{"id":32435,"date":"2026-01-21T17:01:57","date_gmt":"2026-01-21T17:01:57","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/gated-temporal-diffusion-for-stochastic-long-term-dense-anticipation\/"},"modified":"2026-06-08T13:20:30","modified_gmt":"2026-06-08T13:20:30","slug":"gated-temporal-diffusion-for-stochastic-long-term-dense-anticipation","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/gated-temporal-diffusion-for-stochastic-long-term-dense-anticipation\/","title":{"rendered":"Gated Temporal Diffusion for Stochastic Long-Term Dense Anticipation"},"content":{"rendered":"<p>Long-term action anticipation has become an important task for many applications such as autonomous driving and human-robot interaction. Unlike short-term anticipation, predicting more actions into the future imposes a real challenge with the increasing uncertainty in longer horizons. While there has been a significant progress in predicting more actions into the future, most of the proposed methods address the task in a deterministic setup and ignore the underlying uncertainty. In this paper, we propose a novel Gated Temporal Diffusion ({GTD}) network that models the uncertainty of both the observation and the future predictions. As generator, we introduce a Gated Anticipation Network ({GTAN}) to model both observed and unobserved frames of a video in a mutual representation. On the one hand, using a mutual representation for past and future allows us to jointly model ambiguities in the observation and future, while on the other hand {GTAN} can by design treat the observed and unobserved parts differently and steer the information flow between them. Our model achieves state-of-the-art results on the Breakfast, Assembly101 and 50Salads datasets in both stochastic and deterministic settings.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Long-term action anticipation has become an important task for many applications such as autonomous driving and human-robot interaction. Unlike short-term anticipation, predicting more actions into the future imposes a real challenge with the increasing uncertainty in longer horizons. While there has been a significant progress in predicting more actions into the future, most of the proposed methods address the task in a deterministic setup and ignore the underlying uncertainty. In [&hellip;]<\/p>\n","protected":false},"author":12,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[32],"class_list":["post-32435","publication","type-publication","status-publish","hentry","publication-type-inproceedings"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32435","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/12"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32435\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=32435"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=32435"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}