{"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/actionformer-localizing-moments-of-actions","title":"ActionFormer: Localizing Moments of Actions with Transformers","arxiv_id":"2202.07925","date":"2022-02-16","proceeding":null,"authors":["Chenlin Zhang","Jianxin Wu","Yin Li"],"abstract":"Self-attention based Transformer models have demonstrated impressive results for image classification and object detection, and more recently for video understanding. Inspired by this success, we investigate the application of Transformer networks for temporal action localization in videos. To this end, we present ActionFormer -- a simple yet powerful model to identify actions in time and recognize their categories in a single shot, without using action proposals or relying on pre-defined anchor windows. ActionFormer combines a multiscale feature representation with local self-attention, and uses a light-weighted decoder to classify every moment in time and estimate the corresponding action boundaries. We show that this orchestrated design results in major improvements upon prior works. Without bells and whistles, ActionFormer achieves 71.0% mAP at tIoU=0.5 on THUMOS14, outperforming the best prior model by 14.1 absolute percentage points. Further, ActionFormer demonstrates strong results on ActivityNet 1.3 (36.6% average mAP) and EPIC-Kitchens 100 (+13.5% average mAP over prior works). Our code is available at http://github.com/happyharrycn/actionformer_release.","url_abs":"https://arxiv.org/abs/2202.07925v2","url_pdf":"https://arxiv.org/pdf/2202.07925v2.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":"actionformer-localizing-moments-of-actions","repo_url":"https://github.com/happyharrycn/actionformer_release","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-in-videos","task_name":"Action Recognition"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"audio-visual-event-localization","task_name":"audio-visual event localization"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"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/temporal-action-localization-on-activitynet","task":"Temporal Action Localization","dataset":"ActivityNet-1.3","model":"ActionFormer (TSP feautures)","rank_in_archive_order":15,"of":33,"metrics":{"mAP":"36.6","mAP IOU@0.5":"54.7","mAP IOU@0.75":"37.8","mAP IOU@0.95":"8.4"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-epic-kitchens","task":"Temporal Action Localization","dataset":"EPIC-KITCHENS-100","model":"ActionFormer (verb)","rank_in_archive_order":4,"of":6,"metrics":{"Avg mAP (0.1-0.5)":"23.5","mAP IOU@0.1":"26.6","mAP IOU@0.2":"25.4","mAP IOU@0.3":"24.2","mAP IOU@0.4":"22.3","mAP IOU@0.5":"19.1"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-thumos14","task":"Temporal Action Localization","dataset":"THUMOS’14","model":"ActionFormer (I3D features)","rank_in_archive_order":13,"of":42,"metrics":{"Avg mAP (0.3:0.7)":"66.8","mAP IOU@0.3":"82.1","mAP IOU@0.4":"77.8","mAP IOU@0.5":"71.0","mAP IOU@0.6":"59.4","mAP IOU@0.7":"43.9"},"uses_additional_data":false},{"leaderboard":"/sota/audio-visual-event-localization-on-unav-100","task":"audio-visual event localization","dataset":"UnAV-100","model":"ActionFormer","rank_in_archive_order":2,"of":2,"metrics":{" mAP":"42.2","AP@IOU0.5":"43.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2202.07925","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}