{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:47:17Z","timestamp":1765309637672,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","funder":[{"name":"The Fundamental Research Funds for the Central Universities","award":["N2104027,N2404011"],"award-info":[{"award-number":["N2104027,N2404011"]}]},{"name":"Innovation Fund of Chinese Universities Industry-University-Research","award":["2020HYA06003"],"award-info":[{"award-number":["2020HYA06003"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2021B1515120064"],"award-info":[{"award-number":["2021B1515120064"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755762","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:17Z","timestamp":1761375257000},"page":"5120-5129","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Noise-Aware Decoding with Salient Region Enhancing for Zero-Shot Image Captioning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1184-0596","authenticated-orcid":false,"given":"YuXin","family":"Xie","sequence":"first","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0673-6767","authenticated-orcid":false,"given":"Dongyue","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, China and National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Northeastern University, Shenyang, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1729-2583","authenticated-orcid":false,"given":"Yue","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1424-798X","authenticated-orcid":false,"given":"Tong","family":"Jia","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6863-8516","authenticated-orcid":false,"given":"Shizhuo","family":"Deng","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, China and Foshan Graduate School of Innovation, Northeastern University, Foshan, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Nocaps: Novel object captioning at scale.","author":"Agrawal Harsh","year":"2019","unstructured":"Harsh Agrawal, Karan Desai, Yufei Wang, Xinlei Chen, Rishabh Jain, Mark Johnson, Dhruv Batra, Devi Parikh, Stefan Lee, and Peter Anderson. 2019. Nocaps: Novel object captioning at scale. (2019), 8948--8957."},{"key":"e_1_3_2_1_2_1","volume-title":"Guided open vocabulary image captioning with constrained beam search. arXiv preprint arXiv:1612.00576","author":"Anderson Peter","year":"2016","unstructured":"Peter Anderson, Basura Fernando, Mark Johnson, and Stephen Gould. 2016. Guided open vocabulary image captioning with constrained beam search. arXiv preprint arXiv:1612.00576 (2016)."},{"key":"e_1_3_2_1_3_1","volume-title":"Spice: Semantic propositional image caption evaluation.","author":"Anderson Peter","year":"2016","unstructured":"Peter Anderson, Basura Fernando, Mark Johnson, and Stephen Gould. 2016. Spice: Semantic propositional image caption evaluation. (2016), 382--398."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Peter Anderson Xiaodong He Chris Buehler Damien Teney Mark Johnson Stephen Gould and Lei Zhang. 2018. Bottom-up and top-down attention for image captioning and visual question answering. (2018) 6077--6086.","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_5_1","volume-title":"International conference on machine learning. PMLR, 2206--2240","author":"Borgeaud Sebastian","year":"2022","unstructured":"Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George Bm Van Den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, et al. 2022. Improving language models by retrieving from trillions of tokens. In International conference on machine learning. PMLR, 2206--2240."},{"key":"e_1_3_2_1_6_1","volume-title":"Universal captioner: Inducing content-style separation in vision-and-language model training. arXiv preprint arXiv:2111.12727 2","author":"Cornia Marcella","year":"2022","unstructured":"Marcella Cornia, Lorenzo Baraldi, Giuseppe Fiameni, and Rita Cucchiara. 2022. Universal captioner: Inducing content-style separation in vision-and-language model training. arXiv preprint arXiv:2111.12727 2 (2022)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"e_1_3_2_1_8_1","first-page":"7443","article-title":"Few-shot generation via recalling brain-inspired episodic-semantic memory","volume":"36","author":"Duan Zhibin","year":"2023","unstructured":"Zhibin Duan, Zhiyi Lv, Chaojie Wang, Bo Chen, Bo An, and Mingyuan Zhou. 2023. Few-shot generation via recalling brain-inspired episodic-semantic memory. Advances in Neural Information Processing Systems 36 (2023), 7443--7461.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_9_1","unstructured":"Junjie Fei Teng Wang Jinrui Zhang Zhenyu He Chengjie Wang and Feng Zheng. 2023. Transferable decoding with visual entities for zero-shot image captioning. (2023) 3136--3146."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. PMLR, 3929--3938","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. 2020. Retrieval augmented language model pre-training. In International conference on machine learning. PMLR, 3929--3938."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.8"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Andrej Karpathy and Li Fei-Fei. 2015. Deep visual-semantic alignments for generating image descriptions. (2015) 3128--3137.","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_15_1","volume-title":"Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick SH Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering.. In EMNLP (1). 6769--6781."},{"key":"e_1_3_2_1_16_1","volume-title":"Nearest neighbor machine translation. arXiv preprint arXiv:2010.00710","author":"Khandelwal Urvashi","year":"2020","unstructured":"Urvashi Khandelwal, Angela Fan, Dan Jurafsky, Luke Zettlemoyer, and Mike Lewis. 2020. Nearest neighbor machine translation. arXiv preprint arXiv:2010.00710 (2020)."},{"key":"e_1_3_2_1_17_1","volume-title":"Generalization through memorization: Nearest neighbor language models. arXiv preprint arXiv:1911.00172","author":"Khandelwal Urvashi","year":"2019","unstructured":"Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, and Mike Lewis. 2019. Generalization through memorization: Nearest neighbor language models. arXiv preprint arXiv:1911.00172 (2019)."},{"key":"e_1_3_2_1_18_1","unstructured":"Dong-Jin Kim Jinsoo Choi Tae-Hyun Oh and In So Kweon. 2019. Dense relational captioning: Triple-stream networks for relationship-based captioning. (2019) 6271--6280."},{"key":"e_1_3_2_1_19_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_20_1","volume-title":"Latent retrieval for weakly supervised open domain question answering. arXiv preprint arXiv:1906.00300","author":"Lee Kenton","year":"2019","unstructured":"Kenton Lee, Ming-Wei Chang, and Kristina Toutanova. 2019. Latent retrieval for weakly supervised open domain question answering. arXiv preprint arXiv:1906.00300 (2019)."},{"key":"e_1_3_2_1_21_1","volume-title":"Ifcap: Image-like retrieval and frequency-based entity filtering for zero-shot captioning. arXiv preprint arXiv:2409.18046","author":"Lee Soeun","year":"2024","unstructured":"Soeun Lee, Si-Woo Kim, Taewhan Kim, and Dong-Jin Kim. 2024. Ifcap: Image-like retrieval and frequency-based entity filtering for zero-shot captioning. arXiv preprint arXiv:2409.18046 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730--19742."},{"key":"e_1_3_2_1_23_1","volume-title":"International conference on machine learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888--12900."},{"key":"e_1_3_2_1_24_1","volume-title":"Decap: Decoding clip latents for zero-shot captioning via text-only training. arXiv preprint arXiv:2303.03032","author":"Li Wei","year":"2023","unstructured":"Wei Li, Linchao Zhu, Longyin Wen, and Yi Yang. 2023. Decap: Decoding clip latents for zero-shot captioning via text-only training. arXiv preprint arXiv:2303.03032 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings, Part XXX 16","author":"Li Xiujun","year":"2020","unstructured":"Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, et al. 2020. Oscar: Object-semantics aligned pre-training for vision-language tasks. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXX 16. Springer, 121--137."},{"key":"e_1_3_2_1_26_1","volume-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks.","author":"Li Xiujun","year":"2020","unstructured":"Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, et al. 2020. Oscar: Object-semantics aligned pre-training for vision-language tasks. (2020), 121--137."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Tsung-Yi Lin Michael Maire Serge Belongie James Hays Pietro Perona Deva Ramanan Piotr Doll\u00e1r and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. (2014) 740--755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28178"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"e_1_3_2_1_33_1","volume-title":"Gnn-lm: Language modeling based on global contexts via gnn. arXiv preprint arXiv:2110.08743","author":"Meng Yuxian","year":"2021","unstructured":"Yuxian Meng, Shi Zong, Xiaoya Li, Xiaofei Sun, Tianwei Zhang, Fei Wu, and Jiwei Li. 2021. Gnn-lm: Language modeling based on global contexts via gnn. arXiv preprint arXiv:2110.08743 (2021)."},{"key":"e_1_3_2_1_34_1","volume-title":"Text-only training for image captioning using noise-injected clip. arXiv preprint arXiv:2211.00575","author":"Nukrai David","year":"2022","unstructured":"David Nukrai, Ron Mokady, and Amir Globerson. 2022. Text-only training for image captioning using noise-injected clip. arXiv preprint arXiv:2211.00575 (2022)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Kishore Papineni Salim Roukos Todd Ward and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. (2002) 311--318.","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Bryan A Plummer LiweiWang ChrisMCervantes Juan C Caicedo Julia Hockenmaier and Svetlana Lazebnik. 2015. Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models. (2015) 2641--2649.","DOI":"10.1109\/ICCV.2015.303"},{"key":"e_1_3_2_1_37_1","volume-title":"Mining fine-grained image-text alignment for zero-shot captioning via text-only training. 38, 5","author":"Qiu Longtian","year":"2024","unstructured":"Longtian Qiu, Shan Ning, and Xuming He. 2024. Mining fine-grained image-text alignment for zero-shot captioning via text-only training. 38, 5 (2024), 4605--4613."},{"key":"e_1_3_2_1_38_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever.","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. CoRR abs\/2103.00020 (2021). arXiv:2103.00020 https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Rita Ramos Bruno Martins Desmond Elliott and Yova Kementchedjhieva. 2023. Smallcap: lightweight image captioning prompted with retrieval augmentation. (2023) 2840--2849.","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Yu Song Xiaohui Yang Rongping Huang Bai Haifeng and Lili Yang. 2024. CSCCap: Plugging Sparse Coding in Zero-Shot Image Captioning. (2024) 1--5.","DOI":"10.1145\/3696409.3700286"},{"key":"e_1_3_2_1_41_1","volume-title":"Language models can see: Plugging visual controls in text generation. arXiv preprint arXiv:2205.02655","author":"Su Yixuan","year":"2022","unstructured":"Yixuan Su, Tian Lan, Yahui Liu, Fangyu Liu, Dani Yogatama, YanWang, Lingpeng Kong, and Nigel Collier. 2022. Language models can see: Plugging visual controls in text generation. arXiv preprint arXiv:2205.02655 (2022)."},{"key":"e_1_3_2_1_42_1","volume-title":"Zero-shot imageto- text generation for visual-semantic arithmetic. arXiv preprint arXiv:2111.14447 2","author":"Tewel Yoad","year":"2021","unstructured":"Yoad Tewel, Yoav Shalev, Idan Schwartz, and Lior Wolf. 2021. Zero-shot imageto- text generation for visual-semantic arithmetic. arXiv preprint arXiv:2111.14447 2 (2021)."},{"key":"e_1_3_2_1_43_1","volume-title":"Cider: Consensus-based image description evaluation.","author":"Vedantam Ramakrishna","year":"2015","unstructured":"Ramakrishna Vedantam, C Lawrence Zitnick, and Devi Parikh. 2015. Cider: Consensus-based image description evaluation. (2015), 4566--4575."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.130"},{"key":"e_1_3_2_1_45_1","volume-title":"Show and tell: Lessons learned from the 2015 mscoco image captioning challenge","author":"Vinyals Oriol","year":"2016","unstructured":"Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan. 2016. Show and tell: Lessons learned from the 2015 mscoco image captioning challenge. IEEE transactions on pattern analysis and machine intelligence 39, 4 (2016), 652--663."},{"key":"e_1_3_2_1_46_1","volume-title":"From association to generation: Text-only captioning by unsupervised cross-modal mapping. arXiv preprint arXiv:2304.13273","author":"Wang Junyang","year":"2023","unstructured":"Junyang Wang, Ming Yan, Yi Zhang, and Jitao Sang. 2023. From association to generation: Text-only captioning by unsupervised cross-modal mapping. arXiv preprint arXiv:2304.13273 (2023)."},{"key":"e_1_3_2_1_47_1","volume-title":"Text Data-Centric Image Captioning with Interactive Prompts. arXiv preprint arXiv:2403.19193","author":"Wang Yiyu","year":"2024","unstructured":"Yiyu Wang, Hao Luo, Jungang Xu, Yingfei Sun, and Fan Wang. 2024. Text Data-Centric Image Captioning with Interactive Prompts. arXiv preprint arXiv:2403.19193 (2024)."},{"key":"e_1_3_2_1_48_1","volume-title":"attend and tell: Neural image caption generation with visual attention. (2015)","author":"Xu Kelvin","year":"2048","unstructured":"Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. (2015), 2048--2057."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","unstructured":"Ting Yao Yingwei Pan Yehao Li and Tao Mei. 2018. Exploring visual relationship for image captioning. (2018) 684--699.","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"e_1_3_2_1_50_1","unstructured":"Andy Zeng Maria Attarian Brian Ichter Krzysztof Choromanski Adrian Wong StefanWelker Federico Tombari Aveek Purohit Michael Ryoo Vikas Sindhwani et al. 2022. Socratic models: Composing zero-shot multimodal reasoning with language. arXiv preprint arXiv:2204.00598 (2022)."},{"key":"e_1_3_2_1_51_1","volume-title":"Meacap: Memory-augmented zero-shot image captioning.","author":"Zeng Zequn","year":"2024","unstructured":"Zequn Zeng, Yan Xie, Hao Zhang, Chiyu Chen, Bo Chen, and Zhengjue Wang. 2024. Meacap: Memory-augmented zero-shot image captioning. (2024), 14100--14110."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"e_1_3_2_1_53_1","volume-title":"Unified vision-language pre-training for image captioning and vqa. 34, 07","author":"Zhou Luowei","year":"2020","unstructured":"Luowei Zhou, Hamid Palangi, Lei Zhang, Houdong Hu, Jason Corso, and Jianfeng Gao. 2020. Unified vision-language pre-training for image captioning and vqa. 34, 07 (2020), 13041--13049."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:45:07Z","timestamp":1765309507000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755762"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":53,"alternative-id":["10.1145\/3746027.3755762","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755762","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}