{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T12:00:14Z","timestamp":1746187214068,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819609079"},{"type":"electronic","value":"9789819609086"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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\/978-981-96-0908-6_7","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T19:25:33Z","timestamp":1733513133000},"page":"114-130","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["OneDiff: A Generalist Model for\u00a0Image Difference Captioning"],"prefix":"10.1007","author":[{"given":"Erdong","family":"Hu","sequence":"first","affiliation":[]},{"given":"Longteng","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Tongtian","family":"Yue","sequence":"additional","affiliation":[]},{"given":"Zijia","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Shuning","family":"Xue","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"7_CR1","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"7_CR2","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C.L., Parikh, D.: Vqa: Visual question answering. In: Proceedings of the IEEE international conference on computer vision. pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"7_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":"7_CR5","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: Learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"7_CR6","unstructured":"Brown, T.B.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)"},{"key":"7_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Forbes, M., Kaeser-Chen, C., Sharma, P., Belongie, S.: Neural naturalist: Generating fine-grained image comparisons. arXiv preprint arXiv:1909.04101 (2019)","DOI":"10.18653\/v1\/D19-1065"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Guo, Z., Wang, T.J.J., Laaksonen, J.: Clip4idc: Clip for image difference captioning. arXiv preprint arXiv:2206.00629 (2022)","DOI":"10.18653\/v1\/2022.aacl-short.5"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: Gqa: A new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Jhamtani, H., Berg-Kirkpatrick, T.: Learning to describe differences between pairs of similar images. arXiv preprint arXiv:1808.10584 (2018)","DOI":"10.18653\/v1\/D18-1436"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., Van Der\u00a0Maaten, L., Fei-Fei, L., Lawrence\u00a0Zitnick, C., Girshick, R.: Clevr: A diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 2901\u20132910 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Kim, H., Kim, J., Lee, H., Park, H., Kim, G.: Agnostic change captioning with cycle consistency. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2095\u20132104 (2021)","DOI":"10.1109\/ICCV48922.2021.00210"},{"key":"7_CR14","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: International conference on machine learning. pp. 19730\u201319742. PMLR (2023)"},{"key":"7_CR15","unstructured":"Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Text summarization branches out. pp. 74\u201381 (2004)"},{"key":"7_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: Common Objects in Context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"7_CR17","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)"},{"key":"7_CR18","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. pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Park, D.H., Darrell, T., Rohrbach, A.: Robust change captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 4624\u20134633 (2019)","DOI":"10.1109\/ICCV.2019.00472"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE international conference on computer vision. pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"7_CR21","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., Beaufays, F.: Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition. arXiv preprint arXiv:1402.1128 (2014)","DOI":"10.21437\/Interspeech.2014-80"},{"key":"7_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1007\/978-3-030-58568-6_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Shi","year":"2020","unstructured":"Shi, X., Yang, X., Gu, J., Joty, S., Cai, J.: Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change Captioning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 574\u2013590. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_34"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Suhr, A., Zhou, S., Zhang, A., Zhang, I., Bai, H., Artzi, Y.: A corpus for reasoning about natural language grounded in photographs. arXiv preprint arXiv:1811.00491 (2018)","DOI":"10.18653\/v1\/P19-1644"},{"issue":"5","key":"7_CR25","doi-asserted-by":"publisher","first-page":"2969","DOI":"10.1002\/int.22821","volume":"37","author":"Y Sun","year":"2022","unstructured":"Sun, Y., Li, L., Yao, T., Lu, T., Zheng, B., Yan, C., Zhang, H., Bao, Y., Ding, G., Slabaugh, G.: Bidirectional difference locating and semantic consistency reasoning for change captioning. Int. J. Intell. Syst. 37(5), 2969\u20132987 (2022)","journal-title":"Int. J. Intell. Syst."},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Tan, H., Dernoncourt, F., Lin, Z., Bui, T., Bansal, M.: Expressing visual relationships via language. arXiv preprint arXiv:1906.07689 (2019)","DOI":"10.18653\/v1\/P19-1182"},{"key":"7_CR27","doi-asserted-by":"publisher","first-page":"4002","DOI":"10.1109\/TIP.2024.3413599","volume":"33","author":"Y Tang","year":"2024","unstructured":"Tang, Y., Wang, W., Zhang, C., Liu, J., Zhao, Y.: Learnable feature augmentation framework for temporal action localization. IEEE Trans. Image Process. 33, 4002\u20134015 (2024). https:\/\/doi.org\/10.1109\/TIP.2024.3413599","journal-title":"IEEE Trans. Image Process."},{"key":"7_CR28","doi-asserted-by":"publisher","first-page":"2340","DOI":"10.1109\/TMM.2023.3295090","volume":"26","author":"Y Tang","year":"2024","unstructured":"Tang, Y., Wang, W., Zhang, C., Liu, J., Zhao, Y.: Temporal action proposal generation with action frequency adaptive network. IEEE Trans. Multimedia 26, 2340\u20132353 (2024). https:\/\/doi.org\/10.1109\/TMM.2023.3295090","journal-title":"IEEE Trans. Multimedia"},{"key":"7_CR29","unstructured":"Team, G., Anil, R., Borgeaud, S., Wu, Y., Alayrac, J.B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A.M., Hauth, A., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Tu, Y., Li, L., Su, L., Du, J., Lu, K., Huang, Q.: Adaptive representation disentanglement network for change captioning. IEEE Transactions on Image Processing (2023)","DOI":"10.1109\/TIP.2023.3268004"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Tu, Y., Li, L., Su, L., Lu, K., Huang, Q.: Neighborhood contrastive transformer for change captioning. IEEE Transactions on Multimedia (2023)","DOI":"10.1109\/TMM.2023.3254162"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Tu, Y., Li, L., Su, L., Zha, Z.J., Yan, C., Huang, Q.: Self-supervised cross-view representation reconstruction for change captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2805\u20132815 (2023)","DOI":"10.1109\/ICCV51070.2023.00263"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: Cider: Consensus-based image description evaluation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"7_CR34","unstructured":"Wang, W., Lv, Q., Yu, W., Hong, W., Qi, J., Wang, Y., Ji, J., Yang, Z., Zhao, L., Song, X., et\u00a0al.: Cogvlm: Visual expert for pretrained language models. arXiv preprint arXiv:2311.03079 (2023)"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Yan, A., Wang, X.E., Fu, T.J., Wang, W.Y.: L2c: Describing visual differences needs semantic understanding of individuals. arXiv preprint arXiv:2102.01860 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.196"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Yao, L., Wang, W., Jin, Q.: Image difference captioning with pre-training and contrastive learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036, pp. 3108\u20133116 (2022)","DOI":"10.1609\/aaai.v36i3.20218"},{"key":"7_CR37","unstructured":"Zhang, R., Han, J., Liu, C., Gao, P., Zhou, A., Hu, X., Yan, S., Lu, P., Li, H., Qiao, Y.: Llama-adapter: Efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0908-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T20:09:52Z","timestamp":1733515792000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0908-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9789819609079","9789819609086"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0908-6_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}