{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:24Z","timestamp":1778048364337,"version":"3.51.4"},"reference-count":85,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00384","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3939-3950","source":"Crossref","is-referenced-by-count":0,"title":["CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding"],"prefix":"10.1109","author":[{"given":"Fevziye Irem","family":"Eyiokur","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dogucan","family":"Yaman","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haz\u0131m Kemal","family":"Ekenel","sequence":"additional","affiliation":[{"name":"Istanbul Technical University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Waibel","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Phi-4 technical report","author":"Abdin","year":"2024"},{"key":"ref2","article-title":"Embodied Multimodal Referring Expressions Generation","volume-title":"PhD thesis","author":"Alalyani","year":"2024"},{"issue":"2","key":"ref3","first-page":"3","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","volume":"1","author":"Bai","year":"2023"},{"key":"ref4","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-0394.2012.00622.x"},{"key":"ref6","article-title":"Paligemma: A versatile 3b vlm for transfer","author":"Beyer","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-011-9263-y"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2019.05.035"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00056"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00142"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref15","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"International Conference on Machine Learning","author":"Cho"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25075-0_43"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00212"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105151"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref22","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00552"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00066"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","article-title":"Grec: Generalized referring expression comprehension","author":"He","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.35"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1027933.1027964"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1527"},{"key":"ref30","article-title":"Eqa-mx: Embodied question answering using multimodal expression","volume-title":"The Twelfth International Conference on Learning Representations","author":"Islam"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-srw.23"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-90525-5_17"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00180"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.05.004"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref38","article-title":"Understanding embodied reference with touch-line transformer","volume-title":"The Eleventh International Conference on Learning Representations","author":"Li"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref40","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28186"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00843"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN57019.2023.10309487"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2013.12.006"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02561"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref50","article-title":"On the convergence of adam and beyond","author":"Reddi","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02689"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_12"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70773"},{"issue":"1","key":"ref55","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"The journal of machine learning research"},{"key":"ref56","article-title":"Paligemma 2: A family of versatile vlms for transfer","author":"Steiner","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48762-X_94"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/319463.319464"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/971478.971505"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389771"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303165"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01914"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3858"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00196"},{"key":"ref65","article-title":"Pointing gesture understanding via visual prompting and visual question answering for interactive robot navigation","volume-title":"First Workshop on Vision-Language Models for Navigation and Manipulation at ICRA 2024","author":"Tanada"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3556624"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01998"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2162740"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1162\/PRES_a_00176"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2006.889491"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/274644.274666"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_18"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0663"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref78","article-title":"Crema: Generalizable and efficient video-language reasoning via multimodal modular fusion","author":"Yu","year":"2024"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref81","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.3390\/app12178654"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11247498"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01263-4"},{"key":"ref85","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"}],"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\/11492458.pdf?arnumber=11492458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:56:42Z","timestamp":1778047002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492458\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00384","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}