{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T21:06:58Z","timestamp":1764882418580,"version":"3.46.0"},"reference-count":133,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tpami.2025.3613712","type":"journal-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:25:25Z","timestamp":1758648325000},"page":"792-806","source":"Crossref","is-referenced-by-count":0,"title":["Data-And Knowledge-Driven Visual Abductive Reasoning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8026-0843","authenticated-orcid":false,"given":"Chen","family":"Liang","sequence":"first","affiliation":[{"name":"CCAI, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0802-9567","authenticated-orcid":false,"given":"Wenguan","family":"Wang","sequence":"additional","affiliation":[{"name":"CCAI, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6468-5729","authenticated-orcid":false,"given":"Ling","family":"Chen","sequence":"additional","affiliation":[{"name":"DSKD Lab, Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"CCAI, Zhejiang University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Collected Papers of Charles Sanders Peirce","volume":"5","author":"Peirce","year":"1974"},{"volume-title":"Collected Papers of Charles Sanders Peirce","year":"1931","author":"Peirce","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780199734689.013.0014"},{"article-title":"Visual abduction in anthropology and archaeology","volume-title":"Proc. Systematic Methods Sci. Discov.: Papers 1995 Spring Symp.","author":"Shelley","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog2901_5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/11578.003.0023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1509"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-018-9801-4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/254"},{"article-title":"A topology of mind\u2013spiral thought patterns, the hyperlinking of text, ideas and more","year":"2022","author":"Logan","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/info9040083"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(03)00158-X"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.57.102904.190100"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/502"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01512"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.403"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401332"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.58"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.317"},{"key":"ref21","first-page":"2811","article-title":"Bridging machine learning and logical reasoning by abductive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref22","first-page":"26574","article-title":"Fast abductive learning by similarity-based consistency optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/250"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_32"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020346032608"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1084"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_29"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00674"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00675"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01109"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.29"},{"key":"ref40","first-page":"958","article-title":"Multi-modal dense video captioning","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshop","author":"Iashin"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146005"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00030"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00676"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.156"},{"article-title":"Text infilling","year":"2019","author":"Zhu","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1177\/107769905303000401"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-2405"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.226"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1589"},{"article-title":"Deep multi-scale video prediction beyond mean square error","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mathieu","key":"ref54"},{"key":"ref55","first-page":"613","article-title":"Generating videos with scene dynamics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vondrick"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.18"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01242"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_15"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_45"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00560"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00036"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.494"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.573"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.497"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.110"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01104"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.706"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_30"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00472"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00683"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.2100463"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3483273"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2400250"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_20"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref79","first-page":"5754","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref80","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref81","first-page":"4648","article-title":"Rethinking positional encoding in language pre-training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ke"},{"key":"ref82","first-page":"16857","article-title":"MPNet: Masked and permuted pre-training for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.298"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.237"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"ref86","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chu"},{"key":"ref87","first-page":"18241","article-title":"SalKG: Learning from knowledge graph explanations for commonsense reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chan"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.45"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6364"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_34"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00207"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20174"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01389"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.567"},{"key":"ref96","first-page":"5498","article-title":"A semantic loss function for deep learning with symbolic knowledge","volume-title":"Proc. ACM Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.263"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6630"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-1765(01)00524-9"},{"key":"ref101","first-page":"4356","article-title":"Man is to computer programmer as woman is to homemaker? Debiasing word embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bolukbasi"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00742"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01537"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00788"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00783"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20052"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3121705"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01751"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","key":"ref110"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.44"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.517"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00501"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","key":"ref118"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"Oord","key":"ref119"},{"key":"ref120","first-page":"247","article-title":"Learning discriminative projections for text similarity measures","volume-title":"Proc. Conf. Comput. Natural Lang. Learn.","author":"Yih"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref124","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bengio"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","key":"ref127"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref130","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"Banerjee"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.3115\/1118162.1118168"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_23"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11275622\/11176987.pdf?arnumber=11176987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T21:01:33Z","timestamp":1764882093000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11176987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":133,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3613712","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}