{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:19:50Z","timestamp":1755926390127,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Key Research Program of Frontier Sciences of the Chinese Academy of Sciences","award":["QYZDJ-SSW-SYS013"],"award-info":[{"award-number":["QYZDJ-SSW-SYS013"]}]},{"name":"National Natural Science Foundation of China","award":["61472389,61771457,61732007,61572503,61872424,61620106009,U1636214,61836002"],"award-info":[{"award-number":["61472389,61771457,61732007,61572503,61872424,61620106009,U1636214,61836002"]}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["61772494,61836002"],"award-info":[{"award-number":["61772494,61836002"]}],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1522125"],"award-info":[{"award-number":["IIS-1522125"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3351089","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"512-520","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Training Efficient Saliency Prediction Models with Knowledge Distillation"],"prefix":"10.1145","author":[{"given":"Peng","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Li","family":"Su","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences & Institute of Computing Technology, Beijing, China"}]},{"given":"Liang","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Beijing, China"}]},{"given":"BingKun","family":"Bao","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}]},{"given":"Pamela","family":"Cosman","sequence":"additional","affiliation":[{"name":"University of California, San Diego, San Diego, CA, USA"}]},{"given":"GuoRong","family":"Li","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences & Institute of Computing Technology, Beijing, China"}]},{"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences & Institute of Computing Technology, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126712"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2018.2821566"},{"key":"e_1_3_2_1_3_1","volume-title":"Paying more attention to saliency: Image captioning with saliency and context attention. ACMTransactions on Multimedia Computing, Communications, and Applications (TOMM), 14(2):48:1-- 48:21","author":"Cornia M.","year":"2018","unstructured":"M. Cornia , L. Baraldi , G. Serra , and R. Cucchiara . Paying more attention to saliency: Image captioning with saliency and context attention. ACMTransactions on Multimedia Computing, Communications, and Applications (TOMM), 14(2):48:1-- 48:21 , 2018 . M. Cornia, L. Baraldi, G. Serra, and R. Cucchiara. Paying more attention to saliency: Image captioning with saliency and context attention. ACMTransactions on Multimedia Computing, Communications, and Applications (TOMM), 14(2):48:1-- 48:21, 2018."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240632"},{"key":"e_1_3_2_1_5_1","first-page":"22","volume-title":"ACM Multimedia Conference on Multimedia Conference","author":"Xu K.","year":"2018","unstructured":"K. Xu , L.Y. Wen , G.R. Li , L.F. Bo , and Q.M. Huang . Attentive recurrent neural network weak-supervised multi-label image classification . In ACM Multimedia Conference on Multimedia Conference , pages 22 -- 28 , 2018 . K. Xu, L.Y. Wen, G.R. Li, L.F. Bo, and Q.M. Huang. Attentive recurrent neural network weak-supervised multi-label image classification. In ACM Multimedia Conference on Multimedia Conference, pages 22--28, 2018."},{"key":"e_1_3_2_1_6_1","volume-title":"Task-driven visual saliency and attention-based visual question answering. CoRR, abs\/1702.06700","author":"Lin Y.T.","year":"2017","unstructured":"Y.T. Lin , Z.Y. Pang , D.H. Wang , and Y.T. Zhuang . Task-driven visual saliency and attention-based visual question answering. CoRR, abs\/1702.06700 , 2017 . Y.T. Lin, Z.Y. Pang, D.H. Wang, and Y.T. Zhuang. Task-driven visual saliency and attention-based visual question answering. CoRR, abs\/1702.06700, 2017."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396290"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2199126"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2071935"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123319"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2730889"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00147"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240677"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2018.8499257"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967242"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126714"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240571"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967250"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072041"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2815688"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/95"},{"key":"e_1_3_2_1_24_1","volume-title":"ICLR","author":"Simonyan K.","year":"2015","unstructured":"K. Simonyan and A. Zisserman . Very deep convolutional networks for large-scale image recognition . In ICLR , 2015 . K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. In ICLR, 2015."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.776"},{"key":"e_1_3_2_1_26_1","volume-title":"teacher we trust: Learning compressed models for pedestrian detection. CoRR, abs\/1612.00478","author":"Shen J.","year":"2016","unstructured":"J. Shen , N. Vesdapunt , V.N. Boddeti , and K.M. Kitani . In teacher we trust: Learning compressed models for pedestrian detection. CoRR, abs\/1612.00478 , 2016 . J. Shen, N. Vesdapunt, V.N. Boddeti, and K.M. Kitani. In teacher we trust: Learning compressed models for pedestrian detection. CoRR, abs\/1612.00478, 2016."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2487833"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298731"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.698"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.32"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00403"},{"key":"e_1_3_2_1_32_1","article-title":"Learning coupled convolutional networks fusion for video saliency prediction. In","volume":"2018","author":"Wu Z.","unstructured":"Z. Wu , L. Su , and Q.M. Huang . Learning coupled convolutional networks fusion for video saliency prediction. In IEEE Transactions on Circuits and Systems for Video Technology, page Early Access DOI: 10.1109\/TCSVT, 2018 . 10.1109\/TCSVT Z. Wu, L. Su, and Q.M. Huang. Learning coupled convolutional networks fusion for video saliency prediction. In IEEE Transactions on Circuits and Systems for Video Technology, page Early Access DOI: 10.1109\/TCSVT, 2018.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology, page Early Access"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_15"},{"key":"e_1_3_2_1_34_1","volume-title":"Distilling the knowledge in a neural network. CoRR, abs\/1503.02531","author":"Hinton G.E.","year":"2015","unstructured":"G.E. Hinton , O. Vinyals , and J. Dean . Distilling the knowledge in a neural network. CoRR, abs\/1503.02531 , 2015 . G.E. Hinton, O. Vinyals, and J. Dean. Distilling the knowledge in a neural network. CoRR, abs\/1503.02531, 2015."},{"key":"e_1_3_2_1_35_1","volume-title":"ICLR","author":"Romero A.","year":"2015","unstructured":"A. Romero , N. Ballas , S.E. Kahou , A. Chassang , C. Gatta , and Y. Bengio . Fitnets: Hints for thin deep nets . In ICLR , 2015 . A. Romero, N. Ballas, S.E. Kahou, A. Chassang, C. Gatta, and Y. Bengio. Fitnets: Hints for thin deep nets. In ICLR, 2015."},{"key":"e_1_3_2_1_36_1","volume-title":"ICLR","author":"Zagoruyko S.","year":"2017","unstructured":"S. Zagoruyko and N. Komodakis . Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer . In ICLR , 2017 . S. Zagoruyko and N. Komodakis. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. In ICLR, 2017."},{"key":"e_1_3_2_1_37_1","volume-title":"ICLR","author":"Yu F.","year":"2016","unstructured":"F. Yu and V. Koltun . Multi-scale context aggregation by dilated convolutions . In ICLR , 2016 . F. Yu and V. Koltun. Multi-scale context aggregation by dilated convolutions. In ICLR, 2016."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-54345-0_3"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2465960"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2602079"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.43"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.407"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.31"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240667"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"e_1_3_2_1_48_1","first-page":"311","volume-title":"ACL","author":"Papineni K.","year":"2002","unstructured":"K. Papineni , S. Roukos , T. Ward , and W.J. Zhu . Bleu: a method for automatic evaluation of machine translation . In ACL , pages 311 -- 318 , 2002 . K. Papineni, S. Roukos, T. Ward, and W.J. Zhu. Bleu: a method for automatic evaluation of machine translation. In ACL, pages 311--318, 2002."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123420"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Nice France","acronym":"MM '19"},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351089","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3351089","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3351089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:12Z","timestamp":1750201992000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351089"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":50,"alternative-id":["10.1145\/3343031.3351089","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3351089","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}