{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:18:21Z","timestamp":1783095501270,"version":"3.54.6"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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":[[2025,9]]},"DOI":"10.1109\/tpami.2025.3574322","type":"journal-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T13:15:53Z","timestamp":1748351753000},"page":"7689-7703","source":"Crossref","is-referenced-by-count":5,"title":["Compositional Physical Reasoning of Objects and Events From Videos"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1619-932X","authenticated-orcid":false,"given":"Zhenfang","family":"Chen","sequence":"first","affiliation":[{"name":"MIT-IBM Watson AI Lab, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shilong","family":"Dong","sequence":"additional","affiliation":[{"name":"New York University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kexin","family":"Yi","sequence":"additional","affiliation":[{"name":"Harvard University, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunzhu","family":"Li","sequence":"additional","affiliation":[{"name":"UIUC, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6556-8359","authenticated-orcid":false,"given":"Mingyu","family":"Ding","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"Torralba","sequence":"additional","affiliation":[{"name":"MIT, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua B.","family":"Tenenbaum","sequence":"additional","affiliation":[{"name":"MIT, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4031-5886","authenticated-orcid":false,"given":"Chuang","family":"Gan","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5083","article-title":"PHYRE: A new benchmark for physical reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bakhtin"},{"key":"ref2","article-title":"CLEVRER: CoLlision events for video representation and reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yi"},{"key":"ref3","article-title":"CoPhy: Counterfactual learning of physical dynamics","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baradel"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.205"},{"key":"ref5","article-title":"Grounding physical concepts of objects and events through dynamic visual reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref6","first-page":"1039","article-title":"Neural-symbolic VQA: Disentangling reasoning from vision and language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yi"},{"key":"ref7","article-title":"The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mao"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3574322"},{"key":"ref9","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref10","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01113"},{"key":"ref16","article-title":"IntPhys: A framework and benchmark for visual intuitive physics reasoning","author":"Riochet","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.706"},{"key":"ref18","article-title":"Physion: Evaluating physical prediction from vision in humans and machines","author":"Bear","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1167\/jov.23.9.5622"},{"key":"ref20","article-title":"CATER: A diagnostic dataset for compositional actions and temporal reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Girdhar"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.670"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1306572110"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2016.08.012"},{"key":"ref24","first-page":"127","article-title":"Galileo: Perceiving physical object properties by integrating a physics engine with deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref25","first-page":"430","article-title":"Learning physical intuition of block towers by example","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lerer"},{"key":"ref26","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref27","first-page":"4502","article-title":"Interaction networks for learning about objects, relations and physics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Battaglia"},{"key":"ref28","article-title":"A compositional object-based approach to learning physical dynamics","author":"Chang","year":"2016"},{"key":"ref29","first-page":"8459","article-title":"Learning to simulate complex physics with graph networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sanchez-Gonzalez"},{"key":"ref30","article-title":"Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.312"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1167"},{"key":"ref33","first-page":"3637","article-title":"Matching networks for one shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref36","first-page":"5002","article-title":"Visual concept metaconcept learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref37","article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"Coumans","year":"2016"},{"key":"ref38","article-title":"Blender - A 3D modelling and rendering package","author":"Community","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref42","article-title":"Compositional attention networks for machine reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hudson"},{"key":"ref43","article-title":"Attention over learned object embeddings enables complex visual reasoning","author":"Ding","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref48","article-title":"MONet: Unsupervised scene decomposition and representation","author":"Burgess","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref52","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1183"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1137\/0105003"},{"key":"ref55","first-page":"2688","article-title":"Neural relational inference for interacting systems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kipf"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2015.00420"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2012.0122"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793509"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11118328\/11016205.pdf?arnumber=11016205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T17:44:46Z","timestamp":1754588686000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11016205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":59,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3574322","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":[[2025,9]]}}}