{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T23:03:32Z","timestamp":1772147012063,"version":"3.50.1"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tpami.2020.3042192","type":"journal-article","created":{"date-parts":[[2020,12,3]],"date-time":"2020-12-03T21:05:53Z","timestamp":1607029553000},"page":"1-1","source":"Crossref","is-referenced-by-count":45,"title":["Auto-encoding and Distilling Scene Graphs for Image Captioning"],"prefix":"10.1109","author":[{"given":"Xu","family":"Yang","sequence":"first","affiliation":[]},{"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jianfei","family":"Cai","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00728"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2909864"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00435"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref7","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention,","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref9","article-title":"Sequence level training with recurrent neural networks,","author":"Ranzato","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00445"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref13","volume-title":"Vision: A Computational Investigation into the Human Representation and Processing of Visual Information","author":"Marr","year":"1982"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1017\/s0140525x16001837"},{"key":"ref15","article-title":"Relational inductive biases, deep learning, and graph networks,","author":"Battaglia","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1037"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1159"},{"key":"ref21","article-title":"Gated graph sequence neural networks,","author":"Li","year":"2016"},{"key":"ref22","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref26","first-page":"3630","article-title":"Matching networks for one shot learning,","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref27","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks,","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref31","first-page":"359","article-title":"Collective generation of natural image descriptions,","volume-title":"Proc. 50th Annu. Meeting Assoc. Comput. Linguist., Long Papers-Vol. 1","author":"Kuznetsova"},{"key":"ref32","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections,","volume-title":"Proc. 13th Conf. Eur. Chapter Assoc. Comput. Linguist.","author":"Mitchell"},{"key":"ref33","first-page":"220","article-title":"Composing simple image descriptions using web-scale n-grams,","volume-title":"Proc. 15th Conf. Comput. Natural Lang. Learn.","author":"Li"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","first-page":"3104","article-title":"Sequence to sequence learning with neural networks,","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00856"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref43","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks,","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Bengio"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12266"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_31"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00425"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01042"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00751"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00857"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.344"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00878"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_3"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00471"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2812"},{"key":"ref63","article-title":"Spectral networks and locally connected networks on graphs,","author":"Bruna","year":"2014"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157527"},{"key":"ref65","article-title":"Deep convolutional networks on graph-structured data,","author":"Henaff","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2010350"},{"key":"ref67","first-page":"1993","article-title":"Diffusion-convolutional neural networks,","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Atwood"},{"key":"ref68","first-page":"2014","article-title":"Learning convolutional neural networks for graphs,","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Niepert"},{"key":"ref69","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering,","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Xiong"},{"key":"ref70","first-page":"2440","article-title":"End-to-end memory networks,","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Sukhbaatar"},{"key":"ref71","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing,","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Kumar"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1147"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref74","article-title":"Compositional attention networks for machine reasoning,","author":"Hudson","year":"2018"},{"key":"ref75","article-title":"Distilling the knowledge in a neural network,","author":"Hinton","year":"2015"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref77","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer,","author":"Zagoruyko","year":"2017"},{"key":"ref78","article-title":"Model compression via distillation and quantization,","author":"Polino","year":"2018"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075150"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref85","article-title":"Adam: A method for stochastic optimization,","author":"Kingma","year":"2015"},{"key":"ref86","article-title":"Learning to count objects in natural images for visual question answering,","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref87","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding,","volume":"1","author":"Devlin","year":"2019"},{"key":"ref88","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Yosinski"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10475"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref92","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments,","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref93","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries,","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240632"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09279262.pdf?arnumber=9279262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:28:06Z","timestamp":1704842886000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9279262\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":94,"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.3042192","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}