.09888v1" 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>

Synergistic Instance-Level Subspace Alignment for Fine-Grained Sketch-Based Image Retrieval

Ke Li, Kaiyue Pang, Yi-Zhe Song, Timothy M. Hospedales, Tao Xiang, Honggang Zhang
<span title="">2017</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dhlhr4jqkbcmdbua2ca45o7kru" style="color: black;">IEEE Transactions on Image Processing</a> </i> &nbsp;
We study the problem of fine-grained sketch-based image retrieval.  ...  To reduce the sketch-image gap when comparing low-level features, we also (iii) propose a novel method for instance-level domain-alignment, that exploits both subspace and instance-level cues to better  ...  Learning Coupled Feature Spaces for Cross-modal Matching (LCFS) Fig. 3 . 3 Representative sketch-image pairs in our proposed fine-grained SBIR dataset, where each image has three corresponding free-hand  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2017.2745106">doi:10.1109/tip.2017.2745106</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/28858796">pmid:28858796</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dhp2a73iyvg67kk7yu5z2x6u7m">fatcat:dhp2a73iyvg67kk7yu5z2x6u7m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180723115336/https://www.research.ed.ac.uk/portal/files/43695374/li2017fgsa.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/c8/f8c8a5f665631301ad8c7ba225ac8fe867064201.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2017.2745106"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Fine-Grained Image Analysis with Deep Learning: A Survey [article]

Xiu-Shen Wei and Yi-Zhe Song and Oisin Mac Aodha and Jianxin Wu and Yuxin Peng and Jinhui Tang and Jian Yang and Serge Belongie
<span title="2021-11-19">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
image recognition and fine-grained image retrieval.  ...  The small inter-class and large intra-class variation inherent to fine-grained image analysis makes it a challenging problem.  ...  ACKNOWLEDGMENTS The authors would like to thank the editor and the anonymous reviewers for their constructive comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.06119v2">arXiv:2111.06119v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ninawxsjtnf4lndtqquuwl3weq">fatcat:ninawxsjtnf4lndtqquuwl3weq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211128160500/https://arxiv.org/pdf/2111.06119v2.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/5b/c1/5bc13763d9d7fd15304da50389e194d49436522b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.06119v2" 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>

Learning Cross-Modal Deep Embeddings for Multi-Object Image Retrieval using Text and Sketch [article]

Sounak Dey and Anjan Dutta and Suman K. Ghosh and Ernest Valveny and Josep Lladós and Umapada Pal
<span title="2018-04-28">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work we introduce a cross modal image retrieval system that allows both text and sketch as input modalities for the query.  ...  A cross-modal deep network architecture is formulated to jointly model the sketch and text input modalities as well as the the image output modality, learning a common embedding between text and images  ...  the fine grained information.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.10819v1">arXiv:1804.10819v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dc4o5ocajfddfm6652puqy2ize">fatcat:dc4o5ocajfddfm6652puqy2ize</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201009103545/https://arxiv.org/pdf/1804.10819v1.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/f4/96/f496235629c02c98ad83b37d3d054ccfd0de0131.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.10819v1" 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>

Fine-grained sketch-based image retrieval: The role of part-aware attributes

Ke Li, Kaiyue Pang, Yi-Zhe Song, Timothy Hospedales, Honggang Zhang, Yichuan Hu
<span title="">2016</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wsjivbkuezdvxdnrhihbwjrxlu" style="color: black;">2016 IEEE Winter Conference on Applications of Computer Vision (WACV)</a> </i> &nbsp;
We study the problem of fine-grained sketch-based image retrieval.  ...  this dataset, we investigate (ii) how strongly-supervised deformable part-based models can be learned that subsequently enable automatic detection of part-level attributes, and (iii) a novel matching  ...  Conclusion We investigated the practical problem of fine-grained sketch-based image retrieval (SBIR). For the first time, we studied the role of part-aware attributes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wacv.2016.7477615">doi:10.1109/wacv.2016.7477615</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wacv/LiPSHZH16.html">dblp:conf/wacv/LiPSHZH16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7jcxle5e45dbrei6p6yeyr7x7e">fatcat:7jcxle5e45dbrei6p6yeyr7x7e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180719143812/https://www.pure.ed.ac.uk/ws/files/28352797/li2016partattrib.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/7e/bd/7ebd1e4c98d47f3a3f2ee0c54eeafab2b8e222d3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wacv.2016.7477615"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Mutually Orthogonal Softmax Axes for Cross-Domain Retrieval

Hae-Chan Noh, Jae-Pil Heo
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
INDEX TERMS Cross-domain retrieval, domain gap, sketch-based image retrieval. VOLUME 8, 2020 This work is licensed under a Creative Commons Attribution 4.0 License.  ...  For example, bear and teddy bear classes have almost the same instances in a sketch domain whereas they are greatly different in photos.  ...  cross-media retrieval and sketch-based image retrieval.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2982557">doi:10.1109/access.2020.2982557</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6iduotw4nzgqpmnjnjxq63moma">fatcat:6iduotw4nzgqpmnjnjxq63moma</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201107132853/https://ieeexplore.ieee.org/ielx7/6287639/8948470/09044384.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/20/aa/20aa3685d20675a3ea14eb6a27a7ceaeb53cd1a5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2982557"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Sketch-a-Classifier: Sketch-Based Photo Classifier Generation

Conghui Hu, Da Li, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales
<span title="">2018</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
We also demonstrate that this modality of classifier generation can also be used to enhance the granularity of an existing photo classifier, or as a complement to name-based zero-shot learning.  ...  It turns out that this mapping can be learned in a category-agnostic way, allowing photo classifiers for new categories to be synthesized by user with no need for annotated training photos.  ...  Sketch-based image retrieval Sketch based image retrieval aims to input a sketch and retrieve photos of the same category as that sketch (category level SBIR [7, 14] ) or photos corresponding to the specific  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00952">doi:10.1109/cvpr.2018.00952</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/HuLSXH18.html">dblp:conf/cvpr/HuLSXH18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/73aplwu5gbcizhocmivyaqtgsm">fatcat:73aplwu5gbcizhocmivyaqtgsm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200505092040/https://www.pure.ed.ac.uk/ws/files/58992772/hu2018Sketch_a_Classifier_Sketch_basedPhotoClassifierGeneration.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/c9/b4/c9b4952dbff2deff067482e3d44a193943391b7e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00952"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Sketch-a-Classifier: Sketch-based Photo Classifier Generation [article]

Conghui Hu, Da Li, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales
<span title="2018-04-30">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We also demonstrate that this modality of classifier generation can also be used to enhance the granularity of an existing photo classifier, or as a complement to name-based zero-shot learning.  ...  It turns out that this mapping can be learned in a category-agnostic way, allowing photo classifiers for new categories to be synthesized by user with no need for annotated training photos.  ...  Sketch-based image retrieval Sketch based image retrieval aims to input a sketch and retrieve photos of the same category as that sketch (category level SBIR [7, 14] ) or photos corresponding to the specific  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.11182v1">arXiv:1804.11182v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m5jytnqyazgejmxqq2snmhubbu">fatcat:m5jytnqyazgejmxqq2snmhubbu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191020105344/https://arxiv.org/pdf/1804.11182v1.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/e6/01/e60164c8f0f79a2f0e4cc9027b28bcaabafe40ef.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.11182v1" 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>

A Decade Survey of Content Based Image Retrieval using Deep Learning [article]

Shiv Ram Dubey
<span title="2020-11-23">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper presents a comprehensive survey of deep learning based developments in the past decade for content based image retrieval.  ...  The content based image retrieval aims to find the similar images from a large scale dataset against a query image.  ...  In 2017, Wang et al. have generated the common subspace based on adversarial learning for cross-modal retrieval [169] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.00641v1">arXiv:2012.00641v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2zcho2szpzcc3cs6uou3jpcley">fatcat:2zcho2szpzcc3cs6uou3jpcley</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201207041132/https://arxiv.org/pdf/2012.00641v1.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/36/46/36461c8627c3d54d9009fd83dab10c6e1950b401.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.00641v1" 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>

Sketchformer: Transformer-based Representation for Sketched Structure [article]

Leo Sampaio Ferraz Ribeiro, Tu Bui, John Collomosse, Moacir Ponti
<span title="2020-02-24">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Sketchformer effectively addresses multiple tasks: sketch classification, sketch based image retrieval (SBIR), and the reconstruction and interpolation of sketches.  ...  Our learned embedding, driven by a dictionary learning tokenization scheme, yields state of the art performance in classification and image retrieval tasks, when compared against baseline representations  ...  Cross-modal Matching We evaluate the performance of Sketchformer for sketch based retrieval of sketches (S-S) and images (S-I). Sketch2Sketch (S-S) Matching.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.10381v1">arXiv:2002.10381v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mrloqxhw6ffqde7gtd3ykjdwbi">fatcat:mrloqxhw6ffqde7gtd3ykjdwbi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930035137/https://arxiv.org/pdf/2002.10381v1.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/42/b3/42b3a039a666caab2881bfef244d3ce074b7f529.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.10381v1" 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>

Deep multimodal representation learning: a survey

Wenzhong Guo, Jianwen Wang, Shiping Wanga
<span title="">2019</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
Due to the powerful representation ability with multiple levels of abstraction, deep learning-based multimodal representation learning has attracted much attention in recent years.  ...  Finally, we suggest some important directions for future work.  ...  Further, Karpathy and Fei-Fei [76] extended this framework to learn a fine-grained cross-model alignment between words and image regions for generating region-level descriptions of images.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2019.2916887">doi:10.1109/access.2019.2916887</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ms4wcgl5rncsbiywz27uss4ysq">fatcat:ms4wcgl5rncsbiywz27uss4ysq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210428194622/https://ieeexplore.ieee.org/ielx7/6287639/8600701/08715409.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/c1/92/c192c7d1d94e7a64de7e18e2f2fdffbf2909fcff.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2019.2916887"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Deep Multi-Modal Metric Learning with Multi-Scale Correlation for Image-Text Retrieval

Yan Hua, Yingyun Yang, Jianhe Du
<span title="2020-03-10">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ikdpfme5h5egvnwtvvtjrnntyy" style="color: black;">Electronics</a> </i> &nbsp;
In contrast to binary similarity, we formulate semantic relationship with multi-scale similarity to learn fine-grained multi-modal distances.  ...  In this paper, we propose a deep multi-modal metric learning method with multi-scale semantic correlation to deal with the retrieval tasks between image and text modalities.  ...  The optimization is to minimize the loss by fine-tuning ResNet and learning the multiple nonlinear transformations from sketch for image and text modalities.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics9030466">doi:10.3390/electronics9030466</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/32bdzztgx5g3vbrrxutyfebufq">fatcat:32bdzztgx5g3vbrrxutyfebufq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200315235134/https://res.mdpi.com/d_attachment/electronics/electronics-09-00466/article_deploy/electronics-09-00466.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/7a/05/7a057765104a52b161bbf71653bd7e4c041ebda5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics9030466"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Sketchformer: Transformer-Based Representation for Sketched Structure

Leo Sampaio Ferraz Ribeiro, Tu Bui, John Collomosse, Moacir Ponti
<span title="">2020</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</a> </i> &nbsp;
Sketchformer effectively addresses multiple tasks: sketch classification, sketch based image retrieval (SBIR), and the reconstruction and interpolation of sketches.  ...  Our learned embedding, driven by a dictionary learning tokenization scheme, yields state of the art performance in classification and image retrieval tasks, when compared against baseline representations  ...  Cross-modal Matching We evaluate the performance of Sketchformer for sketch based retrieval of sketches (S-S) and images (S-I). Sketch2Sketch (S-S) Matching.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr42600.2020.01416">doi:10.1109/cvpr42600.2020.01416</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/RibeiroBCP20.html">dblp:conf/cvpr/RibeiroBCP20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nifojt75bna5llresrxl7oup4m">fatcat:nifojt75bna5llresrxl7oup4m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201105043923/http://epubs.surrey.ac.uk/858475/1/09156285.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/fa/0a/fa0aeb7264a952fc664bd24e1bc973a58f4a123e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr42600.2020.01416"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Cross-Paced Representation Learning With Partial Curricula for Sketch-Based Image Retrieval

Dan Xu, Xavier Alameda-Pineda, Jingkuan Song, Elisa Ricci, Nicu Sebe
<span title="">2018</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dhlhr4jqkbcmdbua2ca45o7kru" style="color: black;">IEEE Transactions on Image Processing</a> </i> &nbsp;
In this paper we address the problem of learning robust cross-domain representations for sketch-based image retrieval (SBIR).  ...  the cross-paced partial curriculum learning (CPPCL) framework.  ...  CONCLUSIONS We presented a novel cross-domain representation learning framework for computing robust cross-modal features for sketch-based image retrieval.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2018.2837381">doi:10.1109/tip.2018.2837381</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/29870357">pmid:29870357</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7kwq3lsxm5gdbft7vfel2brd7a">fatcat:7kwq3lsxm5gdbft7vfel2brd7a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180719191133/https://hal.inria.fr/hal-01803694/document" 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/34/ac/34ac65dd3a6a01f7e9068fe9d974be5acbac2f01.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2018.2837381"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

T-EMDE: Sketching-based global similarity for cross-modal retrieval [article]

Barbara Rychalska, Mikolaj Wieczorek, Jacek Dabrowski
<span title="2021-05-10">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The key challenge in cross-modal retrieval is to find similarities between objects represented with different modalities, such as image and text.  ...  It facilitates communication between modalities, as each global text/image representation is expressed with a standardized sketch histogram which represents the same manifold structures irrespective of  ...  The aim was to learn to map both modalities to the same vector space, where the similarity measure could be applied for the cross-modal retrieval.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.04242v1">arXiv:2105.04242v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6e4lzid6evdqdh2kw4sgt3rgna">fatcat:6e4lzid6evdqdh2kw4sgt3rgna</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210512112256/https://arxiv.org/pdf/2105.04242v1.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/3a/95/3a957999b638c8c12c0fa755e0f3da74be421f8f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.04242v1" 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>
&laquo; Previous Showing results 1 &mdash; 15 out of 252 results