Filters








87 Hits in 5.6 sec

Efficient Video Instance Segmentation via Tracklet Query and Proposal [article]

Jialian Wu, Sudhir Yarram, Hui Liang, Tian Lan, Junsong Yuan, Jayan Eledath, Gerard Medioni
<span title="2022-03-03">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Video Instance Segmentation (VIS) aims to simultaneously classify, segment, and track multiple object instances in videos.  ...  At the core are tracklet query and tracklet proposal that associate and segment regions-of-interest (RoIs) across space and time by an iterative query-video interaction.  ...  This paper is supported in part by a gift grant from Amazon Go and National Science Foundation Grant CNS1951952.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.01853v1">arXiv:2203.01853v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qkedunu3wvfqtimpylvt5ul6da">fatcat:qkedunu3wvfqtimpylvt5ul6da</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220308161945/https://arxiv.org/pdf/2203.01853v1.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/5d/60/5d60f8dfffa995560e7c1c25eb20e2f89715a6b9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.01853v1" 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>

STEP: Segmenting and Tracking Every Pixel [article]

Mark Weber, Jun Xie, Maxwell Collins, Yukun Zhu, Paul Voigtlaender, Hartwig Adam, Bradley Green, Andreas Geiger, Bastian Leibe, Daniel Cremers, Aljoša Ošep, Laura Leal-Taixé (+1 others)
<span title="2021-12-07">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The datasets contain long video sequences, providing challenging examples and a test-bed for studying long-term pixel-precise segmentation and tracking under real-world conditions.  ...  The task of assigning semantic classes and track identities to every pixel in a video is called video panoptic segmentation.  ...  We would like to thank Sérgio Agostinho, Deqing Sun and Siyuan Qiao for their valuable feedback, and Stefan Popov and Vittorio Ferrari for their work on the annotation tool.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.11859v2">arXiv:2102.11859v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/oawh5wchdzbq3nm5c6inoug2se">fatcat:oawh5wchdzbq3nm5c6inoug2se</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211209012006/https://arxiv.org/pdf/2102.11859v2.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/21/22/21229d4c984f9a6bcc3571742df48f6bd0971b90.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.11859v2" 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>

Video Polyp Segmentation: A Deep Learning Perspective [article]

Ge-Peng Ji, Guobao Xiao, Yu-Cheng Chou, Deng-Ping Fan, Kai Zhao, Geng Chen, Huazhu Fu, Luc Van Gool
<span title="2022-03-27">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In the deep learning era, we present the first comprehensive video polyp segmentation (VPS) study.  ...  Third, we extensively evaluate 13 representative polyp/object segmentation models on our SUN-SEG dataset and provide attribute-based comparisons.  ...  Different from the above datasets, LDPolypVideo [12] includes 40, 266 frames with the circular annotations from 160 colonoscopy videos. 3) Segmentation: As for the video datasets, the early benchmark  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.14291v1">arXiv:2203.14291v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/g4nuvwvzljbmfodzpd4gtj5c3i">fatcat:g4nuvwvzljbmfodzpd4gtj5c3i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220613214705/https://arxiv.org/pdf/2203.14291v1.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/8e/3c/8e3cb1fac2763260665be7619e51fdafb0b0956b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.14291v1" 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>

3D Instance Segmentation of MVS Buildings [article]

Yanghui Xu, Jiazhou Chen, Shufang Lu, Ronghua Liang, Liangliang Nan
<span title="2021-12-18">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A dataset for the evaluation of instance segmentation of 3D building models is provided as well.  ...  To the best of our knowledge, it is the first dataset for 3D urban buildings on the instance segmentation level.  ...  Yan, “Blendmask: sensing dataset and challenge series,” arXiv preprint arXiv:1807.01232, Top-down meets bottom-up for instance segmentation,” in Proceedings 2018.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.09902v1">arXiv:2112.09902v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7xk75hbbpfaxxkoz3hzixvktuu">fatcat:7xk75hbbpfaxxkoz3hzixvktuu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220103085611/https://arxiv.org/pdf/2112.09902v1.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/73/92/73928fb8bb2deb650955a6576b834be6ae3528e5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.09902v1" 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>

Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation

Takehiko Ohkawa, Takuma Yagi, Atsushi Hashimoto, Yoshitaka Ushiku, Yoichi Sato
<span title="">2021</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;
We also demonstrated promising results in challenging multi-target domain adaptation and domain generalization settings. Code is available at https://github.com/ut-vision/FgSty-CPL.  ...  We propose (i) foreground-aware image stylization and (ii) consensus pseudo-labeling for domain adaptation of hand segmentation.  ...  Computer Vision and Image Understanding, the CVPR 2023 General Co-Chair, the ICCV 2021 Program Co-Chair, the ACCV 2018 General Co-Chair, the ACCV 2016 Program Co-Chair, and the ECCV 2012 Program Co-Chair  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3094052">doi:10.1109/access.2021.3094052</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nelc65iu7bfc7nsult3rnjttze">fatcat:nelc65iu7bfc7nsult3rnjttze</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210712195634/https://ieeexplore.ieee.org/ielx7/6287639/9312710/09469781.pdf?tp=&amp;arnumber=9469781&amp;isnumber=9312710&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/17/c1/17c113147d7853412541639bf7a601ff421db1b8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3094052"> <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>

Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation [article]

Gedas Bertasius, Lorenzo Torresani
<span title="2021-07-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
MaskProp achieves the best reported accuracy on the YouTube-VIS dataset, outperforming the ICCV 2019 video instance segmentation challenge winner despite being much simpler and using orders of magnitude  ...  We introduce a method for simultaneously classifying, segmenting and tracking object instances in a video sequence.  ...  Currently, the best method for video instance segmentation is the ICCV 2019 challenge winner [28] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.04573v4">arXiv:1912.04573v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nrrv6vmksfchjf44avtib54rvi">fatcat:nrrv6vmksfchjf44avtib54rvi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210714141740/https://arxiv.org/pdf/1912.04573v4.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/a4/f1/a4f1747ed9e2477c8d1c5f55033dbfba4d42dd63.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.04573v4" 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>

Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation [article]

Christos Sakaridis, Dengxin Dai, Luc Van Gool
<span title="2021-01-07">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
between daytime images from a reference map and dark images to guide the label inference in the dark domains; 2) a novel uncertainty-aware annotation and evaluation framework and metric for semantic segmentation  ...  , including image regions beyond human recognition capability in the evaluation in a principled fashion; 3) the Dark Zurich dataset, comprising 2416 unlabeled nighttime and 2920 unlabeled twilight images  ...  Our dataset is publicly available 1 and is used for hosting a CVPR 2020 challenge on nighttime segmentation 2 .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.14553v2">arXiv:2005.14553v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nzs4xiruuzbvtoopwkitccxi34">fatcat:nzs4xiruuzbvtoopwkitccxi34</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200602013716/https://arxiv.org/pdf/2005.14553v1.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> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.14553v2" 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>

Boundary-Aware Segmentation Network for Mobile and Web Applications [article]

Xuebin Qin and Deng-Ping Fan and Chenyang Huang and Cyril Diagne and Zichen Zhang and Adrià Cabeza Sant'Anna and Albert Suàrez and Martin Jagersand and Ling Shao
<span title="2021-05-11">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Although deep models have greatly improved the accuracy and robustness of image segmentation, obtaining segmentation results with highly accurate boundaries and fine structures is still a challenging problem  ...  In this paper, we propose a simple yet powerful Boundary-Aware Segmentation Network (BASNet), which comprises a predict-refine architecture and a hybrid loss, for highly accurate image segmentation.  ...  The corresponding quantitative results can be found in Fig. 7 . 7 Qualitative comparison on salient object segmentation datasets. created for semantic image segmentation and consists of 850 challenging  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.04704v2">arXiv:2101.04704v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/irni2rl3bbbrbjjuk3s6bz32fe">fatcat:irni2rl3bbbrbjjuk3s6bz32fe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210513121733/https://arxiv.org/pdf/2101.04704v2.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/1f/65/1f65ca19b7e8e47f6620426d5d5bbf1f8bfb4623.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.04704v2" 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>

ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization [article]

Zichen Yang, Jie Qin, Di Huang
<span title="2021-12-21">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Weakly-supervised temporal action localization (WTAL) in untrimmed videos has emerged as a practical but challenging task since only video-level labels are available.  ...  By this means, the segment-level features are more discriminative and robust to spatial-temporal variations, contributing to higher localization accuracies.  ...  The dataset is quite challenging due to the diversified video lengths and the large number of action instances (∼15) per video. The train- Results on THUMOS’14.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.10977v1">arXiv:2112.10977v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r5xj6pnstzelzbhysluzscf5vq">fatcat:r5xj6pnstzelzbhysluzscf5vq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211230090927/https://arxiv.org/pdf/2112.10977v1.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/fc/91/fc911c620b95a29fc9f687d8f1330f8a566ed873.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.10977v1" 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>

Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer [article]

Tao Wang, Hong Liu, Pinhao Song, Tianyu Guo, Wei Shi
<span title="2021-12-11">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Extensive experiments over five challenging datasets for two tasks (occluded and holistic Re-ID) demonstrate that our proposed PFD is superior promising, which performs favorably against state-of-the-art  ...  Occluded person re-identification is a challenging task as human body parts could be occluded by some obstacles (e.g. trees, cars, and pedestrians) in certain scenes.  ...  Occluded-Duke Market-1501 and DukeMTMC-reID datasets.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.02466v2">arXiv:2112.02466v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/37hftouzwrfivpugzvqvfqrwkm">fatcat:37hftouzwrfivpugzvqvfqrwkm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211215200828/https://arxiv.org/pdf/2112.02466v2.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/d5/96/d5960b9a7794bf6a69f1835b974a0a129ecffa65.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.02466v2" 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>

SHD360: A Benchmark Dataset for Salient Human Detection in 360 Videos [article]

Yi Zhang, Lu Zhang, Kang Wang, Wassim Hamidouche, Olivier Deforges
<span title="2021-12-22">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, 360 video SHD has been seldom discussed in the computer vision community due to a lack of datasets with large-scale omnidirectional videos and rich annotations.  ...  To this end, we propose SHD360, the first 360 video SHD dataset which contains various real-life daily scenes.  ...  More recent datasets such as VOS [29] and DAVSOD [14] contain videos with more challenging scenes and more salient objects.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.11578v7">arXiv:2105.11578v7</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/afttbnm5gbfijdvzcrdznl7aqq">fatcat:afttbnm5gbfijdvzcrdznl7aqq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211209005536/https://arxiv.org/pdf/2105.11578v6.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/8d/ca/8dcaa11a5749abd0d6e6136e3aebb8bd2c3f9652.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.11578v7" 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 Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification [article]

Mengxi Jia, Xinhua Cheng, Shijian Lu, Jian Zhang
<span title="2021-07-06">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Extensive experiments over occluded and holistic re-ID benchmarks (Occluded-DukeMTMC, Market1501 and DukeMTMC) show that the DRL-Net achieves superior re-ID performance consistently and outperforms the  ...  Person re-identification (re-ID) under various occlusions has been a long-standing challenge as person images with different types of occlusions often suffer from misalignment in image matching and ranking  ...  Datasets and Evaluation Metrics The experiments are conducted on three person ReID datasets, including one occluded re-ID dataset Occluded-DukeMTMC and two widely used Holistic re-ID datasets MSMT1 and  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.02380v1">arXiv:2107.02380v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kfjfp6zchzeq7c53udq6wzfncu">fatcat:kfjfp6zchzeq7c53udq6wzfncu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210710160416/https://arxiv.org/pdf/2107.02380v1.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/f4/06/f4064793439109140b1385e4e0ef9dc50eea9a22.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.02380v1" 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>

Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey [article]

Gaoang Wang, Mingli Song, Jenq-Neng Hwang
<span title="2022-05-22">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Unlike other computer vision tasks, such as image classification, object detection, re-identification, and segmentation, embedding methods in MOT have large variations, and they have never been systematically  ...  We further summarize the existing widely used MOT datasets and analyze the advantages of existing state-of-the-art methods according to their embedding strategies.  ...  28] 2019 ICCV V C 84.3 73.2 Seq [177] 2021 ICCV V C 91.3 78.0 [177] 2021 ICCV V P 66.0 48.6 Tracklet [40] 2021 ICCV V C 87.6 73.1 [40] 2021 ICCV V C 87.6 73.1 X-Track [208] [6] 2021 2020 ArXiv CVPR V V  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.10766v1">arXiv:2205.10766v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/p7s7lnnlsnadrhsdcmwlg7msfy">fatcat:p7s7lnnlsnadrhsdcmwlg7msfy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220525164248/https://arxiv.org/pdf/2205.10766v1.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/5f/76/5f76de56a59744eb1b771e5940cec65dc488af7e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.10766v1" 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>

Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective [article]

Wu Liu, Qian Bao, Yu Sun, Tao Mei
<span title="2021-04-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Finally, we discuss the challenges and give deep thinking of promising directions for future research.  ...  By systematically summarizing the differences and connections between these approaches, we further analyze the solutions for challenging cases, such as the lack of data, the inherent ambiguity between  ...  The dataset contains over 200K images and 250K person instances. Along with the dataset, the Challenge of COCO Keypoint Detection is held every year since 2016. The dataset has two versions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.11536v1">arXiv:2104.11536v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tdag2jq2vjdrjekwukm5nu7l6a">fatcat:tdag2jq2vjdrjekwukm5nu7l6a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210427042152/https://arxiv.org/pdf/2104.11536v1.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/33/44/33441300a116fe57051619d3680ce30280da3b33.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.11536v1" 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>

VoteHMR: Occlusion-Aware Voting Network for Robust 3D Human Mesh Recovery from Partial Point Clouds [article]

Guanze Liu, Yu Rong, Lu Sheng
<span title="2021-10-17">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The proposed method achieves state-of-the-art performances on two large-scale datasets, namely SURREAL and DFAUST.  ...  Furthermore, VoteHMR also demonstrates superior generalization ability on real-world datasets, such as Berkeley MHAD.  ...  PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation. In Rodgers, and James Davis. 2005.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.08729v1">arXiv:2110.08729v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3b25xw26qraalbtuuejmiqedwy">fatcat:3b25xw26qraalbtuuejmiqedwy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211021034014/https://arxiv.org/pdf/2110.08729v1.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/a3/ca/a3ca1a07dd5d2dda2d598a994d6e06d30199c834.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.08729v1" 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 87 results