{"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/temporal-attentive-alignment-for-large-scale","title":"Temporal Attentive Alignment for Large-Scale Video Domain Adaptation","arxiv_id":"1907.12743","date":"2019-07-30","proceeding":"ICCV 2019 10","authors":["Min-Hung Chen","Zsolt Kira","Ghassan AlRegib","Jaekwon Yoo","Ruxin Chen","Jian Zheng"],"abstract":"Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evaluate performance on small-scale datasets which are saturated. Therefore, we first propose two large-scale video DA datasets with much larger domain discrepancy: UCF-HMDB_full and Kinetics-Gameplay. Second, we investigate different DA integration methods for videos, and show that simultaneously aligning and learning temporal dynamics achieves effective alignment even without sophisticated DA methods. Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on four video DA datasets (e.g. 7.9% accuracy gain over \"Source only\" from 73.9% to 81.8% on \"HMDB --> UCF\", and 10.3% gain on \"Kinetics --> Gameplay\"). The code and data are released at http://github.com/cmhungsteve/TA3N.","url_abs":"https://arxiv.org/abs/1907.12743v6","url_pdf":"https://arxiv.org/pdf/1907.12743v6.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":"temporal-attentive-alignment-for-large-scale","repo_url":"https://github.com/cmhungsteve/TA3N","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"temporal-attentive-alignment-for-large-scale","repo_url":"https://github.com/jonmun/EPIC-KITCHENS-100_UDA_TA3N","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"temporal-attentive-alignment-for-large-scale","repo_url":"https://github.com/mustafa1728/TA3N-Lightning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"temporal-attentive-alignment-for-large-scale","repo_url":"https://github.com/mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"temporal-attentive-alignment-for-large-scale","repo_url":"https://github.com/olivesgatech/TA3N","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-hmdb-ucf-full","task":"Domain Adaptation","dataset":"HMDB --> UCF (full)","model":"TA3N","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"81.79"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-ucf-hmdb-full","task":"Domain Adaptation","dataset":"UCF --> HMDB (full)","model":"TA3N","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"78.33"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-epic","task":"Unsupervised Domain Adaptation","dataset":"EPIC-KITCHENS-100","model":"TA3N","rank_in_archive_order":3,"of":5,"metrics":{"Average Accuracy":"39.9"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-hmdb-ucf","task":"Unsupervised Domain Adaptation","dataset":"HMDB-UCF","model":"TA3N","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"90.54"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-jester-1","task":"Unsupervised Domain Adaptation","dataset":"Jester (Gesture Recognition)","model":"TA3N","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"55.5"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-ucf-hmdb","task":"Unsupervised Domain Adaptation","dataset":"UCF-HMDB","model":"TA3N","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"81.38"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1907.12743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12743"}},"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/olivesgatech/TA3N","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cmhungsteve/TA3N","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mustafa1728/TA3N-Lightning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jonmun/EPIC-KITCHENS-100_UDA_TA3N","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":3,"repositories":1},"listed":{"samples":3,"ran":0,"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":"5dafc748f41191f5","entry":"attentive_entropy","repo":"cmhungsteve/TA3N","repo_kind":"official","path":"loss.py","file_url":"https://github.com/cmhungsteve/TA3N/blob/HEAD/loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5dafc748f41191f5"}},{"code_sha256_prefix":"b1e8dce608f3f658","entry":"cross_entropy_soft","repo":"cmhungsteve/TA3N","repo_kind":"official","path":"loss.py","file_url":"https://github.com/cmhungsteve/TA3N/blob/HEAD/loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b1e8dce608f3f658"}},{"code_sha256_prefix":"0c3c2aa9cf2ac2f0","entry":"dis_MCD","repo":"cmhungsteve/TA3N","repo_kind":"official","path":"loss.py","file_url":"https://github.com/cmhungsteve/TA3N/blob/HEAD/loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c3c2aa9cf2ac2f0"}},{"code_sha256_prefix":"b92a3f112f0c080c","entry":"convert_c3d_tensor_batch","repo":"cmhungsteve/TA3N","repo_kind":"official","path":"dataset_preparation/video2feature.py","file_url":"https://github.com/cmhungsteve/TA3N/blob/HEAD/dataset_preparation/video2feature.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":"b92a3f112f0c080c"}},{"code_sha256_prefix":"468842eca7cd59de","entry":"extract_frame_feature_batch","repo":"cmhungsteve/TA3N","repo_kind":"official","path":"dataset_preparation/video2feature.py","file_url":"https://github.com/cmhungsteve/TA3N/blob/HEAD/dataset_preparation/video2feature.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":"468842eca7cd59de"}},{"code_sha256_prefix":"5fb564b0af4ab527","entry":"get_aggregated_metrics","repo":"mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation","repo_kind":"listed","path":"model.py","file_url":"https://github.com/mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation/blob/HEAD/model.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":"5fb564b0af4ab527"}},{"code_sha256_prefix":"0fb3b659d41d4031","entry":"get_aggregated_metrics_from_dict","repo":"mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation","repo_kind":"listed","path":"model.py","file_url":"https://github.com/mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation/blob/HEAD/model.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":"0fb3b659d41d4031"}},{"code_sha256_prefix":"8376f17deba65583","entry":"im2tensor","repo":"cmhungsteve/TA3N","repo_kind":"official","path":"dataset_preparation/video2feature.py","file_url":"https://github.com/cmhungsteve/TA3N/blob/HEAD/dataset_preparation/video2feature.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":"8376f17deba65583"}},{"code_sha256_prefix":"8651bcfb1198f96d","entry":"randSelectBatch","repo":"cmhungsteve/TA3N","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/cmhungsteve/TA3N/blob/HEAD/utils/utils.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":"8651bcfb1198f96d"}},{"code_sha256_prefix":"0fb8066818796998","entry":"removeDummy","repo":"mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation","repo_kind":"listed","path":"model.py","file_url":"https://github.com/mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation/blob/HEAD/model.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":"0fb8066818796998"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}