{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:51:03Z","timestamp":1742943063475,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031581731"},{"type":"electronic","value":"9783031581748"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-58174-8_35","type":"book-chapter","created":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T09:02:39Z","timestamp":1719910959000},"page":"410-421","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Artificial Eye: Online Video Browsing Guide for\u00a0Visually Impaired"],"prefix":"10.1007","author":[{"given":"Ratnabali","family":"Pal","sequence":"first","affiliation":[]},{"given":"Samarjit","family":"Kar","sequence":"additional","affiliation":[]},{"given":"Arif Ahmed","family":"Sekh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,7,3]]},"reference":[{"issue":"4","key":"35_CR1","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1080\/10641734.2020.1859023","volume":"42","author":"A Pfeuffer","year":"2021","unstructured":"Pfeuffer, A., Li, X., Zhang, Y., Huh, J.: The effect of sponsorship disclosure in YouTube product reviews. J. Curr. Issues Res. Advert. 42(4), 391\u2013410 (2021)","journal-title":"J. Curr. Issues Res. Advert."},{"issue":"3","key":"35_CR2","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1109\/TCSS.2020.2988098","volume":"7","author":"V Gupta","year":"2020","unstructured":"Gupta, V., Aggarwal, A., Chakraborty, T.: Detecting and characterizing extremist reviewer groups in online product reviews. IEEE Trans. Comput. Soc. Syst. 7(3), 741\u2013750 (2020)","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"issue":"2","key":"35_CR3","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/j.im.2018.04.007","volume":"56","author":"X Li","year":"2019","unstructured":"Li, X., Wu, C., Mai, F.: The effect of online reviews on product sales: a joint sentiment-topic analysis. Inf. Manage. 56(2), 172\u2013184 (2019)","journal-title":"Inf. Manage."},{"issue":"23","key":"35_CR4","doi-asserted-by":"publisher","first-page":"e5909","DOI":"10.1002\/cpe.5909","volume":"33","author":"A Onan","year":"2021","unstructured":"Onan, A.: Sentiment analysis on product reviews based on weighted word embeddings and deep neural networks. Concurr. Comput.: Pract. Exp. 33(23), e5909 (2021)","journal-title":"Concurr. Comput.: Pract. Exp."},{"key":"35_CR5","doi-asserted-by":"publisher","first-page":"83871","DOI":"10.1109\/ACCESS.2020.2988370","volume":"8","author":"M Mushtaq","year":"2020","unstructured":"Mushtaq, M., et al.: Whisper: a tool for run-time detection of side-channel attacks. IEEE Access 8, 83871\u201383900 (2020)","journal-title":"IEEE Access"},{"issue":"4","key":"35_CR6","doi-asserted-by":"publisher","first-page":"71","DOI":"10.3390\/jsan10040071","volume":"10","author":"M Jacoby","year":"2021","unstructured":"Jacoby, M., et al.: WHISPER: wireless home identification and sensing platform for energy reduction. J. Sens. Actuat. Netw. 10(4), 71 (2021)","journal-title":"J. Sens. Actuat. Netw."},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Nogueira, R., Jiang, Z., Lin, J.: Document ranking with a pretrained sequence-to-sequence model. arXiv preprint arXiv:2003.06713 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.63"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Pradeep, R., Nogueira, R., Lin, J.: The expando-mono-duo design pattern for text ranking with pretrained sequence-to-sequence models. arXiv preprint arXiv:2101.05667 (2021)","DOI":"10.18653\/v1\/2020.findings-emnlp.63"},{"key":"35_CR9","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"issue":"9","key":"35_CR10","doi-asserted-by":"publisher","first-page":"4419","DOI":"10.3390\/app12094419","volume":"12","author":"V Bhardwaj","year":"2022","unstructured":"Bhardwaj, V., et al.: Automatic speech recognition (ASR) systems for children: a systematic literature review. Appl. Sci. 12(9), 4419 (2022)","journal-title":"Appl. Sci."},{"key":"35_CR11","doi-asserted-by":"publisher","first-page":"131858","DOI":"10.1109\/ACCESS.2021.3112535","volume":"9","author":"S Alharbi","year":"2021","unstructured":"Alharbi, S., et al.: Automatic speech recognition: systematic literature review. IEEE Access 9, 131858\u2013131876 (2021)","journal-title":"IEEE Access"},{"key":"35_CR12","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1109\/TNSRE.2021.3076778","volume":"29","author":"SR Shahamiri","year":"2021","unstructured":"Shahamiri, S.R.: Speech vision: an end-to-end deep learning-based dysarthric automatic speech recognition system. IEEE Trans. Neural Syst. Rehabil. Eng. 29, 852\u2013861 (2021)","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"issue":"9","key":"35_CR13","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1038\/s41928-020-0428-6","volume":"3","author":"Z Zhou","year":"2020","unstructured":"Zhou, Z., et al.: Sign-to-speech translation using machine-learning-assisted stretchable sensor arrays. Nat. Electron. 3(9), 571\u2013578 (2020)","journal-title":"Nat. Electron."},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Inaguma, H., et al.: ESPnet-ST: all-in-one speech translation toolkit. arXiv preprint arXiv:2004.10234 (2020)","DOI":"10.18653\/v1\/2020.acl-demos.34"},{"key":"35_CR15","doi-asserted-by":"publisher","first-page":"102966","DOI":"10.1016\/j.jretconser.2022.102966","volume":"67","author":"SR Agrawal","year":"2022","unstructured":"Agrawal, S.R., Mittal, D.: Optimizing customer engagement content strategy in retail and E-tail: available on online product review videos. J. Retail. Consum. Serv. 67, 102966 (2022)","journal-title":"J. Retail. Consum. Serv."},{"issue":"3","key":"35_CR16","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1111\/ijcs.12740","volume":"46","author":"A Pfeuffer","year":"2022","unstructured":"Pfeuffer, A., Phua, J.: Stranger danger? Cue-based trust in online consumer product review videos. Int. J. Consum. Stud. 46(3), 964\u2013983 (2022)","journal-title":"Int. J. Consum. Stud."},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"35_CR18","doi-asserted-by":"crossref","unstructured":"Chen, C., Anjum, S., Gurari, D.: Grounding answers for visual questions asked by visually impaired people. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19098\u201319107 (2022)","DOI":"10.1109\/CVPR52688.2022.01851"},{"key":"35_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/978-3-030-58520-4_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"D Gurari","year":"2020","unstructured":"Gurari, D., Zhao, Y., Zhang, M., Bhattacharya, N.: Captioning images taken by people who are blind. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XVII. LNCS, vol. 12362, pp. 417\u2013434. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_25"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Brick, E.R., et al.: Am i allergic to this? Assisting sight impaired people in the kitchen. In: Proceedings of the 2021 International Conference on Multimodal Interaction, pp. 92\u2013102 (2021)","DOI":"10.1145\/3462244.3481000"},{"issue":"14","key":"35_CR21","doi-asserted-by":"publisher","first-page":"7684","DOI":"10.1073\/pnas.1915768117","volume":"117","author":"A Koenecke","year":"2020","unstructured":"Koenecke, A., et al.: Racial disparities in automated speech recognition. Proc. Natl. Acad. Sci. 117(14), 7684\u20137689 (2020)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"35_CR22","unstructured":"Chen, Y., et al.: Devil\u2019s whisper: a general approach for physical adversarial attacks against commercial black-box speech recognition devices. In: USENIX Security Symposium, pp. 2667\u20132684 (2020)"},{"key":"35_CR23","doi-asserted-by":"crossref","unstructured":"Mhlanga, D.: Open AI in education, the responsible and ethical use of ChatGPT towards lifelong learning. Education, the Responsible and Ethical Use of ChatGPT Towards Lifelong Learning (2023)","DOI":"10.2139\/ssrn.4354422"},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 397\u2013406 (2021)","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Zhou, X., Y\u0131lmaz, E., Long, Y., Li, Y., Li, H.: Multi-encoder-decoder transformer for code-switching speech recognition. arXiv preprint arXiv:2006.10414 (2020)","DOI":"10.21437\/Interspeech.2020-2488"},{"key":"35_CR26","doi-asserted-by":"crossref","unstructured":"Rajaa, S.: Improving end-to-end SLU performance with prosodic attention and distillation. arXiv preprint arXiv:2305.08067 (2023)","DOI":"10.21437\/Interspeech.2023-1760"},{"key":"35_CR27","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, F., Khan, S.U.: Improve accuracy of speech emotion recognition with attention head fusion. In: 2020 10th Annual Computing and Communication Workshop and Conference (CCWC), pp. 1058\u20131064. IEEE (2020)","DOI":"10.1109\/CCWC47524.2020.9031207"},{"key":"35_CR28","unstructured":"Hugging Face. Hugging face (2022)"},{"key":"35_CR29","unstructured":"Shen, Y., Song, K., Tan, X., Li, D., Lu, W., Zhuang, Y.: HuggingGPT: solving AI tasks with ChatGPT and its friends in HuggingFace. arXiv preprint arXiv:2303.17580 (2023)"},{"issue":"13s","key":"35_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3586075","volume":"55","author":"R Das","year":"2023","unstructured":"Das, R., Singh, T.D.: Multimodal sentiment analysis: a survey of methods, trends, and challenges. ACM Comput. Surveys 55(13s), 1\u201338 (2023)","journal-title":"ACM Comput. Surveys"},{"key":"35_CR31","doi-asserted-by":"crossref","unstructured":"Li, H., Yuan, P., Xu, S., Wu, Y., He, X., Zhou, B.: Aspect-aware multimodal summarization for chinese e-commerce products. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 8188\u20138195 (2020)","DOI":"10.1609\/aaai.v34i05.6332"},{"key":"35_CR32","doi-asserted-by":"publisher","first-page":"3275","DOI":"10.1007\/s11042-020-09549-3","volume":"80","author":"R Rani","year":"2021","unstructured":"Rani, R., Lobiyal, D.K.: An extractive text summarization approach using tagged-LDA based topic modeling. Multimed. Tools Appl. 80, 3275\u20133305 (2021)","journal-title":"Multimed. Tools Appl."},{"key":"35_CR33","doi-asserted-by":"crossref","unstructured":"Hossain, M.S., Rahman, M.F.: Customer sentiment analysis and prediction of insurance products\u2019 reviews using machine learning approaches. FIIB Bus. Rev. 23197145221115793 (2022)","DOI":"10.1177\/23197145221115793"},{"key":"35_CR34","doi-asserted-by":"crossref","unstructured":"Marrese-Taylor, E., Balazs, J.A., Matsuo, Y.: Mining fine-grained opinions on closed captions of YouTube videos with an attention-RNN. arXiv preprint arXiv:1708.02420 (2017)","DOI":"10.18653\/v1\/W17-5213"},{"key":"35_CR35","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: VizWiz-Priv: a dataset for recognizing the presence and purpose of private visual information in images taken by blind people. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 939\u2013948 (2019)","DOI":"10.1109\/CVPR.2019.00103"},{"issue":"8","key":"35_CR36","doi-asserted-by":"publisher","first-page":"e0220976","DOI":"10.1371\/journal.pone.0220976","volume":"14","author":"B Jang","year":"2019","unstructured":"Jang, B., Kim, I., Kim, J.W.: Word2vec convolutional neural networks for classification of news articles and tweets. PloS One 14(8), e0220976 (2019)","journal-title":"PloS One"},{"key":"35_CR37","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Brown, M., Lazebnik, S.: Enhancing video summarization via vision-language embedding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5781\u20135789 (2017)","DOI":"10.1109\/CVPR.2017.118"},{"key":"35_CR38","doi-asserted-by":"crossref","unstructured":"Khosla, A., Hamid, R., Lin, C.-J., Sundaresan, N.: Large-scale video summarization using web-image priors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2698\u20132705 (2013)","DOI":"10.1109\/CVPR.2013.348"},{"key":"35_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/978-3-319-54193-8_23","volume-title":"Computer Vision \u2013 ACCV 2016","author":"M Otani","year":"2017","unstructured":"Otani, M., Nakashima, Y., Rahtu, E., Heikkil\u00e4, J., Yokoya, N.: Video summarization using deep semantic features. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10115, pp. 361\u2013377. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54193-8_23"},{"issue":"12","key":"35_CR40","doi-asserted-by":"publisher","first-page":"e0226902","DOI":"10.1371\/journal.pone.0226902","volume":"14","author":"D Jiahua","year":"2019","unstructured":"Jiahua, D., Rong, J., Michalska, S., Wang, H., Zhang, Y.: Feature selection for helpfulness prediction of online product reviews: an empirical study. PLoS ONE 14(12), e0226902 (2019)","journal-title":"PLoS ONE"},{"key":"35_CR41","doi-asserted-by":"crossref","unstructured":"Shah, J., Sagathiya, M., Redij, K., Hole, V.: Natural language processing based abstractive text summarization of reviews. In: 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC), pp. 461\u2013466. IEEE (2020)","DOI":"10.1109\/ICESC48915.2020.9155759"},{"issue":"5","key":"35_CR42","doi-asserted-by":"publisher","first-page":"4455","DOI":"10.1109\/JIOT.2019.2950469","volume":"7","author":"K Muhammad","year":"2019","unstructured":"Muhammad, K., Hussain, T., Tanveer, M., Sannino, G., de Albuquerque, V.H.C.: Cost-effective video summarization using deep CNN with hierarchical weighted fusion for IoT surveillance networks. IEEE Internet Things J. 7(5), 4455\u20134463 (2019)","journal-title":"IEEE Internet Things J."},{"issue":"6","key":"35_CR43","doi-asserted-by":"publisher","first-page":"1702","DOI":"10.3390\/s20061702","volume":"20","author":"M Rafiq","year":"2020","unstructured":"Rafiq, M., Rafiq, G., Agyeman, R., Choi, G.S., Jin, S.-I.: Scene classification for sports video summarization using transfer learning. Sensors 20(6), 1702 (2020)","journal-title":"Sensors"}],"container-title":["Communications in Computer and Information Science","Computer Vision and Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-58174-8_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T07:46:38Z","timestamp":1732347998000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-58174-8_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031581731","9783031581748"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-58174-8_35","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 July 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Vision and Image Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jammu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iitjammu.ac.in\/cvip2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Online CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"461","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"140","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"30% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}