Filters








6 Hits in 4.1 sec

RPM-Net: Robust Pixel-Level Matching Networks for Self-Supervised Video Object Segmentation [article]

Youngeun Kim, Seokeon Choi, Hankyeol Lee, Taekyung Kim, Changick Kim
<span title="2019-10-10">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we introduce a self-supervised approach for video object segmentation without human labeled data.Specifically, we present Robust Pixel-level Matching Net-works (RPM-Net), a novel deep architecture  ...  Moreover, we significantly reduce the performance gap between self-supervised and fully-supervised video object segmentation (41.0% vs. 52.5% on DAVIS-2017 validation set)  ...  To this end, we introduce Robust Pixel-Level Matching Networks (RPM-Net) for self-supervised video object segmentation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.13247v2">arXiv:1909.13247v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jnbj2ryfhfcqbgerpd54h5ilzm">fatcat:jnbj2ryfhfcqbgerpd54h5ilzm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200907134231/https://arxiv.org/pdf/1909.13247v2.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/9c/86/9c8676057110a0c0178c509f0def601e7f19b681.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.13247v2" 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>

Box Supervised Video Segmentation Proposal Network [article]

Tanveer Hannan, Rajat Koner, Jonathan Kobold, Matthias Schubert
<span title="2022-02-16">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Video Object Segmentation (VOS) has been targeted by various fully-supervised and self-supervised approaches.  ...  In this work, we propose a box-supervised video object segmentation proposal network, which takes advantage of intrinsic video properties.  ...  Color.[60] Self 34.0 34.6 32.7 CycleTime[63] Self 48.7 46.4 50.0 CorrFlow[24] Self 50.3 48.4 52.2 UVC[29] Self 59.5 57.7 61.3 RPM-Net[18] Self 41.6 41.0 42.2 Mug[38] Self 56.1 54.0 58.2 BoxInst[56] †  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.07025v2">arXiv:2202.07025v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/alq22qzyjvfhpi5eyxbt7zbcza">fatcat:alq22qzyjvfhpi5eyxbt7zbcza</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220219045600/https://arxiv.org/pdf/2202.07025v2.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/a2/5b/a25b714cf51906fcf09cde29ae93c3ef936c2f81.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.07025v2" 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>

Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation [article]

Bo Miao, Mohammed Bennamoun, Yongsheng Gao, Ajmal Mian
<span title="2021-10-28">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a self-supervised spatio-temporal matching method, coined Motion-Aware Mask Propagation (MAMP), for video object segmentation.  ...  Moreover, MAMP performs at par with many supervised video object segmentation methods. Our code is available at: https://github.com/bo-miao/MAMP.  ...  Self-supervised Feature Representation Learning We use the reconstruction task for self-supervised feature representation learning and robust spatio-temporal matching.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.12569v2">arXiv:2107.12569v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/escvlh6fsbclllgv34xtsd5paq">fatcat:escvlh6fsbclllgv34xtsd5paq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211101134914/https://arxiv.org/pdf/2107.12569v2.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/96/a5/96a597a1b6649992cf55d8ef758bc6de684fe3ee.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.12569v2" 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 Learning for 3D Point Cloud Understanding: A Survey [article]

Haoming Lu, Humphrey Shi
<span title="2021-05-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
, segmentation, detection, tracking, flow estimation, registration, augmentation and completion), together with commonly used datasets, metrics and state-of-the-art performances.  ...  While deep learning has achieved remarkable success on image-based tasks, there are many unique challenges faced by deep neural networks in processing massive, unstructured and noisy 3D points.  ...  RPM-Net [125] inherits the idea of RPM [27] algorithm, and takes advantage of deep learning to enhance robustness against noise, outliers and bad initialization.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.08920v2">arXiv:2009.08920v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qiuhs6v345bpffzjk2nvhgbfvq">fatcat:qiuhs6v345bpffzjk2nvhgbfvq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210602170539/https://arxiv.org/pdf/2009.08920v2.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/c3/90/c390d6460bc1b3048fb1d293592d676a86d4a9bd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.08920v2" 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>

CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations [article]

Davis Rempe, Tolga Birdal, Yongheng Zhao, Zan Gojcic, Srinath Sridhar, Leonidas J. Guibas
<span title="2020-11-11">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Different from previous work, CaSPR learns representations that support spacetime continuity, are robust to variable and irregularly spacetime-sampled point clouds, and generalize to unseen object instances  ...  We propose CaSPR, a method to learn object-centric Canonical Spatiotemporal Point Cloud Representations of dynamically moving or evolving objects.  ...  The authors thank Michael Niemeyer for providing the code and shape models used to generate the warping cars dataset.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.02792v2">arXiv:2008.02792v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xxn7tf5r3vf35exzpajhqzeazi">fatcat:xxn7tf5r3vf35exzpajhqzeazi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201114100421/https://arxiv.org/pdf/2008.02792v2.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/51/64/51644c3d00fb94a4f3be19309a5a49386800da1c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.02792v2" 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>

Image Matching from Handcrafted to Deep Features: A Survey

Jiayi Ma, Xingyu Jiang, Aoxiang Fan, Junjun Jiang, Junchi Yan
<span title="2020-08-04">2020</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hfdglwo5wbbmta6wop52fam7a4" style="color: black;">International Journal of Computer Vision</a> </i> &nbsp;
matching methods with superior performance in accuracy, robustness and efficiency.  ...  Secondly, we briefly introduce several typical image matching-based applications for a comprehensive understanding of the significance of image matching.  ...  often depend on an appropriate patch similarity measurement for creating pixel level matches between images.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11263-020-01359-2">doi:10.1007/s11263-020-01359-2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/a2epfaolwjfm5mcrsmn7g6sd7m">fatcat:a2epfaolwjfm5mcrsmn7g6sd7m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108024942/https://link.springer.com/content/pdf/10.1007/s11263-020-01359-2.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/77/a9/77a956512e22e37223ac6a00dcf191a086951505.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11263-020-01359-2"> <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>