{"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-feature-fusion-transformer-for","title":"Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation","arxiv_id":"2210.12649","date":"2022-10-23","proceeding":null,"authors":["Zeyun Zhong","David Schneider","Michael Voit","Rainer Stiefelhagen","Jürgen Beyerer"],"abstract":"Although human action anticipation is a task which is inherently multi-modal, state-of-the-art methods on well known action anticipation datasets leverage this data by applying ensemble methods and averaging scores of unimodal anticipation networks. In this work we introduce transformer based modality fusion techniques, which unify multi-modal data at an early stage. Our Anticipative Feature Fusion Transformer (AFFT) proves to be superior to popular score fusion approaches and presents state-of-the-art results outperforming previous methods on EpicKitchens-100 and EGTEA Gaze+. Our model is easily extensible and allows for adding new modalities without architectural changes. Consequently, we extracted audio features on EpicKitchens-100 which we add to the set of commonly used features in the community.","url_abs":"https://arxiv.org/abs/2210.12649v1","url_pdf":"https://arxiv.org/pdf/2210.12649v1.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-feature-fusion-transformer-for","repo_url":"https://github.com/zeyun-zhong/afft","is_official":1,"mentioned_in_paper":1,"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":"AFFT","rank_in_archive_order":5,"of":9,"metrics":{"Recall@5":"18.5"},"uses_additional_data":false},{"leaderboard":"/sota/action-anticipation-on-epic-kitchens-100-test","task":"Action Anticipation","dataset":"EPIC-KITCHENS-100 (test)","model":"AFFT","rank_in_archive_order":3,"of":8,"metrics":{"recall@5":"14.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.12649","atlas_url":"https://app.syntology.ai/?focus=2210.12649","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}