MessyTable: Instance Association in Multiple Camera Views

We present an interesting and challenging dataset that features a large number of scenes with messy tables captured from multiple camera views. Each scene in this dataset is highly complex, containing multiple object instances that could be identical, stacked and occluded by other instances. The key...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-07
Main Authors: Cai, Zhongang, Zhang, Junzhe, Ren, Daxuan, Yu, Cunjun, Zhao, Haiyu, Shuai Yi, Yeo, Chai Kiat, Chen Change Loy
Format: Article
Language:English
Subjects:
Cameras
Datasets
Heuristic methods
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Cai, Zhongang
Zhang, Junzhe
Ren, Daxuan
Yu, Cunjun
Zhao, Haiyu
Shuai Yi
Yeo, Chai Kiat
Chen Change Loy
description We present an interesting and challenging dataset that features a large number of scenes with messy tables captured from multiple camera views. Each scene in this dataset is highly complex, containing multiple object instances that could be identical, stacked and occluded by other instances. The key challenge is to associate all instances given the RGB image of all views. The seemingly simple task surprisingly fails many popular methods or heuristics that we assume good performance in object association. The dataset challenges existing methods in mining subtle appearance differences, reasoning based on contexts, and fusing appearance with geometric cues for establishing an association. We report interesting findings with some popular baselines, and discuss how this dataset could help inspire new problems and catalyse more robust formulations to tackle real-world instance association problems. Project page: \(\href{https://caizhongang.github.io/projects/MessyTable/}{\text{MessyTable}}\)
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2428813716</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2428813716</sourcerecordid><originalsourceid>FETCH-proquest_journals_24288137163</originalsourceid><addsrcrecordid>eNqNyr0KwjAUQOEgCBbtOwScC-lNf6KbFEWHbsW1xHKFlJjU3BTx7XXwAZzO8J0FS0DKPFMFwIqlRKMQAqoaylImbNci0bvTN4t7fnEUtRuQH4j8YHQ03nHjeDvbaCaLvNEPDJpfDb5ow5Z3bQnTX9dsezp2zTmbgn_OSLEf_Rzcl3ooQKlc1nkl_7s-ZdM2MQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2428813716</pqid></control><display><type>article</type><title>MessyTable: Instance Association in Multiple Camera Views</title><source>Publicly Available Content Database</source><creator>Cai, Zhongang ; Zhang, Junzhe ; Ren, Daxuan ; Yu, Cunjun ; Zhao, Haiyu ; Shuai Yi ; Yeo, Chai Kiat ; Chen Change Loy</creator><creatorcontrib>Cai, Zhongang ; Zhang, Junzhe ; Ren, Daxuan ; Yu, Cunjun ; Zhao, Haiyu ; Shuai Yi ; Yeo, Chai Kiat ; Chen Change Loy</creatorcontrib><description>We present an interesting and challenging dataset that features a large number of scenes with messy tables captured from multiple camera views. Each scene in this dataset is highly complex, containing multiple object instances that could be identical, stacked and occluded by other instances. The key challenge is to associate all instances given the RGB image of all views. The seemingly simple task surprisingly fails many popular methods or heuristics that we assume good performance in object association. The dataset challenges existing methods in mining subtle appearance differences, reasoning based on contexts, and fusing appearance with geometric cues for establishing an association. We report interesting findings with some popular baselines, and discuss how this dataset could help inspire new problems and catalyse more robust formulations to tackle real-world instance association problems. Project page: \(\href{https://caizhongang.github.io/projects/MessyTable/}{\text{MessyTable}}\)</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Cameras ; Datasets ; Heuristic methods</subject><ispartof>arXiv.org, 2020-07</ispartof><rights>2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2428813716?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Cai, Zhongang</creatorcontrib><creatorcontrib>Zhang, Junzhe</creatorcontrib><creatorcontrib>Ren, Daxuan</creatorcontrib><creatorcontrib>Yu, Cunjun</creatorcontrib><creatorcontrib>Zhao, Haiyu</creatorcontrib><creatorcontrib>Shuai Yi</creatorcontrib><creatorcontrib>Yeo, Chai Kiat</creatorcontrib><creatorcontrib>Chen Change Loy</creatorcontrib><title>MessyTable: Instance Association in Multiple Camera Views</title><title>arXiv.org</title><description>We present an interesting and challenging dataset that features a large number of scenes with messy tables captured from multiple camera views. Each scene in this dataset is highly complex, containing multiple object instances that could be identical, stacked and occluded by other instances. The key challenge is to associate all instances given the RGB image of all views. The seemingly simple task surprisingly fails many popular methods or heuristics that we assume good performance in object association. The dataset challenges existing methods in mining subtle appearance differences, reasoning based on contexts, and fusing appearance with geometric cues for establishing an association. We report interesting findings with some popular baselines, and discuss how this dataset could help inspire new problems and catalyse more robust formulations to tackle real-world instance association problems. Project page: \(\href{https://caizhongang.github.io/projects/MessyTable/}{\text{MessyTable}}\)</description><subject>Cameras</subject><subject>Datasets</subject><subject>Heuristic methods</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNyr0KwjAUQOEgCBbtOwScC-lNf6KbFEWHbsW1xHKFlJjU3BTx7XXwAZzO8J0FS0DKPFMFwIqlRKMQAqoaylImbNci0bvTN4t7fnEUtRuQH4j8YHQ03nHjeDvbaCaLvNEPDJpfDb5ow5Z3bQnTX9dsezp2zTmbgn_OSLEf_Rzcl3ooQKlc1nkl_7s-ZdM2MQ</recordid><startdate>20200729</startdate><enddate>20200729</enddate><creator>Cai, Zhongang</creator><creator>Zhang, Junzhe</creator><creator>Ren, Daxuan</creator><creator>Yu, Cunjun</creator><creator>Zhao, Haiyu</creator><creator>Shuai Yi</creator><creator>Yeo, Chai Kiat</creator><creator>Chen Change Loy</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20200729</creationdate><title>MessyTable: Instance Association in Multiple Camera Views</title><author>Cai, Zhongang ; Zhang, Junzhe ; Ren, Daxuan ; Yu, Cunjun ; Zhao, Haiyu ; Shuai Yi ; Yeo, Chai Kiat ; Chen Change Loy</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24288137163</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Cameras</topic><topic>Datasets</topic><topic>Heuristic methods</topic><toplevel>online_resources</toplevel><creatorcontrib>Cai, Zhongang</creatorcontrib><creatorcontrib>Zhang, Junzhe</creatorcontrib><creatorcontrib>Ren, Daxuan</creatorcontrib><creatorcontrib>Yu, Cunjun</creatorcontrib><creatorcontrib>Zhao, Haiyu</creatorcontrib><creatorcontrib>Shuai Yi</creatorcontrib><creatorcontrib>Yeo, Chai Kiat</creatorcontrib><creatorcontrib>Chen Change Loy</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Cai, Zhongang</au><au>Zhang, Junzhe</au><au>Ren, Daxuan</au><au>Yu, Cunjun</au><au>Zhao, Haiyu</au><au>Shuai Yi</au><au>Yeo, Chai Kiat</au><au>Chen Change Loy</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>MessyTable: Instance Association in Multiple Camera Views</atitle><jtitle>arXiv.org</jtitle><date>2020-07-29</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>We present an interesting and challenging dataset that features a large number of scenes with messy tables captured from multiple camera views. Each scene in this dataset is highly complex, containing multiple object instances that could be identical, stacked and occluded by other instances. The key challenge is to associate all instances given the RGB image of all views. The seemingly simple task surprisingly fails many popular methods or heuristics that we assume good performance in object association. The dataset challenges existing methods in mining subtle appearance differences, reasoning based on contexts, and fusing appearance with geometric cues for establishing an association. We report interesting findings with some popular baselines, and discuss how this dataset could help inspire new problems and catalyse more robust formulations to tackle real-world instance association problems. Project page: \(\href{https://caizhongang.github.io/projects/MessyTable/}{\text{MessyTable}}\)</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2020-07
issn 2331-8422
language eng
recordid cdi_proquest_journals_2428813716
source Publicly Available Content Database
subjects Cameras
Datasets
Heuristic methods
title MessyTable: Instance Association in Multiple Camera Views
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T05%3A36%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=MessyTable:%20Instance%20Association%20in%20Multiple%20Camera%20Views&rft.jtitle=arXiv.org&rft.au=Cai,%20Zhongang&rft.date=2020-07-29&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2428813716%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_24288137163%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2428813716&rft_id=info:pmid/&rfr_iscdi=true