{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T07:14:14Z","timestamp":1766733254996,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":104,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"International Institute of Information Technology, Bangalore"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,15]]},"DOI":"10.1145\/3627631.3627636","type":"proceedings-article","created":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T12:08:32Z","timestamp":1706702912000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Automatic assessment of communication skill in real-world job interviews: A comparative study using deep learning and domain adaptation."],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6739-3249","authenticated-orcid":false,"given":"Jinal H","family":"Thakkar","sequence":"first","affiliation":[{"name":"International Institute of Information Technology, Bangalore, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4887-2273","authenticated-orcid":false,"given":"Chinchu","family":"Thomas","sequence":"additional","affiliation":[{"name":"HP Computing and printing, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0080-452X","authenticated-orcid":false,"given":"Dinesh Babu","family":"Jayagopi","sequence":"additional","affiliation":[{"name":"International Institute of Information Technology, Bangalore, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,1,31]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. MARGADARSHI \u2014 learn-india4ias.com. https:\/\/www.learn-india4ias.com\/courses\/MARGADARSHI-1661591877760-6309e145e4b007874d4c413f. [Accessed 22-Jul-2023]."},{"key":"e_1_3_2_1_2_1","unstructured":"[n. d.]. Videomae. https:\/\/huggingface.co\/docs\/transformers\/model_doc\/videomae"},{"key":"e_1_3_2_1_3_1","volume-title":"The role of automatic obesity stereotypes in real hiring discrimination.Journal of Applied Psychology 96, 4","author":"Agerstrm Jens","year":"2011","unstructured":"Jens Agerstrm and Dan-Olof Rooth. 2011. The role of automatic obesity stereotypes in real hiring discrimination.Journal of Applied Psychology 96, 4 (2011), 790."},{"key":"e_1_3_2_1_4_1","volume-title":"On judging and being judged accurately in zero-acquaintance situations.Journal of personality and social psychology 69, 3","author":"Ambady Nalini","year":"1995","unstructured":"Nalini Ambady, Mark Hallahan, and Robert Rosenthal. 1995. On judging and being judged accurately in zero-acquaintance situations.Journal of personality and social psychology 69, 3 (1995), 518."},{"key":"e_1_3_2_1_5_1","first-page":"1","article-title":"An Assessment of Students\u2019 Performance in Communication Skills A Case Study of the University of Education Winneba","volume":"6","author":"Asemanyi Abena\u00a0Abokoma","year":"2015","unstructured":"Abena\u00a0Abokoma Asemanyi. 2015. An Assessment of Students\u2019 Performance in Communication Skills A Case Study of the University of Education Winneba. Journal of Education and Practice 6 (2015), 1\u20137. https:\/\/api.semanticscholar.org\/CorpusID:55755246","journal-title":"Journal of Education and Practice"},{"key":"e_1_3_2_1_6_1","volume-title":"Hiring discrimination: An overview of (almost) all correspondence experiments since","author":"Baert Stijn","year":"2005","unstructured":"Stijn Baert. 2018. Hiring discrimination: An overview of (almost) all correspondence experiments since 2005. Springer."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.joep.2016.10.002"},{"key":"e_1_3_2_1_8_1","volume-title":"Outcomes of appearance and obesity in organizations. Handbook of workplace diversity","author":"Bell P","year":"2006","unstructured":"Myrtle\u00a0P Bell and Mary\u00a0E Mclaughlin. 2006. Outcomes of appearance and obesity in organizations. Handbook of workplace diversity (2006), 455\u2013474."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781601982957"},{"key":"e_1_3_2_1_10_1","unstructured":"Gedas Bertasius Heng Wang and Lorenzo Torresani. 2021. Is space-time attention all you need for video understanding?. In ICML Vol.\u00a02. 4."},{"key":"e_1_3_2_1_11_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems 33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared\u00a0D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877\u20131901."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01172"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings, Part I 16","author":"Carion Nicolas","year":"2020","unstructured":"Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. 2020. End-to-end object detection with transformers. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I 16. Springer, 213\u2013229."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00642"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16189"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00352"},{"key":"e_1_3_2_1_19_1","volume-title":"International conference on machine learning. PMLR, 794\u2013803","author":"Chen Zhao","year":"2018","unstructured":"Zhao Chen, Vijay Badrinarayanan, Chen-Yu Lee, and Andrew Rabinovich. 2018. Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In International conference on machine learning. PMLR, 794\u2013803."},{"key":"e_1_3_2_1_20_1","volume-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho, Bart Van\u00a0Merri\u00ebnboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1111\/ijsa.12123"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1177\/0018726716676537"},{"key":"e_1_3_2_1_24_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_25_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_27_1","volume-title":"Age discrimination in simulated employment contexts: An integrative analysis.Journal of applied psychology 80, 6","author":"Finkelstein M","year":"1995","unstructured":"Lisa\u00a0M Finkelstein, Michael\u00a0J Burke, and Manbury\u00a0S Raju. 1995. Age discrimination in simulated employment contexts: An integrative analysis.Journal of applied psychology 80, 6 (1995), 652."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2044-8325.1980.tb00007.x"},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. PMLR, 1180\u20131189","author":"Ganin Yaroslav","year":"2015","unstructured":"Yaroslav Ganin and Victor Lempitsky. 2015. Unsupervised domain adaptation by backpropagation. In International conference on machine learning. PMLR, 1180\u20131189."},{"key":"e_1_3_2_1_30_1","volume-title":"Domain-adversarial training of neural networks. The journal of machine learning research 17, 1","author":"Ganin Yaroslav","year":"2016","unstructured":"Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, Fran\u00e7ois Laviolette, Mario Marchand, and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. The journal of machine learning research 17, 1 (2016), 2096\u20132030."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICEE55646.2022.9827056"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1382"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1382"},{"key":"e_1_3_2_1_34_1","volume-title":"Not welcome here: Discrimination towards women who wear the Muslim headscarf. Human relations 66, 5","author":"Ghumman Sonia","year":"2013","unstructured":"Sonia Ghumman and Ann\u00a0Marie Ryan. 2013. Not welcome here: Discrimination towards women who wear the Muslim headscarf. Human relations 66, 5 (2013), 671\u2013698."},{"key":"e_1_3_2_1_35_1","volume-title":"International conference on machine learning. PMLR, 1764\u20131772","author":"Graves Alex","year":"2014","unstructured":"Alex Graves and Navdeep Jaitly. 2014. Towards end-to-end speech recognition with recurrent neural networks. In International conference on machine learning. PMLR, 1764\u20131772."},{"key":"e_1_3_2_1_36_1","volume-title":"age, sex, and competence as factors in employer selection of the disadvantaged.Journal of Applied Psychology 62, 2","author":"Haefner E","year":"1977","unstructured":"James\u00a0E Haefner. 1977. Race, age, sex, and competence as factors in employer selection of the disadvantaged.Journal of Applied Psychology 62, 2 (1977), 199."},{"key":"e_1_3_2_1_37_1","first-page":"7421","article-title":"Real-time vernacular sign language recognition using mediapipe and machine learning","volume":"2582","author":"Halder Arpita","year":"2021","unstructured":"Arpita Halder and Akshit Tayade. 2021. Real-time vernacular sign language recognition using mediapipe and machine learning. Journal homepage: www. ijrpr. com ISSN 2582 (2021), 7421.","journal-title":"Journal homepage: www. ijrpr. com ISSN"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"e_1_3_2_1_39_1","volume-title":"Formal and interpersonal discrimination: A field study of bias toward homosexual applicants. Personality and social psychology bulletin 28, 6","author":"Hebl R","year":"2002","unstructured":"Michelle\u00a0R Hebl, Jessica\u00a0Bigazzi Foster, Laura\u00a0M Mannix, and John\u00a0F Dovidio. 2002. Formal and interpersonal discrimination: A field study of bias toward homosexual applicants. Personality and social psychology bulletin 28, 6 (2002), 815\u2013825."},{"key":"e_1_3_2_1_40_1","unstructured":"Annemarie Hiemstra and Eva Derous. 2015. Video resumes portrayed: Findings and challenges. (2015) 44\u201360."},{"key":"e_1_3_2_1_41_1","unstructured":"[n. d.]. HireVue hiring platform: Video interviews assessment scheduling AI chatbot: Hirevue. hirevue.com ([n. d.]). https:\/\/www.hirevue.com\/"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493502"},{"key":"e_1_3_2_1_43_1","volume-title":"Influence of nonverbal communication and rater proximity on impressions and decisions in simulated employment interviews.Journal of Applied Psychology 62, 3","author":"Imada S","year":"1977","unstructured":"Andrew\u00a0S Imada and Milton\u00a0D Hakel. 1977. Influence of nonverbal communication and rater proximity on impressions and decisions in simulated employment interviews.Journal of Applied Psychology 62, 3 (1977), 295."},{"key":"e_1_3_2_1_44_1","unstructured":"2023. Interview Stream (Mar 2023). https:\/\/interviewstream.com\/interviewstream-prep\/"},{"key":"e_1_3_2_1_45_1","unstructured":"Arshad Jamal Vinay\u00a0P. Namboodiri Dipti Deodhare and K.\u00a0S. Venkatesh. 2019. Deep domain adaptation in action space. https:\/\/researchportal.bath.ac.uk\/en\/publications\/deep-domain-adaptation-in-action-space"},{"key":"e_1_3_2_1_46_1","volume-title":"3D convolutional neural networks for human action recognition","author":"Ji Shuiwang","year":"2012","unstructured":"Shuiwang Ji, Wei Xu, Ming Yang, and Kai Yu. 2012. 3D convolutional neural networks for human action recognition. IEEE transactions on pattern analysis and machine intelligence 35, 1 (2012), 221\u2013231."},{"key":"e_1_3_2_1_47_1","volume-title":"3D convolutional neural networks for human action recognition","author":"Ji Shuiwang","year":"2012","unstructured":"Shuiwang Ji, Wei Xu, Ming Yang, and Kai Yu. 2012. 3D convolutional neural networks for human action recognition. IEEE transactions on pattern analysis and machine intelligence 35, 1 (2012), 221\u2013231."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.492"},{"key":"e_1_3_2_1_49_1","first-page":"1","article-title":"Factors influencing internal and external employability of employees","volume":"11","author":"Juhdi Nurita","year":"2010","unstructured":"Nurita Juhdi, Fatimah Pa\u2019Wan, Noor\u00a0Akmar Othman, and Hanifah Moksin. 2010. Factors influencing internal and external employability of employees. Business and Economics Journal 11, 1-10 (2010).","journal-title":"Business and Economics Journal"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3016180"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 7482\u20137491","author":"Kendall Alex","year":"2018","unstructured":"Alex Kendall, Yarin Gal, and Roberto Cipolla. 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7482\u20137491."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638346"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638346"},{"key":"e_1_3_2_1_56_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_2_1_58_1","unstructured":"Author links open overlay\u00a0panelJiuxiang Gu\u00a0a a 1 b c AbstractIn the last\u00a0few years J. Mehta W.W. Ng S. Ding J. Lin and et al.2017. Recent advances in Convolutional Neural Networks. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0031320317304120"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_61_1","volume-title":"International conference on machine learning. PMLR, 97\u2013105","author":"Long Mingsheng","year":"2015","unstructured":"Mingsheng Long, Yue Cao, Jianmin Wang, and Michael Jordan. 2015. Learning transferable features with deep adaptation networks. In International conference on machine learning. PMLR, 97\u2013105."},{"key":"e_1_3_2_1_62_1","volume-title":"Mediapipe: A framework for building perception pipelines. arXiv preprint arXiv:1906.08172","author":"Lugaresi Camillo","year":"2019","unstructured":"Camillo Lugaresi, Jiuqiang Tang, Hadon Nash, Chris McClanahan, Esha Uboweja, Michael Hays, Fan Zhang, Chuo-Ling Chang, Ming\u00a0Guang Yong, Juhyun Lee, 2019. Mediapipe: A framework for building perception pipelines. arXiv preprint arXiv:1906.08172 (2019)."},{"key":"e_1_3_2_1_63_1","volume-title":"Both sides of the employment interview interaction: Perceptions of interviewers and applicants with disabilities.Rehabilitation Psychology 40, 4","author":"Macan Therese\u00a0Hoff","year":"1995","unstructured":"Therese\u00a0Hoff Macan and Theodore\u00a0L Hayes. 1995. Both sides of the employment interview interaction: Perceptions of interviewers and applicants with disabilities.Rehabilitation Psychology 40, 4 (1995), 261."},{"key":"e_1_3_2_1_64_1","volume-title":"M-SENA: An Integrated Platform for Multimodal Sentiment Analysis. arXiv preprint arXiv:2203.12441","author":"Mao Huisheng","year":"2022","unstructured":"Huisheng Mao, Ziqi Yuan, Hua Xu, Wenmeng Yu, Yihe Liu, and Kai Gao. 2022. M-SENA: An Integrated Platform for Multimodal Sentiment Analysis. arXiv preprint arXiv:2203.12441 (2022)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1111\/ijsa.12280"},{"key":"e_1_3_2_1_67_1","unstructured":"David Moffat David Ronan and Joshua\u00a0D Reiss. 2015. An evaluation of audio feature extraction toolboxes. (2015)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163127"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2557058"},{"key":"e_1_3_2_1_70_1","volume-title":"Adversarial Cross-Domain Action Recognition with Co-Attention. CoRR abs\/1912.10405","author":"Pan Boxiao","year":"2019","unstructured":"Boxiao Pan, Zhangjie Cao, Ehsan Adeli, and Juan\u00a0Carlos Niebles. 2019. Adversarial Cross-Domain Action Recognition with Co-Attention. CoRR abs\/1912.10405 (2019). arXiv:1912.10405http:\/\/arxiv.org\/abs\/1912.10405"},{"key":"e_1_3_2_1_71_1","volume-title":"Interviewer perceptions of applicant qualifications: A multivariate field study of demographic characteristics and nonverbal cues.Journal of Applied Psychology 69, 4","author":"Parsons K","year":"1984","unstructured":"Charles\u00a0K Parsons and Robert\u00a0C Liden. 1984. Interviewer perceptions of applicant qualifications: A multivariate field study of demographic characteristics and nonverbal cues.Journal of Applied Psychology 69, 4 (1984), 557."},{"key":"e_1_3_2_1_72_1","volume-title":"Syn2real: A new benchmark forsynthetic-to-real visual domain adaptation. arXiv preprint arXiv:1806.09755","author":"Peng Xingchao","year":"2018","unstructured":"Xingchao Peng, Ben Usman, Kuniaki Saito, Neela Kaushik, Judy Hoffman, and Kate Saenko. 2018. Syn2real: A new benchmark forsynthetic-to-real visual domain adaptation. arXiv preprint arXiv:1806.09755 (2018)."},{"volume-title":"Dataset shift in machine learning","author":"Quinonero-Candela Joaquin","key":"e_1_3_2_1_73_1","unstructured":"Joaquin Quinonero-Candela, Masashi Sugiyama, Anton Schwaighofer, and Neil\u00a0D Lawrence. 2008. Dataset shift in machine learning. Mit Press."},{"key":"e_1_3_2_1_74_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever 2018. Improving language understanding by generative pre-training. (2018)."},{"volume-title":"Multimodal emotion recognition using deep learning architectures. In 2016 IEEE winter conference on applications of computer vision (WACV)","author":"Ranganathan Hiranmayi","key":"e_1_3_2_1_75_1","unstructured":"Hiranmayi Ranganathan, Shayok Chakraborty, and Sethuraman Panchanathan. 2016. Multimodal emotion recognition using deep learning architectures. In 2016 IEEE winter conference on applications of computer vision (WACV). IEEE, 1\u20139."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5654-9"},{"key":"e_1_3_2_1_77_1","unstructured":"[n. d.]. Shorten your screening time with video interviews: Recright. Untitled design (23)-1 ([n. d.]). https:\/\/new.recright.com\/"},{"key":"e_1_3_2_1_78_1","volume-title":"A simple neural network module for relational reasoning. Advances in neural information processing systems 30","author":"Santoro Adam","year":"2017","unstructured":"Adam Santoro, David Raposo, David\u00a0G Barrett, Mateusz Malinowski, Razvan Pascanu, Peter Battaglia, and Timothy Lillicrap. 2017. A simple neural network module for relational reasoning. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_79_1","volume-title":"Improving Asynchronous Interview Interaction with Follow-up Question Generation.International Journal of Interactive Multimedia & Artificial Intelligence 6, 5","author":"Manish Agnihotri Pooja\u00a0Rao SB","year":"2021","unstructured":"Pooja\u00a0Rao SB, Manish Agnihotri, and Dinesh\u00a0Babu Jayagopi. 2021. Improving Asynchronous Interview Interaction with Follow-up Question Generation.International Journal of Interactive Multimedia & Artificial Intelligence 6, 5 (2021)."},{"key":"e_1_3_2_1_80_1","volume-title":"Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems 27","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_81_1","volume-title":"Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems 27","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_82_1","first-page":"15","article-title":"Malaysian graduates\u2019 employability skills","volume":"4","author":"Kaur\u00a0Gurcharan Singh Gurvinder","year":"2008","unstructured":"Gurvinder Kaur\u00a0Gurcharan Singh and Sharan Kaur\u00a0Garib Singh. 2008. Malaysian graduates\u2019 employability skills. UNITAR e-Journal 4, 1 (2008), 15\u201345.","journal-title":"UNITAR e-Journal"},{"key":"e_1_3_2_1_83_1","volume-title":"UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir\u00a0Roshan Zamir, and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)."},{"key":"e_1_3_2_1_84_1","volume-title":"Multimodal learning with deep boltzmann machines. Advances in neural information processing systems 25","author":"Srivastava Nitish","year":"2012","unstructured":"Nitish Srivastava and Russ\u00a0R Salakhutdinov. 2012. Multimodal learning with deep boltzmann machines. Advances in neural information processing systems 25 (2012)."},{"key":"e_1_3_2_1_85_1","volume-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. arXiv preprint arXiv:2203.12602","author":"Tong Zhan","year":"2022","unstructured":"Zhan Tong, Yibing Song, Jue Wang, and Limin Wang. 2022. Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. arXiv preprint arXiv:2203.12602 (2022)."},{"key":"e_1_3_2_1_86_1","volume-title":"International conference on machine learning. PMLR, 10347\u201310357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International conference on machine learning. PMLR, 10347\u201310357."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_88_1","unstructured":"Elmira van\u00a0den Broek Anastasia Sergeeva and Marleen Huysman. 2019. Hiring algorithms: An ethnography of fairness in practice. (2019)."},{"key":"e_1_3_2_1_89_1","volume-title":"Visualizing data using t-SNE.Journal of machine learning research 9, 11","author":"Maaten Laurens Van\u00a0der","year":"2008","unstructured":"Laurens Van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE.Journal of machine learning research 9, 11 (2008)."},{"key":"e_1_3_2_1_90_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"volume-title":"Bmvc.","author":"Wang Yifan","key":"e_1_3_2_1_92_1","unstructured":"Yifan Wang, Jie Song, Limin Wang, Luc Van\u00a0Gool, and Otmar Hilliges. 2016. Two-Stream SR-CNNs for Action Recognition in Videos.. In Bmvc. York, UK."},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2044-8325.1988.tb00467.x"},{"key":"e_1_3_2_1_94_1","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie Enze","year":"2021","unstructured":"Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose\u00a0M Alvarez, and Ping Luo. 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems 34 (2021), 12077\u201312090.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3001522"},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.12.046"},{"key":"e_1_3_2_1_97_1","volume-title":"Proceedings, Part XXIV 16","author":"Yang Jianfei","year":"2020","unstructured":"Jianfei Yang, Han Zou, Yuxun Zhou, Zhaoyang Zeng, and Lihua Xie. 2020. Mind the discriminability: Asymmetric adversarial domain adaptation. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXIV 16. Springer, 589\u2013606."},{"key":"e_1_3_2_1_98_1","volume-title":"Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250","author":"Zadeh Amir","year":"2017","unstructured":"Amir Zadeh, Minghai Chen, Soujanya Poria, Erik Cambria, and Louis-Philippe Morency. 2017. Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250 (2017)."},{"volume-title":"Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, Robert\u00a0C","author":"Zechner Klaus","key":"e_1_3_2_1_99_1","unstructured":"Klaus Zechner and Isaac Bejar. 2006. Towards Automatic Scoring of Non-Native Spontaneous Speech. In Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, Robert\u00a0C. Moore, Jeff Bilmes, Jennifer Chu-Carroll, and Mark Sanderson (Eds.). Association for Computational Linguistics, New York City, USA, 216\u2013223. https:\/\/aclanthology.org\/N06-1028"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"e_1_3_2_1_101_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00033"},{"key":"e_1_3_2_1_102_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"e_1_3_2_1_104_1","volume-title":"Deepvit: Towards deeper vision transformer. arXiv preprint arXiv:2103.11886","author":"Zhou Daquan","year":"2021","unstructured":"Daquan Zhou, Bingyi Kang, Xiaojie Jin, Linjie Yang, Xiaochen Lian, Zihang Jiang, Qibin Hou, and Jiashi Feng. 2021. Deepvit: Towards deeper vision transformer. arXiv preprint arXiv:2103.11886 (2021)."}],"event":{"name":"ICVGIP '23: Indian Conference on Computer Vision, Graphics and Image Processing","acronym":"ICVGIP '23","location":"Rupnagar India"},"container-title":["Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627631.3627636","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627631.3627636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:51:04Z","timestamp":1755892264000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627631.3627636"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,15]]},"references-count":104,"alternative-id":["10.1145\/3627631.3627636","10.1145\/3627631"],"URL":"https:\/\/doi.org\/10.1145\/3627631.3627636","relation":{},"subject":[],"published":{"date-parts":[[2023,12,15]]},"assertion":[{"value":"2024-01-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}