{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:36Z","timestamp":1750309536728,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["112-2410-H-182 -026 -MY2"],"award-info":[{"award-number":["112-2410-H-182 -026 -MY2"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,13]]},"DOI":"10.1145\/3711542.3711560","type":"proceedings-article","created":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T04:46:56Z","timestamp":1744606016000},"page":"401-405","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["From Pictures to Prompts: Analyzing and Reconstructing AI-Generated Images with BLIP2 and CLIP"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7425-0593","authenticated-orcid":false,"given":"Yi-Hsuan","family":"Kuo","sequence":"first","affiliation":[{"name":"Department of Computer Science and Information Engineering, Chang Gung University, Taoyuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4987-5943","authenticated-orcid":false,"given":"Hsien-Tsung","family":"Chang","sequence":"additional","affiliation":[{"name":"Bachelor Program in Artificial Intelligence, Chang Gung University, Taoyuan, China and Department of Computer Science and Information Engineering, Chang Gung University, Taoyuan, Taiwan"}]}],"member":"320","published-online":{"date-parts":[[2025,4,13]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Amir Beck and Marc Teboulle. 2009. A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM journal on imaging sciences 2 1 (2009) 183\u2013202.","DOI":"10.1137\/080716542"},{"key":"e_1_3_3_1_3_2","first-page":"1597","volume-title":"International conference on machine learning","author":"Chen Ting","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. [n.\u00a0d.]. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597\u20131607."},{"key":"e_1_3_3_1_4_2","first-page":"886","volume-title":"2005 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201905)","author":"Dalal Navneet","unstructured":"Navneet Dalal and Bill Triggs. [n.\u00a0d.]. Histograms of oriented gradients for human detection. In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201905), Vol.\u00a01. Ieee, 886\u2013893."},{"key":"e_1_3_3_1_5_2","first-page":"248","volume-title":"2009 IEEE conference on computer vision and pattern recognition","author":"Deng Jia","unstructured":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. [n.\u00a0d.]. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. Ieee, 248\u2013255."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Chao Dong Chen\u00a0Change Loy Kaiming He and Xiaoou Tang. 2015. Image super-resolution using deep convolutional networks. IEEE transactions on pattern analysis and machine intelligence 38 2 (2015) 295\u2013307.","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"e_1_3_3_1_7_2","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_3_1_8_2","first-page":"9729","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"He Kaiming","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. [n.\u00a0d.]. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 9729\u20139738."},{"key":"e_1_3_3_1_9_2","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_1_10_2","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey\u00a0E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012)."},{"key":"e_1_3_3_1_11_2","first-page":"4681","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Ledig Christian","unstructured":"Christian Ledig, Lucas Theis, Ferenc Husz\u00e1r, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, and Zehan Wang. [n.\u00a0d.]. Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4681\u20134690."},{"key":"e_1_3_3_1_12_2","first-page":"19730","volume-title":"International conference on machine learning","author":"Li Junnan","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. [n.\u00a0d.]. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730\u201319742."},{"key":"e_1_3_3_1_13_2","first-page":"12888","volume-title":"International conference on machine learning","author":"Li Junnan","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. [n.\u00a0d.]. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888\u201312900."},{"key":"e_1_3_3_1_14_2","first-page":"740","volume-title":"Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13","author":"Lin Tsung-Yi","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C\u00a0Lawrence Zitnick. [n.\u00a0d.]. Microsoft coco: Common objects in context. In Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 740\u2013755."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"David\u00a0G Lowe. 2004. Distinctive image features from scale-invariant keypoints. International journal of computer vision 60 (2004) 91\u2013110.","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"e_1_3_3_1_16_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, and Jack Clark. [n.\u00a0d.]. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_3_1_17_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_18_2","doi-asserted-by":"crossref","unstructured":"Vuda\u00a0Sreenivasa Rao R Balakrishna Yousef A\u00a0Baker El-Ebiary Puneet Thapar K\u00a0Aanandha Saravanan and Sanjiv\u00a0Rao Godla. 2024. AI Driven Anomaly Detection in Network Traffic Using Hybrid CNN-GAN. Journal of Advances in Information Technology 15 7.","DOI":"10.12720\/jait.15.7.886-895"},{"key":"e_1_3_3_1_19_2","first-page":"10684","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Rombach Robin","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. [n.\u00a0d.]. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 10684\u201310695."},{"key":"e_1_3_3_1_20_2","unstructured":"Chitwan Saharia William Chan Saurabh Saxena Lala Li Jay Whang Emily\u00a0L Denton Kamyar Ghasemipour Raphael Gontijo\u00a0Lopes Burcu Karagol\u00a0Ayan and Tim Salimans. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems 35 (2022) 36479\u201336494."},{"key":"e_1_3_3_1_21_2","unstructured":"Christoph Schuhmann Romain Beaumont Richard Vencu Cade Gordon Ross Wightman Mehdi Cherti Theo Coombes Aarush Katta Clayton Mullis and Mitchell Wortsman. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems 35 (2022) 25278\u201325294."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Zhou Wang Alan\u00a0C Bovik Hamid\u00a0R Sheikh and Eero\u00a0P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13 4 (2004) 600\u2013612.","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_3_1_23_2","first-page":"586","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Zhang Richard","unstructured":"Richard Zhang, Phillip Isola, Alexei\u00a0A Efros, Eli Shechtman, and Oliver Wang. [n.\u00a0d.]. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition. 586\u2013595."}],"event":{"name":"NLPIR 2024: 2024 8th International Conference on Natural Language Processing and Information Retrieval","acronym":"NLPIR 2024","location":"Okayama Japan"},"container-title":["Proceedings of the 2024 8th International Conference on Natural Language Processing and Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711542.3711560","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711542.3711560","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:29Z","timestamp":1750295909000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711542.3711560"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,13]]},"references-count":22,"alternative-id":["10.1145\/3711542.3711560","10.1145\/3711542"],"URL":"https:\/\/doi.org\/10.1145\/3711542.3711560","relation":{},"subject":[],"published":{"date-parts":[[2024,12,13]]},"assertion":[{"value":"2025-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}