{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:58:09Z","timestamp":1785488289629,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T00:00:00Z","timestamp":1765929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,17]]},"DOI":"10.1145\/3774521.3774555","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T07:34:24Z","timestamp":1785483264000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CSGaze: Context-aware Social Gaze Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3774-8117","authenticated-orcid":false,"given":"Surbhi","family":"Madan","sequence":"first","affiliation":[{"name":"IIT Ropar, Ropar, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2639-8374","authenticated-orcid":false,"given":"Shreya","family":"Ghosh","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9441-7074","authenticated-orcid":false,"given":"Ramanathan","family":"Subramanian","sequence":"additional","affiliation":[{"name":"University of Canberra, Canberra, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8356-4909","authenticated-orcid":false,"given":"Tom","family":"Gedeon","sequence":"additional","affiliation":[{"name":"Curtin University, Perth, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2230-1440","authenticated-orcid":false,"given":"Abhinav","family":"Dhall","sequence":"additional","affiliation":[{"name":"Monash University, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9780890425596"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Michael Argyle Mark Cook and Duncan Cramer. 1994. Gaze and mutual gaze. The British Journal of Psychiatry 165 6 (1994) 848\u2013850.","DOI":"10.1017\/S0007125000073980"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Jean-David Boucher Ugo Pattacini Amelie Lelong Gerard Bailly Frederic Elisei Sascha Fagel Peter\u00a0Ford Dominey and Jocelyne Ventre-Dominey. 2012. I reach faster when I see you look: gaze effects in human\u2013human and human\u2013robot face-to-face cooperation. Frontiers in neurorobotics 6 (2012) 3.","DOI":"10.3389\/fnbot.2012.00003"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3588015.3588411"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00544"},{"key":"e_1_3_3_1_7_2","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1810.04805 (2018)."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16215"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00676"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00582"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897360"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Shreya Ghosh Abhinav Dhall Munawar Hayat Jarrod Knibbe and Qiang Ji. 2023. Automatic gaze analysis: A survey of deep learning based approaches. IEEE Transactions on Pattern Analysis and Machine Intelligence 46 1 (2023) 61\u201384.","DOI":"10.1109\/TPAMI.2023.3321337"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00123"},{"key":"e_1_3_3_1_14_2","first-page":"1590","volume-title":"Proceedings of the Asian Conference on Computer Vision","author":"Guo Hang","year":"2022","unstructured":"Hang Guo, Zhengxi Hu, and Jingtai Liu. 2022. Mgtr: End-to-end mutual gaze detection with transformer. In Proceedings of the Asian Conference on Computer Vision. 1590\u20131605."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581955"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Anshul Gupta Samy Tafasca Arya Farkhondeh Pierre Vuillecard and Jean-marc Odobez. 2025. MTGS: A Novel Framework for Multi-Person Temporal Gaze Following and Social Gaze Prediction. Advances in Neural Information Processing Systems 37 (2025) 15646\u201315673.","DOI":"10.52202\/079017-0500"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00552"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00066"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP62443.2025.11204342"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Chris\u00a0L Kleinke. 1986. Gaze and eye contact: a research review. Psychological bulletin 100 1 (1986) 78.","DOI":"10.1037\/0033-2909.100.1.78"},{"key":"e_1_3_3_1_22_2","first-page":"403","volume-title":"International Conference on Pattern Recognition","author":"Kumar Deepak","year":"2024","unstructured":"Deepak Kumar, Piyush Dhamdhere, and Balasubramanian Raman. 2024. Fusing Multimodal Streams for Improved Group Emotion Recognition in Videos. In International Conference on Pattern Recognition. Springer, 403\u2013418."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688986"},{"key":"e_1_3_3_1_24_2","first-page":"586","volume-title":"International Conference on Computer Vision and Image Processing","author":"Kumar Deepak","year":"2022","unstructured":"Deepak Kumar and Balasubramanian Raman. 2022. Speech-Based Automatic Prediction of Interview Traits. In International Conference on Computer Vision and Image Processing. Springer, 586\u2013596."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Deepak Kumar Pradeep Singh and Balasubramanian Raman. 2024. All signals point to personality: A dual-pipeline LSTM-attention and symbolic dynamics framework for predicting personality traits from Bio-Electrical signals. Biomedical Signal Processing and Control 96 (2024) 106609.","DOI":"10.1016\/j.bspc.2024.106609"},{"key":"e_1_3_3_1_26_2","unstructured":"Sangmin Lee Minzhi Li Bolin Lai Wenqi Jia Fiona Ryan Xu Cao Ozgur Kara Bikram Boote Weiyan Shi Diyi Yang et\u00a0al. 2024. Towards social AI: A survey on understanding social interactions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.15316 (2024)."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00283"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Manasi Malik and Leyla Isik. 2023. Relational visual representations underlie human social interaction recognition. Nature Communications 14 1 (2023) 7317.","DOI":"10.1038\/s41467-023-43156-8"},{"key":"e_1_3_3_1_30_2","first-page":"22","volume-title":"Proceedings of the British Machine Vision Conference (BMVC): Dundee, September 2011","author":"Marin-Jimenez Manuel","year":"2011","unstructured":"Manuel Marin-Jimenez, Andrew Zisserman, and Vittorio Ferrari. 2011. \" Here\u2019s looking at you, kid\": Detecting people looking at each other in videos. In Proceedings of the British Machine Vision Conference (BMVC): Dundee, September 2011. BMVA Press, 22\u20131."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00359"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00359"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Manuel\u00a0Jes\u00fas Marin-Jimenez Andrew Zisserman Marcin Eichner and Vittorio Ferrari. 2014. Detecting people looking at each other in videos. International Journal of Computer Vision 106 (2014) 282\u2013296.","DOI":"10.1007\/s11263-013-0655-7"},{"key":"e_1_3_3_1_34_2","unstructured":"Zhiliang Peng Wenhui Wang Li Dong Yaru Hao Shaohan Huang Shuming Ma and Furu Wei. 2023. Kosmos-2: Grounding multimodal large language models to the world. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.14824 (2023)."},{"key":"e_1_3_3_1_35_2","unstructured":"Alec Radford. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_3_1_36_2","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et\u00a0al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_3_1_37_2","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.06125 1 2 (2022) 3."},{"key":"e_1_3_3_1_38_2","unstructured":"Adria Recasens Aditya Khosla Carl Vondrick and Antonio Torralba. 2015. Where are they looking? Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_3_1_39_2","volume-title":"Advances in Neural Information Processing Systems (NIPS)","year":"2015","unstructured":"Adria Recasens*, Aditya Khosla*, Carl Vondrick, and Antonio Torralba. 2015. Where are they looking?. In Advances in Neural Information Processing Systems (NIPS). * indicates equal contribution."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02689"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/319463.319464"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/971478.971505"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01914"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00224"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Inam Ullah Muwei Jian Sumaira Hussain Jie Guo Hui Yu Xing Wang and Yilong Yin. 2020. A brief survey of visual saliency detection. Multimedia Tools and Applications 79 (2020) 34605\u201334645.","DOI":"10.1007\/s11042-020-08849-y"},{"key":"e_1_3_3_1_46_2","unstructured":"Jun Wang Hao Ruan Mingjie Wang Chuanghui Zhang Huachun Li and Jun Zhou. 2023. GazeCLIP: Towards Enhancing Gaze Estimation via Text Guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.00260 (2023)."},{"key":"e_1_3_3_1_47_2","unstructured":"Yaokun Yang and Feng Lu. [n.d.]. GTD-LLM: A Plug-and-Play LLM Reasoning Module for Gaze Target Detection. ([n. d.])."},{"key":"e_1_3_3_1_48_2","unstructured":"Liu Yinhan Ott Myle Goyal Naman Du Jingfei Joshi Mandar Chen Danqi Levy Omer and Lewis Mike. 2019. RoBERTa: A robustly optimized BERT pretraining approach (2019). arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1907.11692 (2019) 1\u201313."},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"}],"event":{"name":"ICVGIP 2025: Indian Conference on Computer Vision, Graphics, and Image Processing","location":"Mandi Himachal Pradesh India","acronym":"ICVGIP 2025"},"container-title":["Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774521.3774555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:08:25Z","timestamp":1785485305000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774521.3774555"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":48,"alternative-id":["10.1145\/3774521.3774555","10.1145\/3774521"],"URL":"https:\/\/doi.org\/10.1145\/3774521.3774555","relation":{},"subject":[],"published":{"date-parts":[[2025,12,17]]},"assertion":[{"value":"2026-07-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}