{"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/hat-history-augmented-anchor-transformer-for","title":"HAT: History-Augmented Anchor Transformer for Online Temporal Action Localization","arxiv_id":"2408.06437","date":"2024-08-12","proceeding":null,"authors":["Sakib Reza","Yuexi Zhang","Mohsen Moghaddam","Octavia Camps"],"abstract":"Online video understanding often relies on individual frames, leading to frame-by-frame predictions. Recent advancements such as Online Temporal Action Localization (OnTAL), extend this approach to instance-level predictions. However, existing methods mainly focus on short-term context, neglecting historical information. To address this, we introduce the History-Augmented Anchor Transformer (HAT) Framework for OnTAL. By integrating historical context, our framework enhances the synergy between long-term and short-term information, improving the quality of anchor features crucial for classification and localization. We evaluate our model on both procedural egocentric (PREGO) datasets (EGTEA and EPIC) and standard non-PREGO OnTAL datasets (THUMOS and MUSES). Results show that our model outperforms state-of-the-art approaches significantly on PREGO datasets and achieves comparable or slightly superior performance on non-PREGO datasets, underscoring the importance of leveraging long-term history, especially in procedural and egocentric action scenarios. Code is available at: https://github.com/sakibreza/ECCV24-HAT/","url_abs":"https://arxiv.org/abs/2408.06437v1","url_pdf":"https://arxiv.org/pdf/2408.06437v1.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":"hat-history-augmented-anchor-transformer-for","repo_url":"https://github.com/sakibreza/eccv24-hat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2408.06437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06437"}},"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/sakibreza/eccv24-hat","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/sakibreza/ECCV24-HAT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":11,"ran_fixture":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":14,"ran":13,"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":"f03f1bd0ad7a25d8","entry":"HistoryUnit","repo":"sakibreza/ECCV24-HAT","repo_kind":"official","path":"models.py","file_url":"https://github.com/sakibreza/ECCV24-HAT/blob/HEAD/models.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":"f03f1bd0ad7a25d8"}},{"code_sha256_prefix":"70e832b4db258152","entry":"MYNET","repo":"sakibreza/ECCV24-HAT","repo_kind":"official","path":"models.py","file_url":"https://github.com/sakibreza/ECCV24-HAT/blob/HEAD/models.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":"70e832b4db258152"}},{"code_sha256_prefix":"14516b65574f5ecf","entry":"PositionalEncoding","repo":"sakibreza/ECCV24-HAT","repo_kind":"official","path":"models.py","file_url":"https://github.com/sakibreza/ECCV24-HAT/blob/HEAD/models.py","link_basis":"first_harvest_node","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":"14516b65574f5ecf"}},{"code_sha256_prefix":"3c7815878a239220","entry":"box_include","repo":"sakibreza/eccv24-hat","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/sakibreza/eccv24-hat/blob/HEAD/dataset.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":"3c7815878a239220"}},{"code_sha256_prefix":"76cad4b96bed8a89","entry":"calc_iou","repo":"sakibreza/eccv24-hat","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/sakibreza/eccv24-hat/blob/HEAD/dataset.py","link_basis":"first_harvest_node","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":"76cad4b96bed8a89"}},{"code_sha256_prefix":"fa2555ecb9baeda4","entry":"cls_loss_func","repo":"sakibreza/eccv24-hat","repo_kind":"official","path":"loss_func.py","file_url":"https://github.com/sakibreza/eccv24-hat/blob/HEAD/loss_func.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":"fa2555ecb9baeda4"}},{"code_sha256_prefix":"4010b82fd0123b85","entry":"cls_loss_func_","repo":"sakibreza/eccv24-hat","repo_kind":"official","path":"loss_func.py","file_url":"https://github.com/sakibreza/eccv24-hat/blob/HEAD/loss_func.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":"4010b82fd0123b85"}},{"code_sha256_prefix":"b976a341da79fc62","entry":"get_blocked_videos","repo":"sakibreza/eccv24-hat","repo_kind":"official","path":"Evaluation/utils.py","file_url":"https://github.com/sakibreza/eccv24-hat/blob/HEAD/Evaluation/utils.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":"b976a341da79fc62"}},{"code_sha256_prefix":"81aab88321de62c2","entry":"interpolated_prec_rec","repo":"sakibreza/eccv24-hat","repo_kind":"official","path":"Evaluation/utils.py","file_url":"https://github.com/sakibreza/eccv24-hat/blob/HEAD/Evaluation/utils.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"81aab88321de62c2"}},{"code_sha256_prefix":"6feb659b1cc2c1e8","entry":"load_json","repo":"sakibreza/eccv24-hat","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/sakibreza/eccv24-hat/blob/HEAD/dataset.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":"6feb659b1cc2c1e8"}},{"code_sha256_prefix":"44f4e934798b5b3f","entry":"non_max_suppression","repo":"sakibreza/eccv24-hat","repo_kind":"official","path":"iou_utils.py","file_url":"https://github.com/sakibreza/eccv24-hat/blob/HEAD/iou_utils.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":"44f4e934798b5b3f"}},{"code_sha256_prefix":"a7c0d044f47c77b5","entry":"regress_loss_func","repo":"sakibreza/eccv24-hat","repo_kind":"official","path":"loss_func.py","file_url":"https://github.com/sakibreza/eccv24-hat/blob/HEAD/loss_func.py","link_basis":"first_harvest_node","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":"a7c0d044f47c77b5"}},{"code_sha256_prefix":"d0744a2fe3151508","entry":"segment_iou","repo":"sakibreza/eccv24-hat","repo_kind":"official","path":"Evaluation/utils.py","file_url":"https://github.com/sakibreza/eccv24-hat/blob/HEAD/Evaluation/utils.py","link_basis":"plan_row","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":"d0744a2fe3151508"}},{"code_sha256_prefix":"98763476d52320c5","entry":"check_overlap_proposal","repo":"sakibreza/eccv24-hat","repo_kind":"official","path":"iou_utils.py","file_url":"https://github.com/sakibreza/eccv24-hat/blob/HEAD/iou_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":"98763476d52320c5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}