Filters








7,822 Hits in 8.5 sec

A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes [article]

Mazda Moayeri, Phillip Pope, Yogesh Balaji, Soheil Feizi
<span title="2022-01-26">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Using RIVAL10, we evaluate the sensitivity of a broad set of models to noise corruptions in foregrounds, backgrounds and attributes.  ...  Using saliency methods, we automatically discover spurious features that drive the background sensitivity of models and assess alignment of saliency maps with foregrounds.  ...  We then provide a study of the sensitivity of a diverse set of models to foregrounds, backgrounds, and attributes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.10766v1">arXiv:2201.10766v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hnfnj5h2ive33mbwwc4gkkwq6y">fatcat:hnfnj5h2ive33mbwwc4gkkwq6y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220130180154/https://arxiv.org/pdf/2201.10766v1.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/88/b5/88b5acbec09ed39eecdca136f75ff90feb2fc3a3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.10766v1" 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>

Salient Region Detection by Integrating Intrinsic and Extrinsic Cues without Prior Information

Ji Ma, Jingjiao Li, Zhenni Li, Jiao Jiao
<span title="">2017</span> <i title="Eastern Macedonia and Thrace Institute of Technology"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/bdh2aivq6feixdfzfu2el5io6q" style="color: black;">Journal of Engineering Science and Technology Review</a> </i> &nbsp;
A salient region detection framework that integrates intrinsic and extrinsic visual cues was proposed in this study to remove the limitations of prior information.  ...  This study provides a novel method to improve the performance of salient region detection and to avoid prior information.  ...  This is an Open Access article distributed under the terms of the Creative Commons Attribution Licence ______________________________ References  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.25103/jestr.103.24">doi:10.25103/jestr.103.24</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jqscu7hj5jgdhdc5m2eevo6lay">fatcat:jqscu7hj5jgdhdc5m2eevo6lay</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180604105249/http://www.jestr.org/downloads/Volume10Issue3/fulltext241032017.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/19/bf/19bfc50aecd78c1133fa16804436e8b5cf617adb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.25103/jestr.103.24"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Human detection in surveillance videos and its applications - a review

Manoranjan Paul, Shah M E Haque, Subrata Chakraborty
<span title="2013-11-22">2013</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hqblpsydr5emviirtqkkmctpha" style="color: black;">EURASIP Journal on Advances in Signal Processing</a> </i> &nbsp;
, gender classification and fall detection for elderly people.  ...  The first step of the detection process is to detect an object which is in motion.  ...  The key purpose of this paper is to provide a comprehensive review on studies conducted in the area of human detection process of a visual surveillance system.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/1687-6180-2013-176">doi:10.1186/1687-6180-2013-176</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hucglmedkrffxdvyo4fi7lthqa">fatcat:hucglmedkrffxdvyo4fi7lthqa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170812201441/https://asp-eurasipjournals.springeropen.com/track/pdf/10.1186/1687-6180-2013-176?site=asp.eurasipjournals.springeropen.com" 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/6a/1a/6a1a38748f836a036eb1aebba0b8cb8a75c13ea4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/1687-6180-2013-176"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a>

Attribute-based People Search

Rogerio Feris, Russel Bobbitt, Lisa Brown, Sharath Pankanti
<span title="">2014</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/bj3ypeajjfeb7pqvvlh5snru4a" style="color: black;">Proceedings of International Conference on Multimedia Retrieval - ICMR &#39;14</a> </i> &nbsp;
In particular, we show that a novel set of multimodal integral filters and proper normalization of attribute scores are critical to obtain good performance.  ...  We conduct a comprehensive experimental analysis on video footage captured from a large set of surveillance cameras monitoring metro chokepoints, in both crowded and normal activity periods.  ...  The following filters are considered in our system: Integral Foreground Filter. We compute the integral image I f or of the foreground image obtained by the background modeling algorithm.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2578726.2578732">doi:10.1145/2578726.2578732</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/mir/FerisBBP14.html">dblp:conf/mir/FerisBBP14</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uawezbik5nd3dmjtnac6am5vzq">fatcat:uawezbik5nd3dmjtnac6am5vzq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20150219111254/http://rogerioferis.com/publications/FerisICMR2014.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/bd/2d/bd2d7c7f0145028e85c102fe52655c2b6c26aeb5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2578726.2578732"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

SketchyCOCO: Image Generation from Freehand Scene Sketches [article]

Chengying Gao, Qi Liu, Qi Xu, Limin Wang, Jianzhuang Liu, Changqing Zou
<span title="2020-04-07">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We have built a large-scale composite dataset called SketchyCOCO to support and evaluate the solution.  ...  We validate our approach on the tasks of both object-level and scene-level image generation on SketchyCOCO.  ...  For background generation, we train the pix2pix model with the 110 epochs. We use XDoG [36] to obtain the edge maps of objects for training data.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.02683v5">arXiv:2003.02683v5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jfqsjwctpfflpjkt2bkgpsnice">fatcat:jfqsjwctpfflpjkt2bkgpsnice</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200409003148/https://arxiv.org/pdf/2003.02683v5.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] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.02683v5" 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>

Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation [article]

Qiqi Hou, Feng Liu
<span title="2019-10-02">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper presents a context-aware natural image matting method for simultaneous foreground and alpha matte estimation.  ...  Particularly, we use a matting encoder to learn local features and a context encoder to obtain more global context information.  ...  The source images in Figure 1 are used under a Creative Commons license from Flickr users Robbie Sproule, MEGA PISTOLO and Jeff Latimer.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.09725v2">arXiv:1909.09725v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/quwqsrihbbfhfijw4epkohom2y">fatcat:quwqsrihbbfhfijw4epkohom2y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200830170830/https://arxiv.org/pdf/1909.09725v2.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/9b/96/9b966323f8ba738d9a50bc093fb6ab9fef7a9f3d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.09725v2" 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>

Geometric Recognition of Moving Objects in Monocular Rotating Imagery Using Faster R-CNN

Tzu-Yi Chuang, Jen-Yu Han, Deng-Jie Jhan, Ming-Der Yang
<span title="2020-06-12">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/kay2tsbijbawliu45dnhvyvgsq" style="color: black;">Remote Sensing</a> </i> &nbsp;
Moving object detection and tracking from image sequences has been extensively studied in a variety of fields.  ...  The focus of this study is to determine moving trajectories, object heights, and object recognition using a monocular camera configuration.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs12121908">doi:10.3390/rs12121908</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/di7foe6esbh2di7noooqflclpu">fatcat:di7foe6esbh2di7noooqflclpu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200616034010/https://res.mdpi.com/d_attachment/remotesensing/remotesensing-12-01908/article_deploy/remotesensing-12-01908-v2.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/48/9b/489bf6fcd8ba0559558cb0ca9c601da17a07ffb4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs12121908"> <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>

Vision Transformers are Robust Learners [article]

Sayak Paul, Pin-Yu Chen
<span title="2021-12-04">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We use six different diverse ImageNet datasets concerning robust classification to conduct a comprehensive performance comparison of ViT models and SOTA convolutional neural networks (CNNs), Big-Transfer  ...  Our analyses on image masking, Fourier spectrum sensitivity, and spread on discrete cosine energy spectrum reveal intriguing properties of ViT attributing to improved robustness.  ...  We also thank Justin Gilmer (of Google), Guillermo Ortiz-Jimenez (of EPFL, Switzerland), and Dan Hendrycks (of UC Berkeley) for fruitful discussions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.07581v3">arXiv:2105.07581v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ngw5cdn2mbcwdcsoqzo6kfas24">fatcat:ngw5cdn2mbcwdcsoqzo6kfas24</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210520040503/https://arxiv.org/pdf/2105.07581v2.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/b1/5c/b15cd0a0b8db2f99f5b593d324f116e6177e246c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.07581v3" 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>

An Attention-Based Deep Learning Model for Multiple Pedestrian Attributes Recognition [article]

Ehsan Yaghoubi, Diana Borza, João Neves, Aruna Kumar, Hugo Proença
<span title="2020-04-02">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
between the different full-body attributes, we propose a multi-task deep model that uses an element-wise multiplication layer to extract more comprehensive feature representations.  ...  In practice, this layer serves as a filter to remove irrelevant background features, and is particularly important to handle complex, cluttered data; and 2) we introduce a weighted-sum term to the loss  ...  Also, the work is funded by FCT/MEC through national funds and, when applicable, co-funded by the FEDER PT2020 partnership agreement under the project UID/EEA/50008/2019.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.01110v1">arXiv:2004.01110v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/flyuqx2cyngqnnqzbmwlrkwe4e">fatcat:flyuqx2cyngqnnqzbmwlrkwe4e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200404001552/https://arxiv.org/pdf/2004.01110v1.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] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.01110v1" 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>

Motion Balance Ability Detection Based on Video Analysis in Virtual Reality Environment

Jilan Zhou, Yang You, Yanmin Zhao
<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;
modeling and classification.  ...  Improved Motion Model (IMM) is a background sample balance acquisition algorithm based on simple linear iterative clustering, completes the abstraction of background images.  ...  considers multiple attributes of the target to construct a more comprehensive, accurate and expressive target sample set.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3019609">doi:10.1109/access.2020.3019609</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wbpdbc5hvbb6rnseqllt2z7bhm">fatcat:wbpdbc5hvbb6rnseqllt2z7bhm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829005948/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09178336.pdf?tp=&amp;arnumber=9178336&amp;isnumber=6514899&amp;ref=" 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/2e/c7/2ec7c0131971a6b76c4cbf267c181327e4ebf4ce.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3019609"> <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>

Explaining Knowledge Distillation by Quantifying the Knowledge [article]

Xu Cheng, Zhefan Rao, Yilan Chen, Quanshi Zhang
<span title="2020-03-07">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper presents a method to interpret the success of knowledge distillation by quantifying and analyzing task-relevant and task-irrelevant visual concepts that are encoded in intermediate layers of  ...  Accordingly, we design three types of mathematical metrics to evaluate feature representations of the DNN. In experiments, we diagnosed various DNNs, and above hypotheses were verified.  ...  He thanks the support of National Natural Science Foundation of China (U19B2043 and 61906120) and Huawei Technologies.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.03622v1">arXiv:2003.03622v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yhvibotjxrasna7d4vrg6xqu5y">fatcat:yhvibotjxrasna7d4vrg6xqu5y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200320170656/https://arxiv.org/pdf/2003.03622v1.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] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.03622v1" 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>

Automatic Scribe Attribution for Medieval Manuscripts

Mats Dahllöf
<span title="2018-12-24">2018</span> <i title="Open Library of the Humanities"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/owkbr3mshfckxhxnrqzdbikqra" style="color: black;">Digital Medievalist</a> </i> &nbsp;
Regional Historic Centre Limburg, and the Henri Pirenne Institute for Medieval Studies (Ghent University).  ...  We also want to acknowledge the helpful comments from the anonymous reviewers, who suggested several improvements of the presentation.  ...  This means that the models are difficult to visualize in terms comprehensible from a traditional palaeographic point of view.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.16995/dm.67">doi:10.16995/dm.67</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pb5cuwmg75eavmkzccjixy4eje">fatcat:pb5cuwmg75eavmkzccjixy4eje</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200210120248/https://journal.digitalmedievalist.org/articles/10.16995/dm.67/galley/92/download/" 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] </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.16995/dm.67"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Visual Landscape Assessment for Development Landscape Structure: Case study at Taiping, Perak

Mohd Zulhaili Teh, Noorsazwan Ahmad Pugi, Norhafizah Abdul Rahman
<span title="2017-03-19">2017</span> <i title="e-IPH Ltd."> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7ogtrf7jxfaajjnynblu637dni" style="color: black;">Environment-Behaviour Proceedings Journal (E-BPJ)</a> </i> &nbsp;
The aim of this study is to provide a visual structure for landscape classification of the Taiping District area that will contribute to the decision making in development and management in Malaysia.  ...  This study attempts to evaluate visual landscape of Taiping District in relations to the larger landscape scale in Peninsular Malaysia.  ...  The authors would like to acknowledge Institute of Research Management and Innovation (IRMI), Universiti Teknologi MARA for providing necessary assistance for the preparation of this research.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21834/e-bpj.v2i5.698">doi:10.21834/e-bpj.v2i5.698</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hj5zypdoqzbkbpigdpaap2gzlq">fatcat:hj5zypdoqzbkbpigdpaap2gzlq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170923000154/https://ebpj.e-iph.co.uk/index.php/EBProceedings/article/download/698/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/26/68/2668e8fd0d1a227d403ae7ba952b28b4d934aee2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21834/e-bpj.v2i5.698"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Review of Visual Saliency Detection with Comprehensive Information [article]

Runmin Cong, Jianjun Lei, Huazhu Fu, Ming-Ming Cheng, Weisi Lin, and Qingming Huang
<span title="2018-09-14">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Visual saliency detection model simulates the human visual system to perceive the scene, and has been widely used in many vision tasks.  ...  Moreover, the evaluation datasets and quantitative measurements are briefly introduced, and the experimental analysis and discission are conducted to provide a holistic overview of different saliency detection  ...  However, it is a tricky question, which requires researchers to gain insight into the characteristics of depth data, and to comprehensively explore the depth attributes of salient objects.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.03391v2">arXiv:1803.03391v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/htcmhlo32jhczehvvq6nmgzwam">fatcat:htcmhlo32jhczehvvq6nmgzwam</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929201535/https://arxiv.org/pdf/1803.03391v2.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/10/0b/100b5cffe91d0a2c6b0ea049acaac437fb0f7ec4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.03391v2" 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>

Single Object Tracking: A Survey of Methods, Datasets, and Evaluation Metrics [article]

Zahra Soleimanitaleb, Mohammad Ali Keyvanrad
<span title="2022-01-31">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, different strategies of the following objects are inspected and a comprehensive classification is displayed that classified the following strategies into four fundamental categories of feature-based  ...  Different researches have been tried later a long time, but since of diverse challenges such as occlusion, illumination variations, fast motion, etc. researches in this area continues.  ...  Foreground segmentation is done to separate foreground objects from the background scene. Normally, the foreground objects are the objects that are moving in a scene.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.13066v1">arXiv:2201.13066v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/k6ytweddvrbbzfvt4ntkk75m7a">fatcat:k6ytweddvrbbzfvt4ntkk75m7a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220204225151/https://arxiv.org/ftp/arxiv/papers/2201/2201.13066.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/15/b5/15b5f9b47db87eb01708aedea4ef6e05452fed96.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.13066v1" 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 7,822 results