{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/saliency-guided-detr-for-moment-retrieval-and","title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","arxiv_id":"2410.01615","date":"2024-10-02","proceeding":null,"authors":["Aleksandr Gordeev","Vladimir Dokholyan","Irina Tolstykh","Maksim Kuprashevich"],"abstract":"Existing approaches for video moment retrieval and highlight detection are not able to align text and video features efficiently, resulting in unsatisfying performance and limited production usage. To address this, we propose a novel architecture that utilizes recent foundational video models designed for such alignment. Combined with the introduced Saliency-Guided Cross Attention mechanism and a hybrid DETR architecture, our approach significantly enhances performance in both moment retrieval and highlight detection tasks. For even better improvement, we developed InterVid-MR, a large-scale and high-quality dataset for pretraining. Using it, our architecture achieves state-of-the-art results on the QVHighlights, Charades-STA and TACoS benchmarks. The proposed approach provides an efficient and scalable solution for both zero-shot and fine-tuning scenarios in video-language tasks.","url_abs":"https://arxiv.org/abs/2410.01615v1","url_pdf":"https://arxiv.org/pdf/2410.01615v1.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":"saliency-guided-detr-for-moment-retrieval-and","repo_url":"https://github.com/ai-forever/sg-detr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"highlight-detection","task_name":"Highlight Detection"},{"task_slug":"moment-retrieval","task_name":"Moment Retrieval"},{"task_slug":"natural-language-moment-retrieval","task_name":"Natural Language Moment Retrieval"},{"task_slug":"natural-language-queries","task_name":"Natural Language Queries"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"zero-shot-moment-retrieval","task_name":"Zero-shot Moment Retrieval"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"detr","method_name":"Detr"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/highlight-detection-on-qvhighlights","task":"Highlight Detection","dataset":"QVHighlights","model":"SG-DETR (w/ PT)","rank_in_archive_order":1,"of":21,"metrics":{"Hit@1":"71.00","mAP":"44.70"},"uses_additional_data":true},{"leaderboard":"/sota/highlight-detection-on-qvhighlights","task":"Highlight Detection","dataset":"QVHighlights","model":"SG-DETR","rank_in_archive_order":3,"of":21,"metrics":{"Hit@1":"69.13","mAP":"43.76"},"uses_additional_data":false},{"leaderboard":"/sota/highlight-detection-on-tvsum","task":"Highlight Detection","dataset":"TvSum","model":"SG-DETR","rank_in_archive_order":2,"of":7,"metrics":{"mAP":"87.1"},"uses_additional_data":false},{"leaderboard":"/sota/highlight-detection-on-youtube-highlights","task":"Highlight Detection","dataset":"YouTube Highlights","model":"SG-DETR (w/ PT)","rank_in_archive_order":1,"of":7,"metrics":{"mAP":"78.0"},"uses_additional_data":true},{"leaderboard":"/sota/highlight-detection-on-youtube-highlights","task":"Highlight Detection","dataset":"YouTube Highlights","model":"SG-DETR","rank_in_archive_order":3,"of":7,"metrics":{"mAP":"76.7"},"uses_additional_data":false},{"leaderboard":"/sota/moment-retrieval-on-charades-sta","task":"Moment Retrieval","dataset":"Charades-STA","model":"SG-DETR (w/ PT)","rank_in_archive_order":1,"of":25,"metrics":{"R@1 IoU=0.5":"71.10","R@1 IoU=0.7":"52.80"},"uses_additional_data":true},{"leaderboard":"/sota/moment-retrieval-on-charades-sta","task":"Moment Retrieval","dataset":"Charades-STA","model":"SG-DETR","rank_in_archive_order":4,"of":25,"metrics":{"R@1 IoU=0.5":"70.20","R@1 IoU=0.7":"49.50"},"uses_additional_data":false},{"leaderboard":"/sota/moment-retrieval-on-qvhighlights","task":"Moment Retrieval","dataset":"QVHighlights","model":"SG-DETR (w/ PT)","rank_in_archive_order":1,"of":32,"metrics":{"R@1 IoU=0.5":"74.20","R@1 IoU=0.7":"60.40","mAP":"58.80","mAP@0.5":"76.20","mAP@0.75":"60.80"},"uses_additional_data":true},{"leaderboard":"/sota/moment-retrieval-on-qvhighlights","task":"Moment Retrieval","dataset":"QVHighlights","model":"SG-DETR","rank_in_archive_order":2,"of":32,"metrics":{"R@1 IoU=0.5":"72.20","R@1 IoU=0.7":"56.60","mAP":"54.10","mAP@0.5":"73.20","mAP@0.75":"55.80"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-moment-retrieval-on-tacos","task":"Natural Language Moment Retrieval","dataset":"TACoS","model":"SG-DETR (w/ PT)","rank_in_archive_order":1,"of":13,"metrics":{"R@1,IoU=0.3":"58.10","R@1,IoU=0.5":"46.40","R@1,IoU=0.7":"33.90","mIoU":"42.40"},"uses_additional_data":true},{"leaderboard":"/sota/natural-language-moment-retrieval-on-tacos","task":"Natural Language Moment Retrieval","dataset":"TACoS","model":"SG-DETR","rank_in_archive_order":4,"of":13,"metrics":{"R@1,IoU=0.3":"56.71","R@1,IoU=0.5":"44.70","R@1,IoU=0.7":"29.90","mIoU":"40.90"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-moment-retrieval-on-qvhighlights","task":"Zero-shot Moment Retrieval","dataset":"QVHighlights","model":"SG-DETR (ZS)","rank_in_archive_order":1,"of":2,"metrics":{"R1@0.5":"63.90","R1@0.7":"49.60","mAP":"48.30","mAP@0.5":"67.50","mAP@0.75":"49.00"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.01615","atlas_url":"https://app.syntology.ai/?focus=2410.01615","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2410.01615"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2410.01615\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2410.01615"},"call":"get_concepts_for_paper(arxiv_id=\"2410.01615\")"}],"by_repo":[{"repo":"ai-forever/sg-detr","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"343856f3d8856a01ce2d8a268e17651adcc312658ea7d13b9cb73f522466205e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}