{"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/anticipative-video-transformer","title":"Anticipative Video Transformer","arxiv_id":"2106.02036","date":"2021-06-03","proceeding":"ICCV 2021 10","authors":["Rohit Girdhar","Kristen Grauman"],"abstract":"We propose Anticipative Video Transformer (AVT), an end-to-end attention-based video modeling architecture that attends to the previously observed video in order to anticipate future actions. We train the model jointly to predict the next action in a video sequence, while also learning frame feature encoders that are predictive of successive future frames' features. Compared to existing temporal aggregation strategies, AVT has the advantage of both maintaining the sequential progression of observed actions while still capturing long-range dependencies--both critical for the anticipation task. Through extensive experiments, we show that AVT obtains the best reported performance on four popular action anticipation benchmarks: EpicKitchens-55, EpicKitchens-100, EGTEA Gaze+, and 50-Salads; and it wins first place in the EpicKitchens-100 CVPR'21 challenge.","url_abs":"https://arxiv.org/abs/2106.02036v2","url_pdf":"https://arxiv.org/pdf/2106.02036v2.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":"anticipative-video-transformer","repo_url":"https://github.com/facebookresearch/AVT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-anticipation","task_name":"Action Anticipation"}],"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":"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":[{"leaderboard":"/sota/action-anticipation-on-epic-kitchens-100","task":"Action Anticipation","dataset":"EPIC-KITCHENS-100","model":"AVT+","rank_in_archive_order":7,"of":9,"metrics":{"Recall@5":"15.9"},"uses_additional_data":false},{"leaderboard":"/sota/action-anticipation-on-epic-kitchens-100-test","task":"Action Anticipation","dataset":"EPIC-KITCHENS-100 (test)","model":"AVT++","rank_in_archive_order":2,"of":8,"metrics":{"recall@5":"16.7"},"uses_additional_data":true},{"leaderboard":"/sota/action-anticipation-on-epic-kitchens-100-test","task":"Action Anticipation","dataset":"EPIC-KITCHENS-100 (test)","model":"AVT+","rank_in_archive_order":6,"of":8,"metrics":{"recall@5":"12.6"},"uses_additional_data":false},{"leaderboard":"/sota/action-anticipation-on-epic-kitchens-55-seen","task":"Action Anticipation","dataset":"EPIC-KITCHENS-55 (Seen test set (S1))","model":"AVT+","rank_in_archive_order":2,"of":7,"metrics":{"Top 1 Accuracy - Act.":"16.84","Top 1 Accuracy - Noun":"20.16","Top 1 Accuracy - Verb":"34.36","Top 5 Accuracy - Act.":"36.52","Top 5 Accuracy - Noun":"51.57","Top 5 Accuracy - Verb":"80.03"},"uses_additional_data":false},{"leaderboard":"/sota/action-anticipation-on-epic-kitchens-55-1","task":"Action Anticipation","dataset":"EPIC-KITCHENS-55 (Unseen test set (S2)","model":"AVT+","rank_in_archive_order":2,"of":7,"metrics":{"Top 1 Accuracy - Act.":"10.41","Top 1 Accuracy - Noun":"15.64","Top 1 Accuracy - Verb":"30.66","Top 5 Accuracy - Act.":"24.27","Top 5 Accuracy - Noun":"40.76","Top 5 Accuracy - Verb":"72.17"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.02036","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02036"}},"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/facebookresearch/AVT","reach":null}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"6fce32ed337a95ea","entry":"AVTh","repo":"facebookresearch/AVT","repo_kind":"official","path":"models/future_prediction.py","file_url":"https://github.com/facebookresearch/AVT/blob/HEAD/models/future_prediction.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6fce32ed337a95ea"}},{"code_sha256_prefix":"af9c1829ef2993e6","entry":"KmeansAssigner","repo":"facebookresearch/AVT","repo_kind":"official","path":"models/future_prediction.py","file_url":"https://github.com/facebookresearch/AVT/blob/HEAD/models/future_prediction.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"af9c1829ef2993e6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}