{"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/csta-cnn-based-spatiotemporal-attention-for","title":"CSTA: CNN-based Spatiotemporal Attention for Video Summarization","arxiv_id":"2405.11905","date":"2024-05-20","proceeding":"CVPR 2024 1","authors":["Jaewon Son","Jaehun Park","Kwangsu Kim"],"abstract":"Video summarization aims to generate a concise representation of a video, capturing its essential content and key moments while reducing its overall length. Although several methods employ attention mechanisms to handle long-term dependencies, they often fail to capture the visual significance inherent in frames. To address this limitation, we propose a CNN-based SpatioTemporal Attention (CSTA) method that stacks each feature of frames from a single video to form image-like frame representations and applies 2D CNN to these frame features. Our methodology relies on CNN to comprehend the inter and intra-frame relations and to find crucial attributes in videos by exploiting its ability to learn absolute positions within images. In contrast to previous work compromising efficiency by designing additional modules to focus on spatial importance, CSTA requires minimal computational overhead as it uses CNN as a sliding window. Extensive experiments on two benchmark datasets (SumMe and TVSum) demonstrate that our proposed approach achieves state-of-the-art performance with fewer MACs compared to previous methods. Codes are available at https://github.com/thswodnjs3/CSTA.","url_abs":"https://arxiv.org/abs/2405.11905v2","url_pdf":"https://arxiv.org/pdf/2405.11905v2.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":"csta-cnn-based-spatiotemporal-attention-for","repo_url":"https://github.com/thswodnjs3/CSTA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"supervised-video-summarization","task_name":"Supervised Video Summarization"},{"task_slug":"video-summarization","task_name":"Video Summarization"}],"methods":[{"method_slug":"adaptive-feature-pooling","method_name":"Adaptive Feature Pooling"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"googlenet","method_name":"GoogLeNet"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"positional-encoding-generator","method_name":"Positional Encoding Generator"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"sag","method_name":"Self-Attention Guidance"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/supervised-video-summarization-on-summe","task":"Supervised Video Summarization","dataset":"SumMe","model":"CSTA","rank_in_archive_order":21,"of":21,"metrics":{"Kendall's Tau":"0.246","Spearman's Rho":"0.274"},"uses_additional_data":false},{"leaderboard":"/sota/supervised-video-summarization-on-tvsum","task":"Supervised Video Summarization","dataset":"TvSum","model":"CSTA","rank_in_archive_order":21,"of":21,"metrics":{"Kendall's Tau":"0.194","Spearman's Rho":"0.255"},"uses_additional_data":false},{"leaderboard":"/sota/video-summarization-on-summe","task":"Video Summarization","dataset":"SumMe","model":"CSTA","rank_in_archive_order":6,"of":6,"metrics":{"Kendall's Tau":"0.246","Spearman's Rho":"0.274"},"uses_additional_data":false},{"leaderboard":"/sota/video-summarization-on-tvsum","task":"Video Summarization","dataset":"TvSum","model":"CSTA","rank_in_archive_order":6,"of":6,"metrics":{"Kendall's Tau":"0.194","Spearman's Rho":"0.255"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.11905","atlas_url":"https://app.syntology.ai/?focus=2405.11905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11905"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/thswodnjs3/CSTA","reach":null}],"summary":{"ran":7,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"296ce13d2909cb38","entry":"BasicBlock","repo":"thswodnjs3/CSTA","repo_kind":"official","path":"models/ResNet.py","file_url":"https://github.com/thswodnjs3/CSTA/blob/HEAD/models/ResNet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"296ce13d2909cb38"}},{"code_sha256_prefix":"2b5c8002b738f378","entry":"Bottleneck","repo":"thswodnjs3/CSTA","repo_kind":"official","path":"models/ResNet.py","file_url":"https://github.com/thswodnjs3/CSTA/blob/HEAD/models/ResNet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b5c8002b738f378"}},{"code_sha256_prefix":"abd4c1235b0f54ba","entry":"ConditionalPositionalEncoding","repo":"thswodnjs3/CSTA","repo_kind":"official","path":"models/ResNet.py","file_url":"https://github.com/thswodnjs3/CSTA/blob/HEAD/models/ResNet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"abd4c1235b0f54ba"}},{"code_sha256_prefix":"21b3939f0ce86110","entry":"FixedPositionalEncoding","repo":"thswodnjs3/CSTA","repo_kind":"official","path":"models/ResNet.py","file_url":"https://github.com/thswodnjs3/CSTA/blob/HEAD/models/ResNet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21b3939f0ce86110"}},{"code_sha256_prefix":"dcdf2add2e19b043","entry":"LearnablePositionalEncoding","repo":"thswodnjs3/CSTA","repo_kind":"official","path":"models/ResNet.py","file_url":"https://github.com/thswodnjs3/CSTA/blob/HEAD/models/ResNet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dcdf2add2e19b043"}},{"code_sha256_prefix":"cd1a86bd4a6df8fb","entry":"RelativePositionalEncoding","repo":"thswodnjs3/CSTA","repo_kind":"official","path":"models/ResNet.py","file_url":"https://github.com/thswodnjs3/CSTA/blob/HEAD/models/ResNet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cd1a86bd4a6df8fb"}},{"code_sha256_prefix":"3649f620d04fd589","entry":"ResNet_Att","repo":"thswodnjs3/CSTA","repo_kind":"official","path":"models/ResNet.py","file_url":"https://github.com/thswodnjs3/CSTA/blob/HEAD/models/ResNet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3649f620d04fd589"}},{"code_sha256_prefix":"cb8636daf2db9a73","entry":"CSTA_ResNet","repo":"thswodnjs3/CSTA","repo_kind":"official","path":"models/ResNet.py","file_url":"https://github.com/thswodnjs3/CSTA/blob/HEAD/models/ResNet.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":"cb8636daf2db9a73"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}