{"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/a-local-to-global-approach-to-multi-modal","title":"A Local-to-Global Approach to Multi-modal Movie Scene Segmentation","arxiv_id":"2004.02678","date":"2020-04-06","proceeding":"CVPR 2020 6","authors":["Anyi Rao","Linning Xu","Yu Xiong","Guodong Xu","Qingqiu Huang","Bolei Zhou","Dahua Lin"],"abstract":"Scene, as the crucial unit of storytelling in movies, contains complex activities of actors and their interactions in a physical environment. Identifying the composition of scenes serves as a critical step towards semantic understanding of movies. This is very challenging -- compared to the videos studied in conventional vision problems, e.g. action recognition, as scenes in movies usually contain much richer temporal structures and more complex semantic information. Towards this goal, we scale up the scene segmentation task by building a large-scale video dataset MovieScenes, which contains 21K annotated scene segments from 150 movies. We further propose a local-to-global scene segmentation framework, which integrates multi-modal information across three levels, i.e. clip, segment, and movie. This framework is able to distill complex semantics from hierarchical temporal structures over a long movie, providing top-down guidance for scene segmentation. Our experiments show that the proposed network is able to segment a movie into scenes with high accuracy, consistently outperforming previous methods. We also found that pretraining on our MovieScenes can bring significant improvements to the existing approaches.","url_abs":"https://arxiv.org/abs/2004.02678v3","url_pdf":"https://arxiv.org/pdf/2004.02678v3.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":"a-local-to-global-approach-to-multi-modal","repo_url":"https://github.com/AnyiRao/SceneSeg","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"a-local-to-global-approach-to-multi-modal","repo_url":"https://github.com/Nikhil9786/Scene-Segmentation-Using-MovieScenes-Dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-local-to-global-approach-to-multi-modal","repo_url":"https://github.com/VipulDhariwal/eluvio_data_challenge","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"a-local-to-global-approach-to-multi-modal","repo_url":"https://github.com/bharath3794/SceneSegmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"scene-segmentation","task_name":"Scene Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2004.02678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.02678"}},"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/Nikhil9786/Scene-Segmentation-Using-MovieScenes-Dataset","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bharath3794/SceneSegmentation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/VipulDhariwal/eluvio_data_challenge","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AnyiRao/SceneSeg","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"a930141a486cd85a","entry":"calc_ap","repo":"Nikhil9786/Scene-Segmentation-Using-MovieScenes-Dataset","repo_kind":"listed","path":"evaluate_sceneseg.py","file_url":"https://github.com/Nikhil9786/Scene-Segmentation-Using-MovieScenes-Dataset/blob/HEAD/evaluate_sceneseg.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a930141a486cd85a"}},{"code_sha256_prefix":"fafbe9d0c2d3829d","entry":"calc_precision_recall","repo":"Nikhil9786/Scene-Segmentation-Using-MovieScenes-Dataset","repo_kind":"listed","path":"evaluate_sceneseg.py","file_url":"https://github.com/Nikhil9786/Scene-Segmentation-Using-MovieScenes-Dataset/blob/HEAD/evaluate_sceneseg.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fafbe9d0c2d3829d"}},{"code_sha256_prefix":"725231b9141469af","entry":"calc_miou","repo":"Nikhil9786/Scene-Segmentation-Using-MovieScenes-Dataset","repo_kind":"listed","path":"evaluate_sceneseg.py","file_url":"https://github.com/Nikhil9786/Scene-Segmentation-Using-MovieScenes-Dataset/blob/HEAD/evaluate_sceneseg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"725231b9141469af"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}