{"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/cast-cross-attention-in-space-and-time-for-1","title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","arxiv_id":"2311.18825","date":"2023-11-30","proceeding":"NeurIPS 2023 11","authors":["DongHo Lee","Jongseo Lee","Jinwoo Choi"],"abstract":"Recognizing human actions in videos requires spatial and temporal understanding. Most existing action recognition models lack a balanced spatio-temporal understanding of videos. In this work, we propose a novel two-stream architecture, called Cross-Attention in Space and Time (CAST), that achieves a balanced spatio-temporal understanding of videos using only RGB input. Our proposed bottleneck cross-attention mechanism enables the spatial and temporal expert models to exchange information and make synergistic predictions, leading to improved performance. We validate the proposed method with extensive experiments on public benchmarks with different characteristics: EPIC-KITCHENS-100, Something-Something-V2, and Kinetics-400. Our method consistently shows favorable performance across these datasets, while the performance of existing methods fluctuates depending on the dataset characteristics.","url_abs":"https://arxiv.org/abs/2311.18825v2","url_pdf":"https://arxiv.org/pdf/2311.18825v2.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":"cast-cross-attention-in-space-and-time-for-1","repo_url":"https://github.com/khu-vll/cast","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition-in-videos-2","task_name":"Action Recognition In Videos"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"CAST(ViT-B/16)","rank_in_archive_order":56,"of":207,"metrics":{"Acc@1":"85.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-epic-kitchens-100","task":"Action Recognition","dataset":"EPIC-KITCHENS-100","model":"CAST(ViT-B/16)","rank_in_archive_order":10,"of":32,"metrics":{"Action@1":"49.3","Noun@1":"60.9","Verb@1":"72.5"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"CAST(ViT-B/16)","rank_in_archive_order":27,"of":123,"metrics":{"Top-1 Accuracy":"71.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.18825","atlas_url":"https://app.syntology.ai/?focus=2311.18825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18825"}},"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":"deterministic:regex_extraction","url":"https://github.com/KHU-VLL/CAST","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/khu-vll/cast","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":8,"ran_honours":1,"unverified":8},"by_repo_kind":{"named_in_paper":{"samples":17,"ran":9,"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":17,"samples":[{"code_sha256_prefix":"b181227b8cc95f3d","entry":"Attention","repo":"khu-vll/cast","repo_kind":"named_in_paper","path":"models/bidir_modeling_crossattn.py","file_url":"https://github.com/khu-vll/cast/blob/HEAD/models/bidir_modeling_crossattn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b181227b8cc95f3d"}},{"code_sha256_prefix":"ef0019b3743b17db","entry":"CrossAttentionT2S","repo":"khu-vll/cast","repo_kind":"named_in_paper","path":"models/bidir_modeling_crossattn.py","file_url":"https://github.com/khu-vll/cast/blob/HEAD/models/bidir_modeling_crossattn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ef0019b3743b17db"}},{"code_sha256_prefix":"353426ba46a4932c","entry":"LayerNorm","repo":"khu-vll/cast","repo_kind":"named_in_paper","path":"models/bidir_modeling_crossattn.py","file_url":"https://github.com/khu-vll/cast/blob/HEAD/models/bidir_modeling_crossattn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"353426ba46a4932c"}},{"code_sha256_prefix":"457807b46c3549fe","entry":"composition_train_class_batch","repo":"KHU-VLL/CAST","repo_kind":"named_in_paper","path":"engine_for_compomodel.py","file_url":"https://github.com/KHU-VLL/CAST/blob/HEAD/engine_for_compomodel.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"457807b46c3549fe"}},{"code_sha256_prefix":"bc39b8ed5fefa7eb","entry":"crop_clip","repo":"KHU-VLL/CAST","repo_kind":"named_in_paper","path":"util_tools/functional.py","file_url":"https://github.com/KHU-VLL/CAST/blob/HEAD/util_tools/functional.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":"bc39b8ed5fefa7eb"}},{"code_sha256_prefix":"2604141544b5eec0","entry":"cross_train_class_batch","repo":"KHU-VLL/CAST","repo_kind":"named_in_paper","path":"engine_for_onemodel.py","file_url":"https://github.com/KHU-VLL/CAST/blob/HEAD/engine_for_onemodel.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2604141544b5eec0"}},{"code_sha256_prefix":"2b53e457d5632b4e","entry":"get_resize_sizes","repo":"KHU-VLL/CAST","repo_kind":"named_in_paper","path":"util_tools/functional.py","file_url":"https://github.com/KHU-VLL/CAST/blob/HEAD/util_tools/functional.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":"2b53e457d5632b4e"}},{"code_sha256_prefix":"9b2250a3d13ed688","entry":"get_sinusoid_encoding_table","repo":"khu-vll/cast","repo_kind":"named_in_paper","path":"models/bidir_modeling_crossattn.py","file_url":"https://github.com/khu-vll/cast/blob/HEAD/models/bidir_modeling_crossattn.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9b2250a3d13ed688"}},{"code_sha256_prefix":"981936c73d3cdd12","entry":"resize_clip","repo":"KHU-VLL/CAST","repo_kind":"named_in_paper","path":"util_tools/functional.py","file_url":"https://github.com/KHU-VLL/CAST/blob/HEAD/util_tools/functional.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":"981936c73d3cdd12"}},{"code_sha256_prefix":"857af2a7de44faaa","entry":"Adapter","repo":"khu-vll/cast","repo_kind":"named_in_paper","path":"models/bidir_modeling_crossattn.py","file_url":"https://github.com/khu-vll/cast/blob/HEAD/models/bidir_modeling_crossattn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"857af2a7de44faaa"}},{"code_sha256_prefix":"1dd28bf10048de7d","entry":"Block","repo":"khu-vll/cast","repo_kind":"named_in_paper","path":"models/bidir_modeling_crossattn.py","file_url":"https://github.com/khu-vll/cast/blob/HEAD/models/bidir_modeling_crossattn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1dd28bf10048de7d"}},{"code_sha256_prefix":"445bb3da9e1748a4","entry":"CrossAttentionS2T","repo":"khu-vll/cast","repo_kind":"named_in_paper","path":"models/bidir_modeling_crossattn.py","file_url":"https://github.com/khu-vll/cast/blob/HEAD/models/bidir_modeling_crossattn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"445bb3da9e1748a4"}},{"code_sha256_prefix":"d26fe19969fbc2c2","entry":"STCrossTransformer","repo":"khu-vll/cast","repo_kind":"named_in_paper","path":"models/bidir_modeling_crossattn.py","file_url":"https://github.com/khu-vll/cast/blob/HEAD/models/bidir_modeling_crossattn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d26fe19969fbc2c2"}},{"code_sha256_prefix":"bc71b534fe126be4","entry":"build_dataset","repo":"KHU-VLL/CAST","repo_kind":"named_in_paper","path":"dataset/datasets.py","file_url":"https://github.com/KHU-VLL/CAST/blob/HEAD/dataset/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bc71b534fe126be4"}},{"code_sha256_prefix":"76274d93634ef7d9","entry":"clip_vit_base_patch16_224","repo":"KHU-VLL/CAST","repo_kind":"named_in_paper","path":"models/clip_modelling_finetune.py","file_url":"https://github.com/KHU-VLL/CAST/blob/HEAD/models/clip_modelling_finetune.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"76274d93634ef7d9"}},{"code_sha256_prefix":"29416043c7035e7c","entry":"get_loss_scale_for_deepspeed","repo":"KHU-VLL/CAST","repo_kind":"named_in_paper","path":"engine_for_compomodel.py","file_url":"https://github.com/KHU-VLL/CAST/blob/HEAD/engine_for_compomodel.py","link_basis":"harvester_set","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":"29416043c7035e7c"}},{"code_sha256_prefix":"14b3b13b2e7ee844","entry":"tensor_normalize","repo":"KHU-VLL/CAST","repo_kind":"named_in_paper","path":"dataset/kinetics.py","file_url":"https://github.com/KHU-VLL/CAST/blob/HEAD/dataset/kinetics.py","link_basis":"harvester_set","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":"14b3b13b2e7ee844"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}