{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:51:28Z","timestamp":1755802288886,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658090","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"404-413","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Context or Clutter? Efficiently Matching Objects Across Scenes"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0181-700X","authenticated-orcid":false,"given":"Albatool","family":"Wazzan","sequence":"first","affiliation":[{"name":"Dept. of Computer & Info Sciences, Temple University, Philadelphia, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9043-8035","authenticated-orcid":false,"given":"Imtiaz","family":"Ahmad","sequence":"additional","affiliation":[{"name":"Dept. of Computer & Info Sciences, Temple University, Philadelphia, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2781-6619","authenticated-orcid":false,"given":"Stephen","family":"Macneil","sequence":"additional","affiliation":[{"name":"Dept. of Computer & Info Sciences, Temple University, Philadelphia, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6066-0946","authenticated-orcid":false,"given":"Richard","family":"Souvenir","sequence":"additional","affiliation":[{"name":"Dept. of Computer & Info Sciences, Temple University, Philadelphia, PA, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2011.12.004"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.21236\/ADA478319"},{"volume-title":"Thematic analysis","author":"Braun Virginia","key":"e_1_3_2_1_3_1","unstructured":"Virginia Braun and Victoria Clarke. 2012. Thematic analysis. American Psychological Association, Washington, DC."},{"key":"e_1_3_2_1_4_1","unstructured":"Justin Brooks. 2019. COCO Annotator. https:\/\/github.com\/jsbroks\/coco-annotator\/."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2016.7498955"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350535"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1167\/11.5.14"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Lex Fridman and Bryan Reimer. 2016. Semi-Automated Annotation of Discrete States in Large Video Datasets. https:\/\/doi.org\/10.48550\/ARXIV.1612.01035","DOI":"10.48550\/ARXIV.1612.01035"},{"key":"e_1_3_2_1_10_1","volume-title":"Caltech-256 object category dataset. CaltechDATA","author":"Griffin Gregory","year":"2007","unstructured":"Gregory Griffin, Alex Holub, and Pietro Perona. 2007. Caltech-256 object category dataset. CaltechDATA (2007)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025984"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2013.0067"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/VLHCC.2015.7356972"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1057\/ivs.2009.10"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2675133.2675207"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijinfomgt.2012.04.006"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/1087018"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00182"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047202"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1086\/209181"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_33"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2049843"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9797"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526114.3558627"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00071"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1192\/bjp.130.1.79"},{"key":"e_1_3_2_1_27_1","unstructured":"Commercial Software Engineering (CSE) Microsoft. 2017. Visual Object Tagging Tool: An electron app for building end to end Object Detection Models from Images and Videos. https:\/\/github.com\/microsoft\/VoTT"},{"volume-title":"Columbia Object Image Library (COIL100)","author":"Nayar Sheila J.","key":"e_1_3_2_1_28_1","unstructured":"Sheila J. Nayar. 1996. Columbia Object Image Library (COIL100). In Columbia Object Image Library (COIL100). Center for Research on Intelligent Systems at the Department of Computer Science, Columbia University, New York, USA, 0."},{"volume-title":"Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems","author":"Palani Srishti","key":"e_1_3_2_1_29_1","unstructured":"Srishti Palani, Zijian Ding, Austin Nguyen, Andrew Chuang, Stephen MacNeil, and Steven P. Dow. 2021. CoNotate: Suggesting Queries Based on Notes Promotes Knowledge Discovery. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems (Yokohama, Japan) (CHI '21). Association for Computing Machinery, New York, NY, USA, Article 726, bibinfonumpages14 pages."},{"key":"e_1_3_2_1_30_1","volume-title":"Ozan Oktay, Konstantinos Kamnitsas, Jonathan Passerat-Palmbach, Wenjia Bai, Mellisa Damodaram, Mary A Rutherford, Joseph V Hajnal","author":"Rajchl Martin","year":"2016","unstructured":"Martin Rajchl, Matthew CH Lee, Ozan Oktay, Konstantinos Kamnitsas, Jonathan Passerat-Palmbach, Wenjia Bai, Mellisa Damodaram, Mary A Rutherford, Joseph V Hajnal, Bernhard Kainz, et al. 2016. Deepcut: Object segmentation from bounding box annotations using convolutional neural networks. IEEE transactions on medical imaging , Vol. 36, 2 (2016), 674--683."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1518933"},{"key":"e_1_3_2_1_32_1","volume-title":"ACM transactions on graphics (TOG)","author":"Rother Carsten","year":"2004","unstructured":"Carsten Rother, Vladimir Kolmogorov, and Andrew Blake. 2004. \" GrabCut\" interactive foreground extraction using iterated graph cuts. ACM transactions on graphics (TOG) , Vol. 23, 3 (2004), 309--314."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298824"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0090-8"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.83.5.1178"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2006.06.007"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301726"},{"key":"e_1_3_2_1_38_1","volume-title":"A general inductive approach for analyzing qualitative evaluation data. American journal of evaluation","author":"Thomas David R","year":"2006","unstructured":"David R Thomas. 2006. A general inductive approach for analyzing qualitative evaluation data. American journal of evaluation , Vol. 27, 2 (2006), 237--246."},{"key":"e_1_3_2_1_39_1","unstructured":"Maxim Tkachenko Mikhail Malyuk Andrey Holmanyuk and Nikolai Liubimov. 2020--2022. Label Studio: Data labeling software. https:\/\/github.com\/heartexlabs\/label-studio Open source software available from https:\/\/github.com\/heartexlabs\/label-studio."},{"key":"e_1_3_2_1_40_1","unstructured":"Tzutalin. 2015. LabelImg. Git code. https:\/\/github.com\/tzutalin\/labelImg"},{"key":"e_1_3_2_1_41_1","unstructured":"Johanna Vompras and Stefan Conrad. 2005. A semi-automated Framework for Supporting Semantic Image Annotation.. In SemAnnot@ ISWC. In SemAnnot@ ISWC Galway Ireland 0--0."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474055"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447875"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.40"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021--85605--8"},{"key":"e_1_3_2_1_46_1","first-page":"7","article-title":"Don't Get Lost in the Crowd: Best Practices for Using Amazon's Mechanical Turk in Behavioral Research","volume":"2019","author":"Young Jacob","year":"2019","unstructured":"Jacob Young and Kristie M. Young. 2019. Don't Get Lost in the Crowd: Best Practices for Using Amazon's Mechanical Turk in Behavioral Research. Journal of the Midwest Association for Information Systems , Vol. 2019 (2019), 7--34.","journal-title":"Journal of the Midwest Association for Information Systems"},{"key":"e_1_3_2_1_47_1","volume-title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop. CoRR","author":"Yu Fisher","year":"2015","unstructured":"Fisher Yu, Yinda Zhang, Shuran Song, Ari Seff, and Jianxiong Xiao. 2015. LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop. CoRR , Vol. abs\/1506.03365 (2015). showeprint[arXiv]1506.03365"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1108\/LHT-11-2019-0237"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","unstructured":"Bolei Zhou Hang Zhao Xavier Puig Tete Xiao Sanja Fidler Adela Barriuso and Antonio Torralba. 2016. Semantic Understanding of Scenes through the ADE20K Dataset. https:\/\/doi.org\/10.48550\/ARXIV.1608.05442","DOI":"10.48550\/ARXIV.1608.05442"}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"Phuket Thailand","acronym":"ICMR '24"},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658090","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:45:42Z","timestamp":1755765942000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658090"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":49,"alternative-id":["10.1145\/3652583.3658090","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658090","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}