{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/103736"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/103736","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Computational perception of physical object properties","abstract":"We study the problem of learning physical object properties from visual data. Inspired by findings in cognitive science that even infants are able to perceive a physical world full of dynamic content at a early age, we aim to build models to characterize object properties from synthetic and real-world scenes. We build a novel dataset containing over 17, 000 videos with 101 objects in a set of visually simple but physically rich scenarios. We further propose two novel models for learning physical object properties by incorporating physics simulators, either a symbolic interpreter or a mature physics engine, with deep neural nets. Our extensive evaluations demonstrate that these models can learn physical object properties well and, with a physic engine, the responses of the model positively correlate with human responses. Future research directions include incorporating the knowledge of physical object properties into the understanding of interactions among objects, scenes, and agents.","abstract_html":"We study the problem of learning physical object properties from visual data. Inspired by findings in cognitive science that even infants are able to perceive a physical world full of dynamic content at a early age, we aim to build models to characterize object properties from synthetic and real-world scenes. We build a novel dataset containing over 17, 000 videos with 101 objects in a set of visually simple but physically rich scenarios. We further propose two novel models for learning physical object properties by incorporating physics simulators, either a symbolic interpreter or a mature physics engine, with deep neural nets. Our extensive evaluations demonstrate that these models can learn physical object properties well and, with a physic engine, the responses of the model positively correlate with human responses. Future research directions include incorporating the knowledge of physical object properties into the understanding of interactions among objects, scenes, and agents.","abstract_has_math":false,"creators":["Wu, Jiajun, Ph.D. Massachusetts Institute of Technology"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["William T. Freeman and Joshua B. Tenenbaum."],"committee_chairs":[],"committee_members":[],"year":2016,"date_issued":"2016","date_published":"2016","updated_at":"2026-07-22T22:20:56Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1721.1/103736","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["William T. Freeman and Joshua B. Tenenbaum."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Wu, Jiajun, Ph.D. Massachusetts Institute of Technology"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2016-07-18T20:05:15Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2016-07-18T20:05:15Z"]},{"key":"dc:date.issued","label":"Date","values":["2016"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1721.1/103736"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016.","Cataloged from PDF version of thesis.","Includes bibliographical references (pages 49-50)."]},{"key":"dc:description.abstract","label":"Abstract","values":["We study the problem of learning physical object properties from visual data. Inspired by findings in cognitive science that even infants are able to perceive a physical world full of dynamic content at a early age, we aim to build models to characterize object properties from synthetic and real-world scenes. We build a novel dataset containing over 17, 000 videos with 101 objects in a set of visually simple but physically rich scenarios. We further propose two novel models for learning physical object properties by incorporating physics simulators, either a symbolic interpreter or a mature physics engine, with deep neural nets. Our extensive evaluations demonstrate that these models can learn physical object properties well and, with a physic engine, the responses of the model positively correlate with human responses. Future research directions include incorporating the knowledge of physical object properties into the understanding of interactions among objects, scenes, and agents."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Computational perception of physical object properties"]}]}],"canonical_facts":{"dc:contributor.advisor":["William T. Freeman and Joshua B. Tenenbaum."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:contributor.other":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:creator":["Wu, Jiajun, Ph.D. Massachusetts Institute of Technology"],"dc:date.accessioned":["2016-07-18T20:05:15Z"],"dc:date.available":["2016-07-18T20:05:15Z"],"dc:date.issued":["2016"],"dc:description":["Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016.","Cataloged from PDF version of thesis.","Includes bibliographical references (pages 49-50)."],"dc:description.abstract":["We study the problem of learning physical object properties from visual data. Inspired by findings in cognitive science that even infants are able to perceive a physical world full of dynamic content at a early age, we aim to build models to characterize object properties from synthetic and real-world scenes. We build a novel dataset containing over 17, 000 videos with 101 objects in a set of visually simple but physically rich scenarios. We further propose two novel models for learning physical object properties by incorporating physics simulators, either a symbolic interpreter or a mature physics engine, with deep neural nets. Our extensive evaluations demonstrate that these models can learn physical object properties well and, with a physic engine, the responses of the model positively correlate with human responses. Future research directions include incorporating the knowledge of physical object properties into the understanding of interactions among objects, scenes, and agents."],"dc:description.degree":["S.M."],"dc:identifier.uri":["http://hdl.handle.net/1721.1/103736"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Computational perception of physical object properties"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:20:56Z"}