{"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/rethinking-the-architecture-design-for","title":"Rethinking the Architecture Design for Efficient Generic Event Boundary Detection","arxiv_id":"2407.12622","date":"2024-07-17","proceeding":null,"authors":["Ziwei Zheng","Zechuan Zhang","Yulin Wang","Shiji Song","Gao Huang","Le Yang"],"abstract":"Generic event boundary detection (GEBD), inspired by human visual cognitive behaviors of consistently segmenting videos into meaningful temporal chunks, finds utility in various applications such as video editing and. In this paper, we demonstrate that SOTA GEBD models often prioritize final performance over model complexity, resulting in low inference speed and hindering efficient deployment in real-world scenarios. We contribute to addressing this challenge by experimentally reexamining the architecture of GEBD models and uncovering several surprising findings. Firstly, we reveal that a concise GEBD baseline model already achieves promising performance without any sophisticated design. Secondly, we find that the widely applied image-domain backbones in GEBD models can contain plenty of architecture redundancy, motivating us to gradually ``modernize'' each component to enhance efficiency. Thirdly, we show that the GEBD models using image-domain backbones conducting the spatiotemporal learning in a spatial-then-temporal greedy manner can suffer from a distraction issue, which might be the inefficient villain for GEBD. Using a video-domain backbone to jointly conduct spatiotemporal modeling is an effective solution for this issue. The outcome of our exploration is a family of GEBD models, named EfficientGEBD, significantly outperforms the previous SOTA methods by up to 1.7\\% performance gain and 280\\% speedup under the same backbone. Our research prompts the community to design modern GEBD methods with the consideration of model complexity, particularly in resource-aware applications. The code is available at \\url{https://github.com/Ziwei-Zheng/EfficientGEBD}.","url_abs":"https://arxiv.org/abs/2407.12622v1","url_pdf":"https://arxiv.org/pdf/2407.12622v1.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":"rethinking-the-architecture-design-for","repo_url":"https://github.com/ziwei-zheng/efficientgebd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"boundary-detection","task_name":"Boundary Detection"},{"task_slug":"generic-event-boundary-detection","task_name":"Generic Event Boundary Detection"},{"task_slug":"video-editing","task_name":"Video Editing"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.12622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12622"}},"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/ziwei-zheng/efficientgebd","reach":{"status":"ok"}}],"summary":{"ran":14,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":16,"ran":15,"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":16,"samples":[{"code_sha256_prefix":"4dc9e75ee8673664","entry":"NMS","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"EffSoccerNet/metrics_visibility_fast.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/metrics_visibility_fast.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4dc9e75ee8673664"}},{"code_sha256_prefix":"9bc5e5e03d97e860","entry":"RepVGG8","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"EffSoccerNet/resnet.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9bc5e5e03d97e860"}},{"code_sha256_prefix":"cba195bb7da7ecdf","entry":"ResNet18","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"EffSoccerNet/resnet.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cba195bb7da7ecdf"}},{"code_sha256_prefix":"dcb09fc287f5e5f2","entry":"ResNetXX","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"EffSoccerNet/resnet.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dcb09fc287f5e5f2"}},{"code_sha256_prefix":"aa6da43d05cfaf65","entry":"all_gather","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"EffSoccerNet/distribute.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/distribute.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa6da43d05cfaf65"}},{"code_sha256_prefix":"c0199c9ff94b4797","entry":"append_function","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"EffSoccerNet/metrics_fast.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/metrics_fast.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c0199c9ff94b4797"}},{"code_sha256_prefix":"cf572c8b317f3a4c","entry":"calculate_f1_manual","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"EffSoccerNet/metrics_fast.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/metrics_fast.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cf572c8b317f3a4c"}},{"code_sha256_prefix":"64f3d9cd504a9a78","entry":"compute_class_scores","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"EffSoccerNet/metrics_visibility_fast.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/metrics_visibility_fast.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"64f3d9cd504a9a78"}},{"code_sha256_prefix":"7fe974d74155ad1c","entry":"compute_precision_recall_curve","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"EffSoccerNet/metrics_visibility_fast.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/metrics_visibility_fast.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7fe974d74155ad1c"}},{"code_sha256_prefix":"971ae8d2d8313e30","entry":"drop_path","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"EffSoccerNet/diff_former.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/diff_former.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"code_sha256_prefix":"2816ac2fa19e88bf","entry":"getNegativeIndexes","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"EffSoccerNet/preprocessing.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/preprocessing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2816ac2fa19e88bf"}},{"code_sha256_prefix":"b6b24ff52e085b91","entry":"oneClasslabels","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"EffSoccerNet/preprocessing.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/preprocessing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b6b24ff52e085b91"}},{"code_sha256_prefix":"f7a3c5076aa34b5a","entry":"oneHotToAlllabels","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"EffSoccerNet/preprocessing.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/preprocessing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f7a3c5076aa34b5a"}},{"code_sha256_prefix":"2dd22ce91e46763f","entry":"prepare_gaussian_targets","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"EffSoccerNet/model.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2dd22ce91e46763f"}},{"code_sha256_prefix":"d1270e685e443e13","entry":"temporal_features","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"export/model.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/export/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d1270e685e443e13"}},{"code_sha256_prefix":"33fa4ecf4b2caa08","entry":"calculate_f1_score","repo":"ziwei-zheng/efficientgebd","repo_kind":"official","path":"EffSoccerNet/metrics_fast.py","file_url":"https://github.com/ziwei-zheng/efficientgebd/blob/HEAD/EffSoccerNet/metrics_fast.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":"33fa4ecf4b2caa08"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}