{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T00:55:08Z","timestamp":1773536108517,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2441587"],"award-info":[{"award-number":["2441587"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,16]]},"DOI":"10.1145\/3757279.3785601","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:27:38Z","timestamp":1773102458000},"page":"503-512","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Embodied Referring Expression Comprehension in Human-Robot Interaction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4207-5863","authenticated-orcid":false,"given":"Md Mofijul","family":"Islam","sequence":"first","affiliation":[{"name":"University of Virginia, Charlottesville, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6294-5888","authenticated-orcid":false,"given":"Alexi","family":"Gladstone","sequence":"additional","affiliation":[{"name":"University of Virginia, Charlottesville, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8784-8933","authenticated-orcid":false,"given":"Sujan","family":"Sarker","sequence":"additional","affiliation":[{"name":"University of Virginia, Charlottesville, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7633-875X","authenticated-orcid":false,"given":"Ganesh","family":"Nanduru","sequence":"additional","affiliation":[{"name":"University of Virginia, Charlottesville, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6139-5283","authenticated-orcid":false,"given":"Md","family":"Fahim","sequence":"additional","affiliation":[{"name":"University of Dhaka, Dhaka, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5277-2835","authenticated-orcid":false,"given":"Keyan","family":"Du","sequence":"additional","affiliation":[{"name":"University of Virginia, Charlottesville, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6621-9003","authenticated-orcid":false,"given":"Aman","family":"Chadha","sequence":"additional","affiliation":[{"name":"Apple, Cupertino, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0133-1234","authenticated-orcid":false,"given":"Tariq","family":"Iqbal","sequence":"additional","affiliation":[{"name":"University of Virginia, Charlottesville, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"e_1_3_2_2_2_1","unstructured":"Alexander A Alemi Ian Fischer Joshua V Dillon and Kevin Murphy. 2016. Deep variational information bottleneck. arXiv preprint arXiv:1612.00410."},{"key":"e_1_3_2_2_3_1","volume-title":"VQA: Visual Question Answering. In International Conference on Computer Vision (ICCV).","author":"Antol Stanislaw","year":"2015","unstructured":"Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C. Lawrence Zitnick, and Devi Parikh. 2015. VQA: Visual Question Answering. In International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_2_4_1","volume-title":"Primate vocalization, gesture, and the evolution of human language. Current anthropology, 49, 6","author":"Arbib Michael A","year":"2008","unstructured":"Michael A Arbib, Katja Liebal, and Simone Pika. 2008. Primate vocalization, gesture, and the evolution of human language. Current anthropology, 49, 6 (2008), 1053\u20131076."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00142"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1\u201310","author":"Das Abhishek","year":"2018","unstructured":"Abhishek Das, Samyak Datta, Georgia Gkioxari, Stefan Lee, Devi Parikh, and Dhruv Batra. 2018. Embodied question answering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1\u201310."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2023.1110534"},{"key":"e_1_3_2_2_8_1","volume-title":"Corey Lynch, Aakanksha Chowdhery, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, et al.","author":"Driess Danny","year":"2023","unstructured":"Danny Driess, Fei Xia, Mehdi SM Sajjadi, Corey Lynch, Aakanksha Chowdhery, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, et al. 2023. Palm-e: An embodied multimodal language model."},{"key":"e_1_3_2_2_9_1","volume-title":"Haz\u0131m Kemal Ekenel, and Alexander Waibel","author":"Eyiokur Fevziye Irem","year":"2025","unstructured":"Fevziye Irem Eyiokur, Dogucan Yaman, Haz\u0131m Kemal Ekenel, and Alexander Waibel. 2025. CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding. arxiv:2507.21888. arxiv:2507.21888"},{"key":"e_1_3_2_2_10_1","volume-title":"Are you talking to a machine? dataset and methods for multilingual image question. Advances in neural information processing systems, 28","author":"Gao Haoyuan","year":"2015","unstructured":"Haoyuan Gao, Junhua Mao, Jie Zhou, Zhiheng Huang, Lei Wang, and Wei Xu. 2015. Are you talking to a machine? dataset and methods for multilingual image question. Advances in neural information processing systems, 28 (2015)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3773895"},{"key":"e_1_3_2_2_13_1","volume-title":"2025 IEEE International Conference on Robotics and Automation (ICRA). 11868\u201311875","author":"Haley","unstructured":"Haley N. Green and Tariq Iqbal. 2025. Using Physiological Measures, Gaze, and Facial Expressions to Model Human Trust in a Robot Partner. In 2025 IEEE International Conference on Robotics and Automation (ICRA). 11868\u201311875."},{"key":"e_1_3_2_2_14_1","volume-title":"MMRL: Multi-Modal Representation Learning for Vision-Language Models. arxiv:2503.08497. arxiv:2503.08497","author":"Guo Yuncheng","year":"2025","unstructured":"Yuncheng Guo and Xiaodong Gu. 2025. MMRL: Multi-Modal Representation Learning for Vision-Language Models. arxiv:2503.08497. arxiv:2503.08497"},{"key":"e_1_3_2_2_15_1","unstructured":"Zhiwei Hao Jianyuan Guo Li Shen Yong Luo Han Hu and Yonggang Wen. 2024. ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning. arxiv:2410.17779."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_17_1","volume-title":"The 27th Workshop on the Semantics and Pragmatics of Dialogue (SemDial).","author":"Higger Mark","year":"2023","unstructured":"Mark Higger, Polina Rygina, Logan Daigler, Lara Ferreira Bezerra, Zhao Han, and Tom Williams. 2023. Toward Open-World Human-Robot Interaction: What Types of Gestures Are Used in Task-Based Open-World Referential Communication? In The 27th Workshop on the Semantics and Pragmatics of Dialogue (SemDial)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_2_19_1","volume-title":"Proceedings, Part IV 14","author":"Huang Gao","year":"2016","unstructured":"Gao Huang, Yu Sun, Zhuang Liu, Daniel Sedra, and Kilian Q Weinberger. 2016. Deep networks with stochastic depth. In Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part IV 14. 646\u2013661."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794054"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561763"},{"key":"e_1_3_2_2_22_1","volume-title":"PATRON: Perspective-aware Multitask Model for Referring Expression Grounding using Embodied Multimodal Cues.","author":"Islam Md Mofijul","year":"2022","unstructured":"Md Mofijul Islam, Alexi Gladstone, and Tariq Iqbal. 2022. PATRON: Perspective-aware Multitask Model for Referring Expression Grounding using Embodied Multimodal Cues."},{"key":"e_1_3_2_2_23_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Islam Md Mofijul","year":"2024","unstructured":"Md Mofijul Islam, Alexi Gladstone, Riashat Islam, and Tariq Iqbal. 2024. EQA-MX: Embodied Question Answering using Multimodal Expression. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340987"},{"key":"e_1_3_2_2_25_1","volume-title":"Multi-GAT: A Graphical Attention-based Hierarchical Multimodal Representation Learning Approach for Human Activity Recognition","author":"Islam Md Mofijul","unstructured":"Md Mofijul Islam and Tariq Iqbal. 2021. Multi-GAT: A Graphical Attention-based Hierarchical Multimodal Representation Learning Approach for Human Activity Recognition. In IEEE Robotics and Automation Letters (RA-L)."},{"key":"e_1_3_2_2_26_1","volume-title":"Alexi Gladstone, Haley N Green, and Tariq Iqbal.","author":"Islam Md Mofijul","year":"2022","unstructured":"Md Mofijul Islam, Reza Manuel Mirzaiee, Alexi Gladstone, Haley N Green, and Tariq Iqbal. 2022. CAESAR: A Multimodal Simulator for Generating Embodied Relationship Grounding Dataset. In NeurIPS."},{"key":"e_1_3_2_2_27_1","volume-title":"International Conference on Artificial Intelligence and Statistics. 8699\u20138722","author":"Islam Riashat","year":"2023","unstructured":"Riashat Islam, Hongyu Zang, Manan Tomar, Aniket Didolkar, Md Mofijul Islam, Samin Yeasar Arnob, Tariq Iqbal, Xin Li, Anirudh Goyal, Nicolas Heess, et al. 2023. Representation Learning in Deep RL via Discrete Information Bottleneck. In International Conference on Artificial Intelligence and Statistics. 8699\u20138722."},{"key":"e_1_3_2_2_28_1","volume-title":"Vima: General robot manipulation with multimodal prompts. arXiv.","author":"Jiang Yunfan","year":"2022","unstructured":"Yunfan Jiang, Agrim Gupta, Zichen Zhang, Guanzhi Wang, Yongqiang Dou, Yanjun Chen, Li Fei-Fei, Anima Anandkumar, Yuke Zhu, and Linxi Fan. 2022. Vima: General robot manipulation with multimodal prompts. arXiv."},{"key":"e_1_3_2_2_29_1","volume-title":"International Conference on Machine Learning. 5583\u20135594","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. Vilt: Vision-and-language transformer without convolution or region supervision. In International Conference on Machine Learning. 5583\u20135594."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.5220\/0010871200003124"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3043167"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David A Shamma et al. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision 123 1 (2017) 32\u201373.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Shuhei Kurita Naoki Katsura and Eri Onami. 2023. RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D. arxiv:2308.12035. arxiv:2308.12035","DOI":"10.1109\/ICCV51070.2023.01396"},{"key":"e_1_3_2_2_34_1","unstructured":"Jae Hee Lee Matthias Kerzel Kyra Ahrens Cornelius Weber and Stefan Wermter. 2022. What is Right for Me is Not Yet Right for You: A Dataset for Grounding Relative Directions via Multi-Task Learning. arXiv preprint arXiv:2205.02671."},{"key":"e_1_3_2_2_35_1","unstructured":"Junnan Li Dongxu Li Silvio Savarese and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597."},{"key":"e_1_3_2_2_36_1","volume-title":"International Conference on Machine Learning. 12888\u201312900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning. 12888\u201312900."},{"key":"e_1_3_2_2_37_1","unstructured":"Liunian Harold Li Mark Yatskar Da Yin Cho-Jui Hsieh and Kai-Wei Chang. 2019. VisualBERT: A Simple and Performant Baseline for Vision and Language. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"e_1_3_2_2_39_1","volume-title":"Twelve-month-olds point to share attention and interest. Developmental science, 7, 3","author":"Liszkowski Ulf","year":"2004","unstructured":"Ulf Liszkowski, Malinda Carpenter, Anne Henning, Tricia Striano, and Michael Tomasello. 2004. Twelve-month-olds point to share attention and interest. Developmental science, 7, 3 (2004), 297\u2013307."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1207\/s15327647jcd0702_2"},{"key":"e_1_3_2_2_41_1","unstructured":"Hao Liu Lisa Lee Kimin Lee and Pieter Abbeel. 2022. Instruction-following agents with multimodal transformer. arXiv preprint arXiv:2210.13431."},{"key":"e_1_3_2_2_42_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual Instruction Tuning. arxiv:2304.08485."},{"key":"e_1_3_2_2_43_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled Weight Decay Regularization. In ICLR."},{"key":"e_1_3_2_2_44_1","unstructured":"Jiasen Lu Dhruv Batra Devi Parikh and Stefan Lee. 2019. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_45_1","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume":"35","author":"Lu Pan","year":"2022","unstructured":"Pan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. 2022. Learn to explain: Multimodal reasoning via thought chains for science question answering. Advances in Neural Information Processing Systems, 35 (2022), 2507\u20132521.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1515\/9783110874259.351"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139108669"},{"key":"e_1_3_2_2_48_1","volume-title":"https:\/\/azure.microsoft.com\/en-us\/products\/kinect-dk Accessed","author":"Kinect Azure","year":"2025","unstructured":"Microsoft. 2025. Azure Kinect. https:\/\/azure.microsoft.com\/en-us\/products\/kinect-dk Accessed: July 28, 2025"},{"key":"e_1_3_2_2_49_1","volume-title":"Ohmni Telepresence Robot. https:\/\/ohmnilabs.com\/products\/ohmni-telepresence-robot\/ Accessed","year":"2025","unstructured":"OhmniLabs. 2025. Ohmni Telepresence Robot. https:\/\/ohmnilabs.com\/products\/ohmni-telepresence-robot\/ Accessed: July 28, 2025"},{"key":"e_1_3_2_2_50_1","volume-title":"https:\/\/pupil-labs.com\/ Accessed","author":"Labs Pupil","year":"2025","unstructured":"Pupil Labs. 2025. Pupil Labs. https:\/\/pupil-labs.com\/ Accessed: July 28, 2025"},{"key":"e_1_3_2_2_51_1","volume-title":"International Conference on Machine Learning. 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. 8748\u20138763."},{"key":"e_1_3_2_2_52_1","volume-title":"Safety and Normative Behaviors in Human-Robot Interaction Workshop.","author":"Sarker Sujan","year":"2024","unstructured":"Sujan Sarker, Haley N Green, Mohammad Samin Yasar, and Tariq Iqbal. 2024. Cohrt: A collaboration system for human-robot teamwork. Robotics Science and Systems (RSS), Safety and Normative Behaviors in Human-Robot Interaction Workshop."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3415247"},{"key":"e_1_3_2_2_55_1","volume-title":"Natsgd: A dataset with speech, gestures, and demonstrations for robot learning in natural human-robot interaction. arXiv preprint arXiv:2403.02274.","author":"Shrestha Snehesh","year":"2024","unstructured":"Snehesh Shrestha, Yantian Zha, Saketh Banagiri, Ge Gao, Yiannis Aloimonos, and Cornelia Fermuller. 2024. Natsgd: A dataset with speech, gestures, and demonstrations for robot learning in natural human-robot interaction. arXiv preprint arXiv:2403.02274."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"crossref","unstructured":"Anas Shrinah Masoud S Bahraini Fahad Khan Seemal Asif Niels Lohse and Kerstin Eder. 2024. On the design of human-robot collaboration gestures. arXiv preprint arXiv:2402.19058.","DOI":"10.54941\/ahfe1005166"},{"key":"e_1_3_2_2_58_1","unstructured":"Ravid Shwartz-Ziv and Naftali Tishby. 2017. Opening the black box of deep neural networks via information. arXiv preprint arXiv:1703.00810."},{"key":"e_1_3_2_2_59_1","unstructured":"Stephanie Stacy Qingyi Zhao Minglu Zhao Max Kleiman-Weiner and Tao Gao. 2020. Intuitive Signaling Through an\" Imagined We\u2019\".. In CogSci."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20335"},{"key":"e_1_3_2_2_61_1","unstructured":"Ning Tang Stephanie Stacy Minglu Zhao Gabriel Marquez and Tao Gao. 2020. Bootstrapping an Imagined We for Cooperation.. In CogSci."},{"key":"e_1_3_2_2_62_1","unstructured":"Zineng Tang Lingjun Mao and Alane Suhr. 2024. Grounding Language in Multi-Perspective Referential Communication. arxiv:2410.03959. arxiv:2410.03959"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794287"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"crossref","unstructured":"Naftali Tishby and Noga Zaslavsky. 2015. Deep learning and the information bottleneck principle. In 2015 ieee information theory workshop (itw). 1\u20135.","DOI":"10.1109\/ITW.2015.7133169"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7551.001.0001"},{"key":"e_1_3_2_2_66_1","unstructured":"Frederik Tr\u00e4uble Anirudh Goyal Nasim Rahaman Michael Mozer Kenji Kawaguchi Yoshua Bengio and Bernhard Sch\u00f6lkopf. 2022. Discrete Key-Value Bottleneck."},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01557"},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"e_1_3_2_2_69_1","unstructured":"Hao Yang Can Gao Hao L\u00edu Xinyan Xiao Yanyan Zhao and Bing Qin. 2023. UNIMO-3: Multi-granularity Interaction for Vision-Language Representation Learning. arxiv:2305.13697."},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3058917"},{"key":"e_1_3_2_2_71_1","volume-title":"VADER: Vector-Quantized Generative Adversarial Network for Motion Prediction. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS).","author":"Yasar Mohammad Samin","year":"2023","unstructured":"Mohammad Samin Yasar and Tariq Iqbal. 2023. VADER: Vector-Quantized Generative Adversarial Network for Motion Prediction. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)."},{"key":"e_1_3_2_2_72_1","volume-title":"Md Mofijul Islam*, and Tariq Iqbal","author":"Mohammad Samin","year":"2022","unstructured":"Mohammad Samin Yasar*, Md Mofijul Islam*, and Tariq Iqbal. 2022. IMPRINT: Interactional Dynamics-aware Motion Prediction in Teams using Multimodal Context. In ACM Transactions on Human-Robot Interaction (under-review)."},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610977.3635006"},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00647"},{"key":"e_1_3_2_2_75_1","unstructured":"Licheng Yu Eunbyung Park Alexander C Berg and Tamara L Berg. 2015. Visual madlibs: Fill in the blank image generation and question answering. arXiv preprint arXiv:1506.00278."},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108493"},{"key":"e_1_3_2_2_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"}],"event":{"name":"HRI '26: 21st ACM\/IEEE International Conference on Human-Robot Interaction","location":"Edinburgh Scotland UK","acronym":"HRI '26","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction","IEEE RAS"]},"container-title":["Proceedings of the 21st ACM\/IEEE International Conference on Human-Robot Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3757279.3785601","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T00:33:49Z","timestamp":1773534829000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757279.3785601"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":78,"alternative-id":["10.1145\/3757279.3785601","10.1145\/3757279"],"URL":"https:\/\/doi.org\/10.1145\/3757279.3785601","relation":{},"subject":[],"published":{"date-parts":[[2026,3,16]]},"assertion":[{"value":"2026-03-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}