{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:14Z","timestamp":1778048354892,"version":"3.51.4"},"reference-count":82,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00783","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"8113-8123","source":"Crossref","is-referenced-by-count":0,"title":["Scalable Video Action Anticipation with Cross Linear Attentive Memory"],"prefix":"10.1109","author":[{"given":"Zeyun","family":"Zhong","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel","family":"Martin","sequence":"additional","affiliation":[{"name":"Fraunhofer IOSB"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Schneider","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David J.","family":"Lerch","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengzhi","family":"Wu","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frederik","family":"Diederichs","sequence":"additional","affiliation":[{"name":"Fraunhofer IOSB"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juergen","family":"Gall","sequence":"additional","affiliation":[{"name":"Lamarr Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00fcrgen","family":"Beyerer","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00949"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02209"},{"key":"ref3","article-title":"Token merging: Your vit but faster","author":"Bolya","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref6","article-title":"Internvideo-ego4d: A pack of champion solutions to ego4d challenges","author":"Chen","year":"2022"},{"key":"ref7","article-title":"Videollm: Modeling video sequence with large language models","author":"Chen","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01930"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01742"},{"key":"ref10","article-title":"Rethinking attention with performers","author":"Choromanski","year":"2021","journal-title":"ICLR"},{"key":"ref11","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref12","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"Damen","year":"2018","journal-title":"ECCV"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2991965"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_26"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00560"},{"key":"ref17","article-title":"Hungry hungry hippos: Towards language modeling with state space models","author":"Fu","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00635"},{"key":"ref19","article-title":"Forecasting future action sequences with neural memory networks","author":"Gammulle","year":"2019","journal-title":"BMVC"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.92"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_17"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01799"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00306"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref27","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref28","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00085"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_12"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196548"},{"key":"ref33","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"ICML","author":"Jaegle","year":"2021"},{"key":"ref34","author":"Jiang","year":"2014","journal-title":"Thumos challenge: Action recognition with a large number of classes"},{"key":"ref35","first-page":"5156","article-title":"Transformers are rnns: Fast autoregressive transformers with linear attention","volume-title":"ICML","author":"Katharopoulos","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01016"},{"key":"ref37","first-page":"140","article-title":"Palm: Predicting actions through language models","volume-title":"ECCV","author":"Kim","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref39","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li","year":"2023"},{"key":"ref40","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021","journal-title":"CVPR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00599"},{"key":"ref42","article-title":"Long range language modeling via gated state spaces","author":"Mehta","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01758"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_32"},{"key":"ref45","volume-title":"Introducing triton: Open-source gpu programming for neural networks"},{"key":"ref46","article-title":"Random feature attention","author":"Peng","year":"2021"},{"key":"ref47","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.473"},{"key":"ref49","article-title":"Scaling transnormer to 175 billion parameters","author":"Qin","year":"2023"},{"issue":"8","key":"ref50","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref51","article-title":"Pedestrian Action Anticipation using Contextual Feature Fusion in Stacked RNNs","author":"Rasouli","year":"2019","journal-title":"BMVC"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00660"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21236\/ADA164453"},{"key":"ref54","first-page":"12786","article-title":"Tokenlearner: Adaptive space-time tokenization for videos","author":"Ryoo","year":"2021","journal-title":"NeuerIPS"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01828"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_10"},{"key":"ref57","article-title":"Simplified state space layers for sequence modeling","author":"Smith","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref59","article-title":"Retentive network: A successor to transformer for large language models","author":"Sun","year":"2023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref61","article-title":"Attention is All you Need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.18"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01271"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.087"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"ref68","article-title":"Videollm-mod: Efficient video-language streaming with mixture-of-depths vision computation","author":"Wu","year":"2024","journal-title":"NeurIPS"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3040521"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00563"},{"key":"ref71","first-page":"1086","article-title":"Long short-term transformer for online action detection","author":"Xu","year":"2021","journal-title":"NeurIPS"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01240"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00229"},{"key":"ref74","article-title":"Gated linear attention transformers with hardware-efficient training","author":"Yang","year":"2024","journal-title":"ICML"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_26"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.146"},{"key":"ref77","article-title":"Antgpt: Can large language models help long-term action anticipation from videos?","author":"Zhao","year":"2023"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_28"},{"key":"ref79","article-title":"A survey on deep learning techniques for action anticipation","author":"Zhong","year":"2023"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00601"},{"key":"ref81","article-title":"Diffant: Diffusion models for action anticipation","author":"Zhong","year":"2023"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01727"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11491945.pdf?arnumber=11491945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:53:04Z","timestamp":1778046784000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11491945\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00783","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}