{"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/detecting-moments-and-highlights-in-videos","title":"Detecting Moments and Highlights in Videos via Natural Language Queries","arxiv_id":null,"date":"2021-12-01","proceeding":"NeurIPS 2021 12","authors":["Jie Lei","Tamara 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, Moment-DETR 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":"http://proceedings.neurips.cc/paper/2021/hash/62e0973455fd26eb03e91d5741a4a3bb-Abstract.html","url_pdf":"http://proceedings.neurips.cc/paper/2021/file/62e0973455fd26eb03e91d5741a4a3bb-Paper.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":"detecting-moments-and-highlights-in-videos","repo_url":"https://github.com/jayleicn/moment_detr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"moment-retrieval","task_name":"Moment Retrieval"},{"task_slug":"natural-language-queries","task_name":"Natural Language Queries"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"video-grounding","task_name":"Video Grounding"}],"methods":[{"method_slug":null,"method_name":"Travel"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-grounding-on-qvhighlights","task":"Video Grounding","dataset":"QVHighlights","model":"Moment-DETR","rank_in_archive_order":7,"of":7,"metrics":{"R@1,IoU=0.5":"52.89","R@1,IoU=0.7":"33.02"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}