{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T21:55:38Z","timestamp":1770414938635,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,10,15]],"date-time":"2018-10-15T00:00:00Z","timestamp":1539561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"State Key Development Program","award":["2018YFC0830103"],"award-info":[{"award-number":["2018YFC0830103"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,10,15]]},"DOI":"10.1145\/3240508.3240660","type":"proceedings-article","created":{"date-parts":[[2018,10,18]],"date-time":"2018-10-18T17:52:08Z","timestamp":1539885128000},"page":"1527-1535","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":41,"title":["Adaptive Temporal Encoding Network for Video Instance-level Human Parsing"],"prefix":"10.1145","author":[{"given":"Qixian","family":"Zhou","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, GuangZhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Gong","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, GuangZhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, GuangZhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Michal Irani Alon Faktor. 2014. Video segmentation by non-local consensus voting. In BMVC .  Michal Irani Alon Faktor. 2014. Video segmentation by non-local consensus voting. In BMVC ."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_26"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/1888150.1888173"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00757"},{"key":"e_1_3_2_1_5_1","volume-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. arXiv preprint arXiv:1606.00915","author":"Chen Liang-Chieh","year":"2016"},{"key":"e_1_3_2_1_6_1","unstructured":"Liang-Chieh Chen George Papandreou Florian Schroff and Hartwig Adam. 2017. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017).  Liang-Chieh Chen George Papandreou Florian Schroff and Hartwig Adam. 2017. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Liang-Chieh Chen Yi Yang Jiang Wang Wei Xu and Alan L Yuille. 2016b. Attention to Scale: Scale-aware Semantic Image Segmentation. In CVPR .  Liang-Chieh Chen Yi Yang Jiang Wang Wei Xu and Alan L Yuille. 2016b. Attention to Scale: Scale-aware Semantic Image Segmentation. In CVPR .","DOI":"10.1109\/CVPR.2016.396"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Liang Chieh Chen Yukun Zhu George Papandreou Florian Schroff and Hartwig Adam. 2018. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. (2018).  Liang Chieh Chen Yukun Zhu George Papandreou Florian Schroff and Hartwig Adam. 2018. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. (2018).","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"e_1_3_2_1_10_1","unstructured":"Kyunghyun Cho Bart Van Merrienboer Caglar Gulcehre Dzmitry Bahdanau Fethi Bougares Holger Schwenk and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. Computer Science (2014).  Kyunghyun Cho Bart Van Merrienboer Caglar Gulcehre Dzmitry Bahdanau Fethi Bougares Holger Schwenk and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. Computer Science (2014)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"e_1_3_2_1_12_1","unstructured":"Chuang Gan Ming Lin Yi Yang Gerard de Melo and Alexander G Hauptmann. 2016. Concepts not alone: Exploring pairwise relationships for zero-shot video activity recognition. In AAAI .   Chuang Gan Ming Lin Yi Yang Gerard de Melo and Alexander G Hauptmann. 2016. Concepts not alone: Exploring pairwise relationships for zero-shot video activity recognition. In AAAI ."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Ke Gong Xiaodan Liang Dongyu Zhang Xiaohui Shen and Liang Lin. 2017. Look Into Person: Self-Supervised Structure-Sensitive Learning and a New Benchmark for Human Parsing. In CVPR .  Ke Gong Xiaodan Liang Dongyu Zhang Xiaohui Shen and Liang Lin. 2017. Look Into Person: Self-Supervised Structure-Sensitive Learning and a New Benchmark for Human Parsing. In CVPR .","DOI":"10.1109\/CVPR.2017.715"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00946"},{"key":"e_1_3_2_1_15_1","unstructured":"Kaiming He Georgia Gkioxari Piotr Dollar and Ross Girshick. 2017. Mask R-CNN. In ICCV .  Kaiming He Georgia Gkioxari Piotr Dollar and Ross Girshick. 2017. Mask R-CNN. In ICCV ."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"e_1_3_2_1_17_1","volume-title":"Video Scene Parsing with Predictive Feature Learning. In IEEE International Conference on Computer Vision. 5581--5589","author":"Jin Xiaojie","year":"2017"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.374"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2759508"},{"key":"e_1_3_2_1_20_1","unstructured":"Jianan Li Xiaodan Liang Yunchao Wei Tingfa Xu Jiashi Feng and Shuicheng Yan. 2017b. Perceptual generative adversarial networks for small object detection. In IEEE CVPR .  Jianan Li Xiaodan Liang Yunchao Wei Tingfa Xu Jiashi Feng and Shuicheng Yan. 2017b. Perceptual generative adversarial networks for small object detection. In IEEE CVPR ."},{"key":"e_1_3_2_1_21_1","unstructured":"Qizhu Li Anurag Arnab and Philip HS Torr. 2017a. Holistic Instance-Level Human Parsing. arXiv preprint arXiv:1709.03612 (2017).  Qizhu Li Anurag Arnab and Philip HS Torr. 2017a. Holistic Instance-Level Human Parsing. arXiv preprint arXiv:1709.03612 (2017)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Xiaodan Liang Ke Gong Xiaohui Shen and Liang Lin. 2018a. Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence (2018).  Xiaodan Liang Ke Gong Xiaohui Shen and Liang Lin. 2018a. Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence (2018).","DOI":"10.1109\/TPAMI.2018.2820063"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.194"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.469"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.234"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2408360"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.347"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.75"},{"key":"e_1_3_2_1_29_1","unstructured":"Xiaodan Liang Yunchao Wei Xiaohui Shen Jianchao Yang Liang Lin and Shuicheng Yan. 2015b. Proposal-free network for instance-level object segmentation. arXiv preprint arXiv:1509.02636 (2015).  Xiaodan Liang Yunchao Wei Xiaohui Shen Jianchao Yang Liang Lin and Shuicheng Yan. 2015b. Proposal-free network for instance-level object segmentation. arXiv preprint arXiv:1509.02636 (2015)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.163"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00085"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Si Liu Xiaodan Liang Luoqi Liu Xiaohui Shen Jianchao Yang Changsheng Xu Liang Lin Xiaochun Cao and Shuicheng Yan. 2015. Matching-CNN Meets KNN: Quasi-Parametric Human Parsing. In CVPR .  Si Liu Xiaodan Liang Luoqi Liu Xiaohui Shen Jianchao Yang Changsheng Xu Liang Lin Xiaochun Cao and Shuicheng Yan. 2015. Matching-CNN Meets KNN: Quasi-Parametric Human Parsing. In CVPR .","DOI":"10.1109\/CVPR.2015.7298748"},{"key":"e_1_3_2_1_33_1","volume-title":"Surveillance Video Parsing with Single Frame Supervision. In IEEE Conference on Computer Vision and Pattern Recognition. 1013--1021","author":"Liu Si","year":"2017"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Jonathan Long Evan Shelhamer and Trevor Darrell. 2015. Fully convolutional networks for semantic segmentation. In CVPR .  Jonathan Long Evan Shelhamer and Trevor Darrell. 2015. Fully convolutional networks for semantic segmentation. In CVPR .","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.223"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Evan Shelhamer Kate Rakelly Judy Hoffman and Trevor Darrell. 2016. Clockwork Convnets for Video Semantic Segmentation .Springer International Publishing. 852--868 pages.  Evan Shelhamer Kate Rakelly Judy Hoffman and Trevor Darrell. 2016. Clockwork Convnets for Video Semantic Segmentation .Springer International Publishing. 852--868 pages.","DOI":"10.1007\/978-3-319-49409-8_69"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Edgar Simo-Serra Sanja Fidler Francesc Moreno-Noguer and Raquel Urtasun. 2014. A High Performance CRF Model for Clothes Parsing. In ACCV .  Edgar Simo-Serra Sanja Fidler Francesc Moreno-Noguer and Raquel Urtasun. 2014. A High Performance CRF Model for Clothes Parsing. In ACCV .","DOI":"10.1007\/978-3-319-16811-1_5"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995364"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299055"},{"key":"e_1_3_2_1_41_1","volume-title":"Learning Motion Patterns in Videos. In IEEE Conference on Computer Vision and Pattern Recognition. 531--539","author":"Tokmakov Pavel","year":"2017"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Pavel Tokmakov Karteek Alahari and Cordelia Schmid. 2017b. Learning Video Object Segmentation with Visual Memory. (2017) 4491--4500.  Pavel Tokmakov Karteek Alahari and Cordelia Schmid. 2017b. Learning Video Object Segmentation with Visual Memory. (2017) 4491--4500.","DOI":"10.1109\/ICCV.2017.480"},{"key":"e_1_3_2_1_43_1","unstructured":"Lu Wang Xiaoli Ji Qingxu Deng and Mingxing Jia. 2014. Deformable part model based multiple pedestrian detection for video surveillance in crowded scenes. In VISAPP .  Lu Wang Xiaoli Ji Qingxu Deng and Mingxing Jia. 2014. Deformable part model based multiple pedestrian detection for video surveillance in crowded scenes. In VISAPP ."},{"key":"e_1_3_2_1_44_1","unstructured":"Fangting Xia Peng Wang Liang-Chieh Chen and Alan L Yuille. 2016. Zoom Better to See Clearer: Huamn Part Segmentation with Auto Zoom Net. In ECCV .  Fangting Xia Peng Wang Liang-Chieh Chen and Alan L Yuille. 2016. Zoom Better to See Clearer: Huamn Part Segmentation with Auto Zoom Net. In ECCV ."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.437"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"K. Yamaguchi M.H. Kiapour L.E. Ortiz and T.L. Berg. 2012. Parsing clothing in fashion photographs. In CVPR .   K. Yamaguchi M.H. Kiapour L.E. Ortiz and T.L. Berg. 2012. Parsing clothing in fashion photographs. In CVPR .","DOI":"10.1109\/CVPR.2012.6248101"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Yuan Yuan Xiaodan Liang Xiaolong Wang Dit Yan Yeung and Abhinav Gupta. 2017. Temporal dynamic graph LSTM for action-driven video object detection. arXiv preprint arXiv:1708.00666 (2017).  Yuan Yuan Xiaodan Liang Xiaolong Wang Dit Yan Yeung and Abhinav Gupta. 2017. Temporal dynamic graph LSTM for action-driven video object detection. arXiv preprint arXiv:1708.00666 (2017).","DOI":"10.1109\/ICCV.2017.200"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_28"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"},{"key":"e_1_3_2_1_50_1","volume-title":"Flow-Guided Feature Aggregation for Video Object Detection. In IEEE International Conference on Computer Vision. 408--417","author":"Zhu Xizhou","year":"2017"},{"key":"e_1_3_2_1_51_1","volume-title":"Deep Feature Flow for Video Recognition. In IEEE Conference on Computer Vision and Pattern Recognition. 4141--4150","author":"Zhu Xizhou","year":"2017"}],"event":{"name":"MM '18: ACM Multimedia Conference","location":"Seoul Republic of Korea","acronym":"MM '18","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 26th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3240508.3240660","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3240508.3240660","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:43:31Z","timestamp":1750207411000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3240508.3240660"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,15]]},"references-count":51,"alternative-id":["10.1145\/3240508.3240660","10.1145\/3240508"],"URL":"https:\/\/doi.org\/10.1145\/3240508.3240660","relation":{},"subject":[],"published":{"date-parts":[[2018,10,15]]},"assertion":[{"value":"2018-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}