{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T17:35:00Z","timestamp":1742924100364,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031730320"},{"type":"electronic","value":"9783031730337"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-73033-7_25","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:03:55Z","timestamp":1730333035000},"page":"441-458","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HiFi-Score: Fine-Grained Image Description Evaluation with\u00a0Hierarchical Parsing Graphs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1817-2390","authenticated-orcid":false,"given":"Ziwei","family":"Yao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1830-2595","authenticated-orcid":false,"given":"Ruiping","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3024-4404","authenticated-orcid":false,"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"25_CR1","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.cviu.2017.12.004","volume":"173","author":"S Aditya","year":"2018","unstructured":"Aditya, S., Yang, Y., Baral, C., Aloimonos, Y., Ferm\u00fcller, C.: Image understanding using vision and reasoning through scene description graph. Comput. Vis. Image Underst. 173, 33\u201345 (2018)","journal-title":"Comput. Vis. Image Underst."},{"key":"25_CR2","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: Proceedings of the 36th International Conference on Neural Information Processing Systems (NeurIPS), pp. 23716\u201323736 (2022)"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: SPICE: semantic propositional image caption evaluation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 382\u2013398 (2016)","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"25_CR4","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Chan, D., Petryk, S., Gonzalez, J., Darrell, T., Canny, J.: CLAIR: evaluating image captions with large language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 13638\u201313646 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.841"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., et al.: UNITER: universal image-text representation learning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 104\u2013120 (2020)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Cornia, M., Baraldi, L., Cucchiara, R.: Show, control and tell: a framework for generating controllable and grounded captions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8307\u20138316 (2019)","DOI":"10.1109\/CVPR.2019.00850"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Cui, Y., Yang, G., Veit, A., Huang, X., Belongie, S.: Learning to evaluate image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5804\u20135812 (2018)","DOI":"10.1109\/CVPR.2018.00608"},{"key":"25_CR9","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. In: Proceedings of the 37th International Conference on Neural Information Processing Systems (NeurIPS), pp. 49250\u201349267 (2023)"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Deng, C., Ding, N., Tan, M., Wu, Q.: Length-controllable image captioning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 712\u2013729 (2020)","DOI":"10.1007\/978-3-030-58601-0_42"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Deshpande, A., Aneja, J., Wang, L., Schwing, A.G., Forsyth, D.: Fast, diverse and accurate image captioning guided by part-of-speech. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10695\u201310704 (2019)","DOI":"10.1109\/CVPR.2019.01095"},{"key":"25_CR12","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), pp. 4171\u20134186 (2019)"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Le\u00a0Bras, R., Choi, Y.: CLIPScore: a reference-free evaluation metric for image captioning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 7514\u20137528 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"25_CR14","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh, M., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. J. Artif. Intell. Res. 47, 853\u2013899 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Hu, A., Chen, S., Zhang, L., Jin, Q.: InfoMetIC: an informative metric for reference-free image caption evaluation. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pp. 3171\u20133185 (2023)","DOI":"10.18653\/v1\/2023.acl-long.178"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Jain, J., Li, J., Chiu, M.T., Hassani, A., Orlov, N., Shi, H.: OneFormer: one transformer to rule universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2989\u20132998 (2023)","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, M., Hu, J., Huang, Q., Zhang, L., Diesner, J., Gao, J.: REO-relevance, extraness, omission: a fine-grained evaluation for image captioning. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 1475\u20131480 (2019)","DOI":"10.18653\/v1\/D19-1156"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, M., et al.: TIGEr: text-to-image grounding for image caption evaluation. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 2141\u20132152 (2019)","DOI":"10.18653\/v1\/D19-1220"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: DenseCap: fully convolutional localization networks for dense captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4565\u20134574 (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Kasai, J., et al.: Transparent human evaluation for image captioning. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), pp. 3464\u20133478 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.254"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Kim, D.J., Choi, J., Oh, T.H., Kweon, I.S.: Dense relational captioning: triple-stream networks for relationship-based captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6271\u20136280 (2019)","DOI":"10.1109\/CVPR.2019.00643"},{"key":"25_CR22","unstructured":"Kirillov, A., et al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Krause, J., Johnson, J., Krishna, R., Fei-Fei, L.: A hierarchical approach for generating descriptive image paragraphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 317\u2013325 (2017)","DOI":"10.1109\/CVPR.2017.356"},{"key":"25_CR24","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"25_CR25","unstructured":"Kusner, M., Sun, Y., Kolkin, N., Weinberger, K.: From word embeddings to document distances. In: Proceedings of the 32nd International Conference on Machine Learning (ICML), pp. 957\u2013966 (2015)"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Lee, H., Yoon, S., Dernoncourt, F., Bui, T., Jung, K.: UMIC: an unreferenced metric for image captioning via contrastive learning. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP), pp. 220\u2013226 (2021)","DOI":"10.18653\/v1\/2021.acl-short.29"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Proceedings of the European conference on computer vision (ECCV), pp. 201\u2013216 (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"25_CR28","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: Proceedings of the 40th International Conference on Machine Learning (ICML), pp. 19730\u201319742 (2023)"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Li, L.H., et al.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"25_CR30","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"25_CR31","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Proceedings of the 37th International Conference on Neural Information Processing Systems (NeurIPS), pp. 34892\u201334916 (2023)"},{"key":"25_CR32","unstructured":"Lu, Y., Yang, X., Li, X., Wang, X.E., Wang, W.Y.: LLMScore: unveiling the power of large language models in text-to-image synthesis evaluation. In: Proceedings of the 37th International Conference on Neural Information Processing Systems (NeurIPS), pp. 23075\u201323093 (2023)"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Madhyastha, P., Wang, J., Specia, L.: VIFIDEL: evaluating the visual fidelity of image descriptions. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 6539\u20136550 (2019)","DOI":"10.18653\/v1\/P19-1654"},{"issue":"3","key":"25_CR34","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1016\/0010-0285(77)90012-3","volume":"9","author":"D Navon","year":"1977","unstructured":"Navon, D.: Forest before trees: the precedence of global features in visual perception. Cogn. Psychol. 9(3), 353\u2013383 (1977)","journal-title":"Cogn. Psychol."},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"25_CR36","unstructured":"Peng, Z., et al.: Grounding multimodal large language models to the world. In: Proceedings of the 12th International Conference on Learning Representations (ICLR) (2024)"},{"key":"25_CR37","doi-asserted-by":"crossref","unstructured":"Pont-Tuset, J., Uijlings, J., Changpinyo, S., Soricut, R., Ferrari, V.: Connecting vision and language with localized narratives. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 647\u2013664 (2020)","DOI":"10.1007\/978-3-030-58558-7_38"},{"key":"25_CR38","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Sarto, S., Barraco, M., Cornia, M., Baraldi, L., Cucchiara, R.: Positive-augmented contrastive learning for image and video captioning evaluation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6914\u20136924 (2023)","DOI":"10.1109\/CVPR52729.2023.00668"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Sharif, N., Bennamoun, M., White, L.R., Shah, S.A.A.: Learning-based composite metrics for improved caption evaluation. In: Proceedings of ACL 2018, Student Research Workshop, pp. 14\u201320 (2018)","DOI":"10.18653\/v1\/P18-3003"},{"key":"25_CR41","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"25_CR42","doi-asserted-by":"crossref","unstructured":"Wang, S., Yao, Z., Wang, R., Wu, Z., Chen, X.: FAIEr: fidelity and adequacy ensured image caption evaluation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14050\u201314059 (2021)","DOI":"10.1109\/CVPR46437.2021.01383"},{"key":"25_CR43","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: BERTScore: evaluating text generation with bert. In: Proceedings of the 8th International Conference on Learning Representations (ICLR) (2020)"},{"key":"25_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, T., Wu, X.: Pyramid feature attention network for saliency detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3085\u20133094 (2019)","DOI":"10.1109\/CVPR.2019.00320"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73033-7_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:41:21Z","timestamp":1730335281000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73033-7_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031730320","9783031730337"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73033-7_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}