{"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/qvhighlights-detecting-moments-and-highlights","title":"QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries","arxiv_id":"2107.09609","date":"2021-07-20","proceeding":null,"authors":["Jie Lei","Tamara L. Berg","Mohit Bansal"],"abstract":"Detecting customized moments and highlights from videos given natural language (NL) user queries is an important but under-studied topic. One of the challenges in pursuing this direction is the lack of annotated data. To address this issue, we present the Query-based Video Highlights (QVHIGHLIGHTS) dataset. It consists of over 10,000 YouTube videos, covering a wide range of topics, from everyday activities and travel in lifestyle vlog videos to social and political activities in news videos. Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant moments in the video w.r.t. the query, and (3) five-point scale saliency scores for all query-relevant clips. This comprehensive annotation enables us to develop and evaluate systems that detect relevant moments as well as salient highlights for diverse, flexible user queries. We also present a strong baseline for this task, Moment-DETR, a transformer encoder-decoder model that views moment retrieval as a direct set prediction problem, taking extracted video and query representations as inputs and predicting moment coordinates and saliency scores end-to-end. While our model does not utilize any human prior, we show that it performs competitively when compared to well-engineered architectures. With weakly supervised pretraining using ASR captions, MomentDETR substantially outperforms previous methods. Lastly, we present several ablations and visualizations of Moment-DETR. Data and code is publicly available at https://github.com/jayleicn/moment_detr","url_abs":"https://arxiv.org/abs/2107.09609v2","url_pdf":"https://arxiv.org/pdf/2107.09609v2.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":"qvhighlights-detecting-moments-and-highlights","repo_url":"https://github.com/jayleicn/moment_detr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"qvhighlights-detecting-moments-and-highlights","repo_url":"https://github.com/houzhijian/cone","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"qvhighlights-detecting-moments-and-highlights","repo_url":"https://github.com/tencentarc/umt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"qvhighlights-detecting-moments-and-highlights","repo_url":"https://github.com/yeliudev/R2-Tuning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"highlight-detection","task_name":"Highlight Detection"},{"task_slug":"moment-retrieval","task_name":"Moment Retrieval"},{"task_slug":"natural-language-queries","task_name":"Natural Language Queries"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":null,"method_name":"Travel"}],"datasets_introduced":[{"slug":"qvhighlights","name":"QVHighlights","full_name":"Query-based Video Highlights"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/highlight-detection-on-qvhighlights","task":"Highlight Detection","dataset":"QVHighlights","model":"Moment-DETR w/ PT","rank_in_archive_order":18,"of":21,"metrics":{"Hit@1":"60.17","mAP":"37.43"},"uses_additional_data":false},{"leaderboard":"/sota/moment-retrieval-on-charades-sta","task":"Moment Retrieval","dataset":"Charades-STA","model":"Moment-DETR w/ PT (on 10K HowTo100M videos)","rank_in_archive_order":20,"of":25,"metrics":{"R@1 IoU=0.5":"55.65","R@1 IoU=0.7":"34.17"},"uses_additional_data":false},{"leaderboard":"/sota/moment-retrieval-on-charades-sta","task":"Moment Retrieval","dataset":"Charades-STA","model":"Moment-DETR","rank_in_archive_order":21,"of":25,"metrics":{"R@1 IoU=0.5":"53.63","R@1 IoU=0.7":"31.37"},"uses_additional_data":false},{"leaderboard":"/sota/moment-retrieval-on-qvhighlights","task":"Moment Retrieval","dataset":"QVHighlights","model":"Moment-DETR (w/ PT ASR Cpations)","rank_in_archive_order":26,"of":32,"metrics":{"R@1 IoU=0.5":"59.78","R@1 IoU=0.7":"40.33","mAP":"36.14","mAP@0.5":"60.51","mAP@0.75":"35.36"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2107.09609","atlas_url":"https://app.syntology.ai/?focus=2107.09609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09609"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/jayleicn/moment_detr","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/houzhijian/cone","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yeliudev/R2-Tuning","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tencentarc/umt","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"ab831e4d334aed83","entry":"CONE","repo":"houzhijian/cone","repo_kind":"listed","path":"cone/model.py","file_url":"https://github.com/houzhijian/cone/blob/HEAD/cone/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ab831e4d334aed83"}},{"code_sha256_prefix":"ed43d511a292c720","entry":"MomentDETR","repo":"jayleicn/moment_detr","repo_kind":"official","path":"moment_detr/model.py","file_url":"https://github.com/jayleicn/moment_detr/blob/HEAD/moment_detr/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed43d511a292c720"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}