{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/hierarchical-conditional-relation-networks","title":"Hierarchical Conditional Relation Networks for Video Question Answering","arxiv_id":"2002.10698","date":"2020-02-25","proceeding":"CVPR 2020 6","authors":["Thao Minh Le","Vuong Le","Svetha Venkatesh","Truyen Tran"],"abstract":"Video question answering (VideoQA) is challenging as it requires modeling capacity to distill dynamic visual artifacts and distant relations and to associate them with linguistic concepts. We introduce a general-purpose reusable neural unit called Conditional Relation Network (CRN) that serves as a building block to construct more sophisticated structures for representation and reasoning over video. CRN takes as input an array of tensorial objects and a conditioning feature, and computes an array of encoded output objects. Model building becomes a simple exercise of replication, rearrangement and stacking of these reusable units for diverse modalities and contextual information. This design thus supports high-order relational and multi-step reasoning. The resulting architecture for VideoQA is a CRN hierarchy whose branches represent sub-videos or clips, all sharing the same question as the contextual condition. Our evaluations on well-known datasets achieved new SoTA results, demonstrating the impact of building a general-purpose reasoning unit on complex domains such as VideoQA.","url_abs":"https://arxiv.org/abs/2002.10698v3","url_pdf":"https://arxiv.org/pdf/2002.10698v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"hierarchical-conditional-relation-networks","repo_url":"https://github.com/thaolmk54/hcrn-videoqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"audio-visual-question-answering-avqa","task_name":"Audio-Visual Question Answering (AVQA)"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-network","task_name":"Relation Network"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"crn","method_name":"CRN"}],"datasets_introduced":[],"methods_introduced":[{"slug":"crn","name":"CRN","full_name":"Conditional Relation Network"}],"results":[{"leaderboard":"/sota/video-question-answering-on-sutd-trafficqa","task":"Video Question Answering","dataset":"SUTD-TrafficQA","model":"HCRN","rank_in_archive_order":4,"of":6,"metrics":{"1/2":"63.79","1/4":"36.49"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-msrvtt-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSRVTT-QA","model":"HCRN","rank_in_archive_order":28,"of":34,"metrics":{"Accuracy":"0.356"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-msvd-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSVD-QA","model":"HCRN","rank_in_archive_order":32,"of":36,"metrics":{"Accuracy":"0.361"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.10698","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}