{"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/number-it-temporal-grounding-videos-like","title":"Number it: Temporal Grounding Videos like Flipping Manga","arxiv_id":"2411.10332","date":"2024-11-15","proceeding":"CVPR 2025 1","authors":["Yongliang Wu","Xinting Hu","Yuyang Sun","Yizhou Zhou","Wenbo Zhu","Fengyun Rao","Bernt Schiele","Xu Yang"],"abstract":"Video Large Language Models (Vid-LLMs) have made remarkable advancements in comprehending video content for QA dialogue. However, they struggle to extend this visual understanding to tasks requiring precise temporal localization, known as Video Temporal Grounding (VTG). To address this gap, we introduce Number-Prompt (NumPro), a novel method that empowers Vid-LLMs to bridge visual comprehension with temporal grounding by adding unique numerical identifiers to each video frame. Treating a video as a sequence of numbered frame images, NumPro transforms VTG into an intuitive process: flipping through manga panels in sequence. This allows Vid-LLMs to \"read\" event timelines, accurately linking visual content with corresponding temporal information. Our experiments demonstrate that NumPro significantly boosts VTG performance of top-tier Vid-LLMs without additional computational cost. Furthermore, fine-tuning on a NumPro-enhanced dataset defines a new state-of-the-art for VTG, surpassing previous top-performing methods by up to 6.9\\% in mIoU for moment retrieval and 8.5\\% in mAP for highlight detection. The code will be available at https://github.com/yongliang-wu/NumPro.","url_abs":"https://arxiv.org/abs/2411.10332v2","url_pdf":"https://arxiv.org/pdf/2411.10332v2.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":"number-it-temporal-grounding-videos-like","repo_url":"https://github.com/yongliang-wu/numpro","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"highlight-detection","task_name":"Highlight Detection"},{"task_slug":"moment-retrieval","task_name":"Moment Retrieval"},{"task_slug":"temporal-localization","task_name":"Temporal Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/highlight-detection-on-qvhighlights","task":"Highlight Detection","dataset":"QVHighlights","model":"NumPro","rank_in_archive_order":8,"of":21,"metrics":{"Hit@1":"70.71","mAP":"40.54"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.10332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10332"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yongliang-wu/numpro","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"unverified":10},"by_repo_kind":{"official":{"samples":11,"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":0,"samples":[{"code_sha256_prefix":"b0a851cae92754ff","entry":"extract_patches","repo":"yongliang-wu/numpro","repo_kind":"official","path":"longva/mm_utils.py","file_url":"https://github.com/yongliang-wu/numpro/blob/HEAD/longva/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b0a851cae92754ff"}},{"code_sha256_prefix":"6e523b8746fa8eed","entry":"annotate_frame_with_pil","repo":"yongliang-wu/numpro","repo_kind":"official","path":"eval/numpro_ft_hd.py","file_url":"https://github.com/yongliang-wu/numpro/blob/HEAD/eval/numpro_ft_hd.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e523b8746fa8eed"}},{"code_sha256_prefix":"f00d5d67e5507265","entry":"annotate_frame_with_pil","repo":"yongliang-wu/numpro","repo_kind":"official","path":"eval/numpro_ft_mr.py","file_url":"https://github.com/yongliang-wu/numpro/blob/HEAD/eval/numpro_ft_mr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f00d5d67e5507265"}},{"code_sha256_prefix":"60f0c1ec82dcb487","entry":"annotate_frame_with_pil","repo":"yongliang-wu/numpro","repo_kind":"official","path":"eval/qwen2_vl_7b_hd.py","file_url":"https://github.com/yongliang-wu/numpro/blob/HEAD/eval/qwen2_vl_7b_hd.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"60f0c1ec82dcb487"}},{"code_sha256_prefix":"1eb7ede6ad3ffb28","entry":"annotate_frame_with_pil","repo":"yongliang-wu/numpro","repo_kind":"official","path":"eval/qwen2_vl_7b_mr.py","file_url":"https://github.com/yongliang-wu/numpro/blob/HEAD/eval/qwen2_vl_7b_mr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1eb7ede6ad3ffb28"}},{"code_sha256_prefix":"3c8823948724e269","entry":"auto_pad_images","repo":"yongliang-wu/numpro","repo_kind":"official","path":"longva/mm_utils.py","file_url":"https://github.com/yongliang-wu/numpro/blob/HEAD/longva/mm_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c8823948724e269"}},{"code_sha256_prefix":"72ed5b8816e4da32","entry":"cal_iou","repo":"yongliang-wu/numpro","repo_kind":"official","path":"eval/metrics_mr.py","file_url":"https://github.com/yongliang-wu/numpro/blob/HEAD/eval/metrics_mr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"72ed5b8816e4da32"}},{"code_sha256_prefix":"df30d90fba7edb3e","entry":"calculate_iou","repo":"yongliang-wu/numpro","repo_kind":"official","path":"eval/metrics_mr.py","file_url":"https://github.com/yongliang-wu/numpro/blob/HEAD/eval/metrics_mr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df30d90fba7edb3e"}},{"code_sha256_prefix":"45bf4c9b636fac7a","entry":"load_lora","repo":"yongliang-wu/numpro","repo_kind":"official","path":"eval/numpro_ft_hd.py","file_url":"https://github.com/yongliang-wu/numpro/blob/HEAD/eval/numpro_ft_hd.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"45bf4c9b636fac7a"}},{"code_sha256_prefix":"c80358dff96c25ce","entry":"resize_and_center_crop","repo":"yongliang-wu/numpro","repo_kind":"official","path":"longva/mm_utils.py","file_url":"https://github.com/yongliang-wu/numpro/blob/HEAD/longva/mm_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c80358dff96c25ce"}},{"code_sha256_prefix":"4974a9f271405506","entry":"video_demo","repo":"yongliang-wu/numpro","repo_kind":"official","path":"eval/numpro_ft_mr.py","file_url":"https://github.com/yongliang-wu/numpro/blob/HEAD/eval/numpro_ft_mr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4974a9f271405506"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}