{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T21:00:27Z","timestamp":1773954027185,"version":"3.50.1"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1109\/tvcg.2021.3114794","type":"journal-article","created":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T17:37:32Z","timestamp":1632937052000},"page":"802-812","source":"Crossref","is-referenced-by-count":78,"title":["M2Lens: Visualizing and Explaining Multimodal Models for Sentiment Analysis"],"prefix":"10.1109","volume":"28","author":[{"given":"Xingbo","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology, United States"}]},{"given":"Jianben","family":"He","sequence":"additional","affiliation":[{"name":"University of Science and Technology, United States"}]},{"given":"Zhihua","family":"Jin","sequence":"additional","affiliation":[{"name":"University of Science and Technology, United States"}]},{"given":"Muqiao","family":"Yang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, United States"}]},{"given":"Yong","family":"Wang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, United States"}]},{"given":"Huamin","family":"Qu","sequence":"additional","affiliation":[{"name":"University of Science and Technology, United States"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376726"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019301"},{"key":"ref71","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.143"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref77","first-page":"5634","article-title":"Memory fusion network for multi-view sequential learning","volume":"32","author":"zadeh","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2934619"},{"key":"ref39","author":"molnar","year":"2019","journal-title":"Interpretable Machine Learning"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-005-7880-9"},{"key":"ref38","first-page":"4765","article-title":"A unified approach to interpreting model predictions","author":"lundberg","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref78","first-page":"5642","article-title":"Multi-attention recurrent network for human communication comprehension","volume":"32","author":"zadeh","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref79","first-page":"2236","article-title":"Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph","author":"zadeh","year":"0","journal-title":"Proceedings annual meeting of the Association for Computational Linguistics"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2467622"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858529"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2014.2346482"},{"key":"ref30","article-title":"Increasing the interpretability of recurrent neural networks using hidden markov models","author":"krakovna","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57321-8_1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2678025.2701399"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366127"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881970-018"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref63","article-title":"Direct-manipulation visualization of deep networks","author":"smilkov","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref28","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","author":"koh","year":"0","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.08.003"},{"key":"ref27","article-title":"Visualizing and understanding recurrent networks","author":"karpathy","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref65","article-title":"Striving for simplicity: The all convolutional net","author":"springenberg","year":"0","journal-title":"International Conference on Learning Representations (Workshop Track)"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2744158"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2008.117"},{"key":"ref67","first-page":"3319","article-title":"Axiomatic attribution for deep networks","author":"sundararajan","year":"0","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098039"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702509"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2934262"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-27857-5_77"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-014-0368-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219853"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2843369"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2744718"},{"key":"ref25","first-page":"295","article-title":"Accuracy vs. comprehensibility in data mining models","volume":"1","author":"johansson","year":"2004","journal-title":"Information Fusion"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_21"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2501988.2501993"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00349"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2007.190734"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.442"},{"key":"ref55","first-page":"1527","article-title":"Anchors: High-precision model-agnostic explanations","volume":"32","author":"ribeiro","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2016.2598828"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24571-8_51"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8080832"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136801"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070509"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2307\/2284077"},{"key":"ref13","first-page":"960","article-title":"COVAREP-A collaborative voice analysis repository for speech technologies","author":"degottex","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref14","author":"ekman","year":"1997","journal-title":"What the Face Reveals Basic and Applied Studies of Spontaneous Expression using the Facial Action Coding System (FACS)"},{"key":"ref15","author":"friesen","year":"1978","journal-title":"Facial Action Coding System A Technique for the Measurement of Facial Movement"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.52"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-3019"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2934656"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24571-8_47"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.78"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2864499"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1023\/B:DAMI.0000005258.31418.83"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2963659"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2744683"},{"key":"ref5","article-title":"Interpretability via model extraction","author":"bastani","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/VAST.2015.7347637"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"1306","DOI":"10.1109\/JPROC.2003.817150","article-title":"Recent advances in the automatic recognition of audiovisual speech","volume":"91","author":"potamianos","year":"0","journal-title":"Proceedings of the IEEE"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/VAST47406.2019.8986948"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993176"},{"key":"ref41","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"0","journal-title":"Proceedings of the 28th International Conference on Machine Learning"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1357054.1357160"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00007"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/2945\/9663056\/09552921.pdf?arnumber=9552921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T05:47:38Z","timestamp":1769492858000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9552921\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1]]},"references-count":83,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2021.3114794","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1]]}}}