{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:34:43Z","timestamp":1742913283228,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":38,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819620531"},{"type":"electronic","value":"9789819620548"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-2054-8_5","type":"book-chapter","created":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T15:46:52Z","timestamp":1735832812000},"page":"58-71","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AD2AT: Audio Description to\u00a0Alternative Text, a\u00a0Dataset of\u00a0Alternative Text from\u00a0Movies"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1104-1785","authenticated-orcid":false,"given":"Elise","family":"Lincker","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7249-8715","authenticated-orcid":false,"given":"Camille","family":"Guinaudeau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6995-6447","authenticated-orcid":false,"given":"Shin\u2019ichi","family":"Satoh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,3]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: SPICE: Semantic propositional image caption evaluation. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"5_CR2","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization (2005)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12M: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: IEEE\/CVF CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Chintalapati, S.S., Bragg, J., Wang, L.L.: A dataset of alt texts from HCI publications: analyses and uses towards producing more descriptive alt texts of data visualizations in scientific papers. In: ASSETS 2022 (2022)","DOI":"10.1145\/3517428.3544796"},{"key":"5_CR5","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. In: Advances in Neural Information Processing Systems (2024)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Doddington, G.: Automatic evaluation of machine translation quality using n-gram co-occurrence statistics. In: HLT 2002 (2002)","DOI":"10.3115\/1289189.1289273"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Han, T., Bain, M., Nagrani, A., Varol, G., Xie, W., Zisserman, A.: AutoAD II: the sequel-who, when, and what in movie audio description. In: IEEE\/CVF CVPR (2023)","DOI":"10.1109\/ICCV51070.2023.01255"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Han, T., Bain, M., Nagrani, A., Varol, G., Xie, W., Zisserman, A.: AutoAD: movie description in context. In: IEEE\/CVF CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01815"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: CLIPScore: a reference-free evaluation metric for image captioning. In: EMNLP 2021 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Hu, A., Chen, S., Zhang, L., Jin, Q.: InfoMetIC: an informative metric for reference-free image caption evaluation. In: ACL 2023 (2023)","DOI":"10.18653\/v1\/2023.acl-long.178"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, L., Jung, C., Phutane, M., Stangl, A., Azenkot, S.: \u201cIt\u2019s kind of context dependent\u201d: understanding blind and low vision people\u2019s video accessibility preferences across viewing scenarios. In: CHI Conference on Human Factors in Computing Systems (2024)","DOI":"10.1145\/3613904.3642238"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Kreiss, E., Bennett, C., Hooshmand, S., Zelikman, E., Ringel\u00a0Morris, M., Potts, C.: Context matters for image descriptions for accessibility: challenges for referenceless evaluation metrics. In: EMNLP 2022 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.309"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Kreiss, E., Fang, F., Goodman, N., Potts, C.: Concadia: towards image-based text generation with a purpose. In: EMNLP 2022 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.308"},{"key":"5_CR14","unstructured":"Kreiss, E., Zelikman, E., Potts, C., Haber, N.: ContextRef: evaluating referenceless metrics for image description generation. arXiv preprint arXiv:2309.11710 (2023)"},{"key":"5_CR15","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML (2022)"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Lin, C.Y., Hovy, E.: Automatic evaluation of summaries using n-gram co-occurrence statistics. In: HLT-NAACL 2003 (2003)","DOI":"10.3115\/1073445.1073465"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: IEEE\/CVF CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"5_CR18","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems (2023)"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Manning, C.D., Surdeanu, M., Bauer, J., Finkel, J.R., Bethard, S., McClosky, D.: The Stanford CoreNLP natural language processing toolkit. In: ACL 2014 (2014)","DOI":"10.3115\/v1\/P14-5010"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Matamala, A.: The VIW project: multimodal corpus linguistics for audio description analysis. Revista Espa\u00f1ola de Ling\u00fc\u00edstica Aplicada (2019)","DOI":"10.1075\/resla.17001.mat"},{"key":"5_CR21","unstructured":"Matamala, A., Villegas, M.: Building an audio description multilingual multimodal corpus: the VIW project. Computer vision and language processing, Multimodal Corpora (2016)"},{"key":"5_CR22","doi-asserted-by":"publisher","unstructured":"Moured, O., et al.: Alt4Blind: a user interface to simplify charts alt-text creation. In: International Conference on Computers Helping People with Special Needs (2024). https:\/\/doi.org\/10.1007\/978-3-031-62846-7_35","DOI":"10.1007\/978-3-031-62846-7_35"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: ACL 2002 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"5_CR24","unstructured":"Pitcher-Cooper, C., Seth, M., Kao, B., Coughlan, J.M., Yoon, I.: You described, we archived: a rich audio description dataset. J. Technol. Persons Disabil. 11, 192\u2013208 (2023)"},{"key":"5_CR25","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Tandon, N., Schiele, B.: A dataset for movie description. In: IEEE CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., et al.: Movie description. Int. J. Comput. Vis. (2017)","DOI":"10.1007\/s11263-016-0987-1"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Rotstein, N., Bensa\u00efd, D., Brody, S., Ganz, R., Kimmel, R.: FuseCap: leveraging large language models for enriched fused image captions. In: IEEE\/CVF Winter Conference on Applications of Computer Vision (2024)","DOI":"10.1109\/WACV57701.2024.00559"},{"key":"5_CR29","unstructured":"Schuhmann, C., et\u00a0al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Advances in Neural Information Processing Systems (2022)"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: ACL 2018 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Soldan, M., et al.: MAD: a scalable dataset for language grounding in videos from movie audio descriptions. In: IEEE\/CVF CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00497"},{"key":"5_CR32","unstructured":"Srivatsan, N., Samaniego, S., Florez, O., Berg-Kirkpatrick, T.: Alt-text with context: improving accessibility for images on twitter. In: ICLR (2024)"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Stangl, A., Verma, N., Fleischmann, K.R., Morris, M.R., Gurari, D.: Going beyond one-size-fits-all image descriptions to satisfy the information wants of people who are blind or have low vision. In: ASSETS 2021 (2021)","DOI":"10.1145\/3441852.3471233"},{"key":"5_CR34","unstructured":"Torabi, A., Pal, C., Larochelle, H., Courville, A.: Using descriptive video services to create a large data source for video annotation research. arXiv preprint arXiv:1503.01070 (2015)"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: CIDEr: Consensus-based image description evaluation. In: IEEE CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"5_CR36","unstructured":"Wang, J., Yang, Z., Hu, X., Li, L., Lin, K., Gan, Z., Liu, Z., Liu, C., Wang, L.: GIT: a generative image-to-text transformer for vision and language. Trans. Mach. Learn. Res. (2022)"},{"key":"5_CR37","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: BertSCORE: evaluating text generation with BERT. arXiv preprint arXiv:1904.09675 (2019)"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, W., Bhat, S.: GRUEN for evaluating linguistic quality of generated text. In: Findings of the ACL: EMNLP 2020 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.9"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2054-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T01:42:01Z","timestamp":1742694121000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2054-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819620531","9789819620548"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2054-8_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"3 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}