{"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/movieclip-visual-scene-recognition-in-movies","title":"MovieCLIP: Visual Scene Recognition in Movies","arxiv_id":"2210.11065","date":"2022-10-20","proceeding":null,"authors":["Digbalay Bose","Rajat Hebbar","Krishna Somandepalli","Haoyang Zhang","Yin Cui","Kree Cole-McLaughlin","Huisheng Wang","Shrikanth Narayanan"],"abstract":"Longform media such as movies have complex narrative structures, with events spanning a rich variety of ambient visual scenes. Domain specific challenges associated with visual scenes in movies include transitions, person coverage, and a wide array of real-life and fictional scenarios. Existing visual scene datasets in movies have limited taxonomies and don't consider the visual scene transition within movie clips. In this work, we address the problem of visual scene recognition in movies by first automatically curating a new and extensive movie-centric taxonomy of 179 scene labels derived from movie scripts and auxiliary web-based video datasets. Instead of manual annotations which can be expensive, we use CLIP to weakly label 1.12 million shots from 32K movie clips based on our proposed taxonomy. We provide baseline visual models trained on the weakly labeled dataset called MovieCLIP and evaluate them on an independent dataset verified by human raters. We show that leveraging features from models pretrained on MovieCLIP benefits downstream tasks such as multi-label scene and genre classification of web videos and movie trailers.","url_abs":"https://arxiv.org/abs/2210.11065v2","url_pdf":"https://arxiv.org/pdf/2210.11065v2.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":"movieclip-visual-scene-recognition-in-movies","repo_url":"https://github.com/usc-sail/mica-MovieCLIP","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"genre-classification","task_name":"Genre classification"},{"task_slug":"scene-recognition","task_name":"Scene Recognition"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[{"slug":"movieclip","name":"MovieCLIP","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.11065","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11065"}},"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/usc-sail/mica-MovieCLIP","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_fixture":1,"unverified":9},"by_repo_kind":{"official":{"samples":11,"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":0,"samples":[{"code_sha256_prefix":"ee5e85cfd16bc5dc","entry":"linear_combination","repo":"usc-sail/mica-MovieCLIP","repo_kind":"official","path":"losses/loss_functions.py","file_url":"https://github.com/usc-sail/mica-MovieCLIP/blob/HEAD/losses/loss_functions.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee5e85cfd16bc5dc"}},{"code_sha256_prefix":"9f7b947fbfdaa657","entry":"reduce_loss","repo":"usc-sail/mica-MovieCLIP","repo_kind":"official","path":"losses/loss_functions.py","file_url":"https://github.com/usc-sail/mica-MovieCLIP/blob/HEAD/losses/loss_functions.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f7b947fbfdaa657"}},{"code_sha256_prefix":"4bebda9ddfdffe0a","entry":"focal_loss","repo":"usc-sail/mica-MovieCLIP","repo_kind":"official","path":"losses/loss_functions.py","file_url":"https://github.com/usc-sail/mica-MovieCLIP/blob/HEAD/losses/loss_functions.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":"4bebda9ddfdffe0a"}},{"code_sha256_prefix":"b20728fa672ca30b","entry":"generate_cmd_clip_list","repo":"usc-sail/mica-MovieCLIP","repo_kind":"official","path":"preprocess_scripts/check_shot_segment_files_overlap.py","file_url":"https://github.com/usc-sail/mica-MovieCLIP/blob/HEAD/preprocess_scripts/check_shot_segment_files_overlap.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":"b20728fa672ca30b"}},{"code_sha256_prefix":"7c0d71ba04363654","entry":"generate_file_name","repo":"usc-sail/mica-MovieCLIP","repo_kind":"official","path":"preprocess_scripts/check_shot_segment_files_overlap.py","file_url":"https://github.com/usc-sail/mica-MovieCLIP/blob/HEAD/preprocess_scripts/check_shot_segment_files_overlap.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":"7c0d71ba04363654"}},{"code_sha256_prefix":"1c1579560a594d32","entry":"generate_video_key_wise_dictionary","repo":"usc-sail/mica-MovieCLIP","repo_kind":"official","path":"preprocess_scripts/preprocess_movieCLIP_json_format.py","file_url":"https://github.com/usc-sail/mica-MovieCLIP/blob/HEAD/preprocess_scripts/preprocess_movieCLIP_json_format.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":"1c1579560a594d32"}},{"code_sha256_prefix":"c551073449e12e26","entry":"generate_video_tensor_cv2","repo":"usc-sail/mica-MovieCLIP","repo_kind":"official","path":"feature_extraction/extract_places365_features.py","file_url":"https://github.com/usc-sail/mica-MovieCLIP/blob/HEAD/feature_extraction/extract_places365_features.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":"c551073449e12e26"}},{"code_sha256_prefix":"f2cba7d64b723bb9","entry":"getActivation","repo":"usc-sail/mica-MovieCLIP","repo_kind":"official","path":"feature_extraction/extract_places365_features.py","file_url":"https://github.com/usc-sail/mica-MovieCLIP/blob/HEAD/feature_extraction/extract_places365_features.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":"f2cba7d64b723bb9"}},{"code_sha256_prefix":"fd9228d157bd9d54","entry":"optimizer_adam","repo":"usc-sail/mica-MovieCLIP","repo_kind":"official","path":"optimizers/optimizer.py","file_url":"https://github.com/usc-sail/mica-MovieCLIP/blob/HEAD/optimizers/optimizer.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":"fd9228d157bd9d54"}},{"code_sha256_prefix":"c824a0c1aaa7431f","entry":"read_shot_segment_csv_file","repo":"usc-sail/mica-MovieCLIP","repo_kind":"official","path":"preprocess_scripts/preprocess_movieCLIP_json_format.py","file_url":"https://github.com/usc-sail/mica-MovieCLIP/blob/HEAD/preprocess_scripts/preprocess_movieCLIP_json_format.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":"c824a0c1aaa7431f"}},{"code_sha256_prefix":"7596f0e252f8018d","entry":"read_txt_file","repo":"usc-sail/mica-MovieCLIP","repo_kind":"official","path":"preprocess_scripts/compute_distribution_visual_scene_labels.py","file_url":"https://github.com/usc-sail/mica-MovieCLIP/blob/HEAD/preprocess_scripts/compute_distribution_visual_scene_labels.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":"7596f0e252f8018d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}