{"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/videolights-feature-refinement-and-cross-task","title":"VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval","arxiv_id":"2412.01558","date":"2024-12-02","proceeding":null,"authors":["Dhiman Paul","Md Rizwan Parvez","Nabeel Mohammed","Shafin Rahman"],"abstract":"Video Highlight Detection and Moment Retrieval (HD/MR) are essential in video analysis. Recent joint prediction transformer models often overlook their cross-task dynamics and video-text alignment and refinement. Moreover, most models typically use limited, uni-directional attention mechanisms, resulting in weakly integrated representations and suboptimal performance in capturing the interdependence between video and text modalities. Although large-language and vision-language models (LLM/LVLMs) have gained prominence across various domains, their application in this field remains relatively underexplored. Here we propose VideoLights, a novel HD/MR framework addressing these limitations through (i) Convolutional Projection and Feature Refinement modules with an alignment loss for better video-text feature alignment, (ii) Bi-Directional Cross-Modal Fusion network for strongly coupled query-aware clip representations, and (iii) Uni-directional joint-task feedback mechanism enhancing both tasks through correlation. In addition, (iv) we introduce hard positive/negative losses for adaptive error penalization and improved learning, and (v) leverage LVLMs like BLIP-2 for enhanced multimodal feature integration and intelligent pretraining using synthetic data generated from LVLMs. Comprehensive experiments on QVHighlights, TVSum, and Charades-STA benchmarks demonstrate state-of-the-art performance. Codes and models are available at https://github.com/dpaul06/VideoLights .","url_abs":"https://arxiv.org/abs/2412.01558v1","url_pdf":"https://arxiv.org/pdf/2412.01558v1.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":"videolights-feature-refinement-and-cross-task","repo_url":"https://github.com/dpaul06/VideoLights","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"highlight-detection","task_name":"Highlight Detection"},{"task_slug":"moment-retrieval","task_name":"Moment Retrieval"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/highlight-detection-on-qvhighlights","task":"Highlight Detection","dataset":"QVHighlights","model":"VideoLights-B-pt","rank_in_archive_order":4,"of":21,"metrics":{"Hit@1":"70.56","mAP":"42.84"},"uses_additional_data":true},{"leaderboard":"/sota/moment-retrieval-on-charades-sta","task":"Moment Retrieval","dataset":"Charades-STA","model":"VideoLights-B-pt","rank_in_archive_order":10,"of":25,"metrics":{"R@1 IoU=0.3":"73.33","R@1 IoU=0.5":"61.96","R@1 IoU=0.7":"41.05","mIoU":"52.94"},"uses_additional_data":true},{"leaderboard":"/sota/moment-retrieval-on-qvhighlights","task":"Moment Retrieval","dataset":"QVHighlights","model":"VideoLights-B-pt","rank_in_archive_order":7,"of":32,"metrics":{"R@1 IoU=0.5":"70.36","R@1 IoU=0.7":"55.25","mAP":"47.94","mAP@0.5":"69.53","mAP@0.75":"49.17"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.01558","atlas_url":"https://app.syntology.ai/?focus=2412.01558","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":"2412.01558"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2412.01558\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2412.01558"},"call":"get_concepts_for_paper(arxiv_id=\"2412.01558\")"}],"by_repo":[{"repo":"dpaul06/VideoLights","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":"e40ddeddf6ddfca24a732b9a481f147310739fdb1a2fd4dfa00c75b7938c9cf6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}