{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T15:18:26Z","timestamp":1787671106510,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591979","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"1960-1965","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Evaluating Cross-modal Generative Models Using Retrieval Task"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6152-4866","authenticated-orcid":false,"given":"Shivangi","family":"Bithel","sequence":"first","affiliation":[{"name":"IIT Delhi, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3949-2175","authenticated-orcid":false,"given":"Srikanta","family":"Bedathur","sequence":"additional","affiliation":[{"name":"IIT Delhi, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2022. BLIP Model. https:\/\/github.com\/salesforce\/BLIP."},{"key":"e_1_3_2_2_2_1","unstructured":"2022. CLIPCAP Model. https:\/\/github.com\/rmokady\/CLIP_prefix_caption."},{"key":"e_1_3_2_2_3_1","unstructured":"2022. GIT Model. https:\/\/huggingface.co\/microsoft\/git-base-coco."},{"key":"e_1_3_2_2_4_1","unstructured":"2022. Stable Diffusion Model. https:\/\/huggingface.co\/stabilityai\/stable-diffusion-2--1."},{"key":"e_1_3_2_2_5_1","unstructured":"2022. ViT-GPT2 Model. https:\/\/huggingface.co\/nlpconnect\/vit-gpt2-image-captioning."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3--319--46454--1_24"},{"key":"e_1_3_2_2_7_1","volume-title":"Proceedings of the Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization@ACL 2005","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments. In Proceedings of the Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization@ACL 2005, Ann Arbor, Michigan, USA, June 29, 2005, Jade Goldstein, Alon Lavie, Chin-Yew Lin, and Clare R. Voss (Eds.). Association for Computational Linguistics, 65--72. https:\/\/aclanthology.org\/W05-0909\/"},{"key":"e_1_3_2_2_8_1","unstructured":"Shane Barratt and Rishi Sharma. 2018. A Note on the Inception Score. arXiv:1801.01973 [stat.ML]"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2206.10935"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","unstructured":"Soravit Changpinyo Piyush Sharma Nan Ding and Radu Soricut. 2021. Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts. (2021) 3558--3568. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00356","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-031--20074--8_1"},{"key":"e_1_3_2_2_12_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-031--19784-0_6"},{"key":"e_1_3_2_2_14_1","volume-title":"Generative Adversarial Nets. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014","author":"Goodfellow Ian J.","year":"2014","unstructured":"Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C. Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8--13 2014, Montreal, Quebec, Canada, Zoubin Ghahramani, Max Welling, Corinna Cortes, Neil D. Lawrence, and Kilian Q. Weinberger (Eds.). 2672--2680. https:\/\/proceedings.neurips.cc\/paper\/2014\/hash\/5ca3e9b122f61f8f06494c97b1afccf3-Abstract.html"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"e_1_3_2_2_16_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4--9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 6626--6637. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/8a1d694707eb0fefe65871369074926d-Abstract.html"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"e_1_3_2_2_19_1","unstructured":"Saehoon Kim Sanghun Cho Chiheon Kim Doyup Lee and Woonhyuk Baek. 2021. minDALL-E on Conceptual Captions. https:\/\/github.com\/kakaobrain\/minDALL-E."},{"key":"e_1_3_2_2_20_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24","volume":"5594","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 Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 5583--5594. http:\/\/proceedings.mlr.press\/v139\/kim21k.html"},{"key":"e_1_3_2_2_21_1","volume-title":"Kingma and Max Welling","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. In 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14--16, 2014, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1312.6114"},{"key":"e_1_3_2_2_22_1","volume-title":"Hinton","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3--6, 2012, Lake Tahoe, Nevada, United States, Peter L. Bartlett, Fernando C. N. Pereira, Christopher J. C. Burges, L\u00e9on Bottou, and Kilian Q. Weinberger (Eds.). 1106--1114. https:\/\/proceedings.neurips.cc\/paper\/2012\/hash\/c399862d3b9d6b76c8436e924a68c45b-Abstract.html"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2212.12249"},{"key":"e_1_3_2_2_24_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning, ICML 2022","volume":"12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven C. H. Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning, ICML 2022, 17--23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 12888--12900. https:\/\/proceedings.mlr.press\/v162\/li22n.html"},{"key":"e_1_3_2_2_25_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Annual Meeting of the Association for Computational Linguistics.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Annual Meeting of the Association for Computational Linguistics."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3--319--10602--1_48"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.07179"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1416950.1416952"},{"key":"e_1_3_2_2_29_1","volume-title":"Bermano","author":"Mokady Ron","year":"2021","unstructured":"Ron Mokady, Amir Hertz, and Amit H. Bermano. 2021. ClipCap: CLIP Prefix for Image Captioning. CoRR abs\/2111.09734 (2021). arXiv:2111.09734 https:\/\/arxiv.org\/abs\/2111.09734"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030--58595--2_41"},{"key":"e_1_3_2_2_31_1","volume-title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning, ICML 2022","volume":"16804","author":"Nichol Alexander Quinn","year":"2022","unstructured":"Alexander Quinn Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2022. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning, ICML 2022, 17--23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 16784--16804. https:\/\/proceedings.mlr.press\/v162\/nichol22a.html"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_2_33_1","volume-title":"On the influence of random seeds in deep learning architectures for computer vision. CoRR abs\/2109.08203","author":"Picard David","year":"2021","unstructured":"David Picard. 2021. Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision. CoRR abs\/2109.08203 (2021). arXiv:2109.08203 https:\/\/arxiv.org\/abs\/2109.08203"},{"key":"e_1_3_2_2_34_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24","volume":"8763","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748--8763. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_2_35_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2204.06125"},{"key":"e_1_3_2_2_37_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24","volume":"8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-Shot Text-to-Image Generation. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8821--8831. http:\/\/proceedings.mlr.press\/v139\/ramesh21a.html"},{"key":"e_1_3_2_2_38_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6--11 July 2015 (JMLR Workshop and Conference Proceedings","volume":"1538","author":"Rezende Danilo Jimenez","year":"2015","unstructured":"Danilo Jimenez Rezende and Shakir Mohamed. 2015. Variational Inference with Normalizing Flows. In Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6--11 July 2015 (JMLR Workshop and Conference Proceedings, Vol. 37), Francis R. Bach and David M. Blei (Eds.). JMLR.org, 1530--1538. http:\/\/proceedings.mlr.press\/v37\/rezende15.html"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.11487"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277756"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3451964.3451976"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-008--9059--7"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.08402"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_46_1","volume-title":"Multimodal Few-Shot Learning with Frozen Language Models. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Tsimpoukelli Maria","year":"2021","unstructured":"Maria Tsimpoukelli, Jacob Menick, Serkan Cabi, S. M. Ali Eslami, Oriol Vinyals, and Felix Hill. 2021. Multimodal Few-Shot Learning with Frozen Language Models. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6--14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 200--212. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/01b7575c38dac42f3cfb7d500438b875-Abstract.html"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2205.14100"},{"key":"e_1_3_2_2_49_1","volume-title":"Florence: A New Foundation Model for Computer Vision. CoRR abs\/2111.11432","author":"Yuan Lu","year":"2021","unstructured":"Lu Yuan, Dongdong Chen, Yi-Ling Chen, Noel Codella, Xiyang Dai, Jianfeng Gao, Houdong Hu, Xuedong Huang, Boxin Li, Chunyuan Li, Ce Liu, Mengchen Liu, Zicheng Liu, Yumao Lu, Yu Shi, Lijuan Wang, Jianfeng Wang, Bin Xiao, Zhen Xiao, Jianwei Yang, Michael Zeng, Luowei Zhou, and Pengchuan Zhang. 2021. Florence: A New Foundation Model for Computer Vision. CoRR abs\/2111.11432 (2021). arXiv:2111.11432 https:\/\/arxiv.org\/abs\/2111.11432"},{"key":"e_1_3_2_2_50_1","volume-title":"BERTScore: Evaluating Text Generation with BERT. In 8th International Conference on Learning Representations, ICLR 2020","author":"Zhang Tianyi","year":"2020","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26--30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=SkeHuCVFDr"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591979","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:48Z","timestamp":1750178268000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591979"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":50,"alternative-id":["10.1145\/3539618.3591979","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591979","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}