{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:58:46Z","timestamp":1790279926610,"version":"4.1.0"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032369833","type":"print"},{"value":"9783032369840","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-36984-0_21","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:01:30Z","timestamp":1790276490000},"page":"381-398","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Finding Highlight Images In Your Albums: From Benchmark to Agentic MLLMs"],"prefix":"10.1007","author":[{"given":"Rong","family":"Qin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Congcong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaopeng","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanbin","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chensen","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eunil","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi Man","family":"Vong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jufeng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Abdullahu, F., Grabner, H.: Commonly interesting images. In: European Conference on Computer Vision (ECCV), pp. 180\u2013198 (2024)","DOI":"10.1007\/978-3-031-73036-8_11"},{"key":"21_CR2","unstructured":"Achiam, J., et al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"21_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"21_CR4","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"issue":"1","key":"21_CR5","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1186\/1471-2288-13-97","volume":"13","author":"SI Bangdiwala","year":"2013","unstructured":"Bangdiwala, S.I., Shankar, V.: The agreement chart. BMC Med. Res. Methodol. 13(1), 97 (2013)","journal-title":"BMC Med. Res. Methodol."},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Event recognition in photo collections with a stopwatch hmm. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1193\u20131200 (2013)","DOI":"10.1109\/ICCV.2013.151"},{"key":"21_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2020.102973","volume":"74","author":"J Bum","year":"2021","unstructured":"Bum, J., Whang, J.J., Choo, H.: Sentiment-based sub-event segmentation and key photo selection. J. Vis. Commun. Image Represent. 74, 102973 (2021)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"21_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2020.116033","volume":"90","author":"B Celikkale","year":"2021","unstructured":"Celikkale, B., Erdogan, G., Erdem, A., Erdem, E.: Generating visual story graphs with application to photo album summarization. Signal Process. Image Commun. 90, 116033 (2021)","journal-title":"Signal Process. Image Commun."},{"issue":"1","key":"21_CR9","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","volume":"20","author":"J Cohen","year":"1960","unstructured":"Cohen, J.: A coefficient of agreement for nominal scales. Educ. Psychol. Measur. 20(1), 37\u201346 (1960)","journal-title":"Educ. Psychol. Measur."},{"issue":"10","key":"21_CR10","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1016\/j.jclinepi.2005.10.015","volume":"59","author":"HC De Vet","year":"2006","unstructured":"De Vet, H.C., Terwee, C.B., Knol, D.L., Bouter, L.M.: When to use agreement versus reliability measures. J. Clin. Epidemiol. 59(10), 1033\u20131039 (2006)","journal-title":"J. Clin. Epidemiol."},{"key":"21_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"issue":"7","key":"21_CR12","first-page":"8577","volume":"45","author":"T Feng","year":"2022","unstructured":"Feng, T., et al.: Ic9600: A benchmark dataset for automatic image complexity assessment. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 45(7), 8577\u20138593 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Glaser, T., Ben-Baruch, E., Sharir, G., Zamir, N., Noy, A., Zelnik-Manor, L.: Peta: Photo albums event recognition using transformers attention. In: International Conference on Pattern Recognition (ICPR) (2022)","DOI":"10.1109\/ICPR56361.2022.9956129"},{"issue":"7","key":"21_CR14","doi-asserted-by":"publisher","first-page":"1837","DOI":"10.1109\/TMM.2017.2777664","volume":"20","author":"C Guo","year":"2017","unstructured":"Guo, C., Tian, X., Mei, T.: Multigranular event recognition of personal photo albums. IEEE Trans. Multimedia (TMM) 20(7), 1837\u20131847 (2017)","journal-title":"IEEE Trans. Multimedia (TMM)"},{"issue":"1","key":"21_CR15","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1348\/000711006X126600","volume":"61","author":"KL Gwet","year":"2008","unstructured":"Gwet, K.L.: Computing inter-rater reliability and its variance in the presence of high agreement. Br. J. Math. Stat. Psychol. 61(1), 29\u201348 (2008)","journal-title":"Br. J. Math. Stat. Psychol."},{"key":"21_CR16","unstructured":"Hu, E.J., et al.: Lora: Low-rank adaptation of large language models. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Isola, P., Parikh, D., Torralba, A., Oliva, A.: Understanding the intrinsic memorability of images. In: Advances in Neural Information Processing Systems (NeurIPS) (2011)","DOI":"10.21236\/ADA554133"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Khosla, A., Raju, A.S., Torralba, A., Oliva, A.: Understanding and predicting image memorability at a large scale. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2390\u20132398 (2015)","DOI":"10.1109\/ICCV.2015.275"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Kim, J.H., Lee, J.S.: Travel photo album summarization based on aesthetic quality, interestingness, and memorableness. In: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), pp. 1\u20135 (2016)","DOI":"10.1109\/APSIPA.2016.7820889"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Kong, S., Shen, X., Lin, Z., Mech, R., Fowlkes, C.: Photo aesthetics ranking network with attributes and content adaptation. In: European Conference on Computer Vision (ECCV), pp. 662\u2013679 (2016)","DOI":"10.1007\/978-3-319-46448-0_40"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Kosti, R., Alvarez, J.M., Recasens, A., Lapedriza, A.: Emotic: Emotions in context dataset. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 61\u201369 (2017)","DOI":"10.1109\/CVPRW.2017.285"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Kuzovkin, D., Pouli, T., Cozot, R., Le Meur, O., Kervec, J., Bouatouch, K.: Image selection in photo albums. In: ACM International Conference on Multimedia Retrieval (ICMR), pp. 397\u2013404 (2018)","DOI":"10.1145\/3206025.3206077"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Liu, X., Han, Y., Qin, R., Wang, B., Yang, J.: Collaborative feature matching with progressive correspondence learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, pp. 7314\u20137322 (2026)","DOI":"10.1609\/aaai.v40i9.37669"},{"issue":"12","key":"21_CR24","doi-asserted-by":"publisher","first-page":"11254","DOI":"10.1109\/TPAMI.2024.3462453","volume":"46","author":"X Liu","year":"2024","unstructured":"Liu, X., Qin, R., Yan, J., Yang, J.: Ncmnet: Neighbor consistency mining network for two-view correspondence pruning. IEEE Trans. Pattern Anal. Mach. Intell. 46(12), 11254\u201311272 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"21_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"21_CR27","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1109\/TMM.2021.3130752","volume":"25","author":"P Lv","year":"2021","unstructured":"Lv, P., et al.: User-guided personalized image aesthetic assessment based on deep reinforcement learning. IEEE Trans. Multimedia (TMM) 25, 736\u2013749 (2021)","journal-title":"IEEE Trans. Multimedia (TMM)"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Mertens, L., Yargholi, E., Op\u00a0de Beeck, H., Van\u00a0den Stock, J., Vennekens, J.: Findingemo: An image dataset for emotion recognition in the wild. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 4956\u20134996 (2024)","DOI":"10.52202\/079017-0161"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Murray, N., Marchesotti, L., Perronnin, F.: Ava: A large-scale database for aesthetic visual analysis. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2408\u20132415 (2012)","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"21_CR30","unstructured":"Oquab, M., et al.: Dinov2: Learning robust visual features without supervision. Trans. Mach. Learn. Res. J. (TMLR) (2024)"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Ozkose, Y.E., Celikkale, B., Erdem, E., Erdem, A.: Diverse neural photo album summarization. In: International Conference on Image Processing Theory, Tools and Applications (IPTA), pp.\u00a01\u20136 (2019)","DOI":"10.1109\/IPTA.2019.8936084"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Peng, K.C., Chen, T., Sadovnik, A., Gallagher, A.C.: A mixed bag of emotions: Model, predict, and transfer emotion distributions. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 860\u2013868 (2015)","DOI":"10.1109\/CVPR.2015.7298687"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Qin, R., Liu, X., Shi, J., Lin, L., Yang, J.: Boosting the dual-stream architecture in ultra-high resolution segmentation with resolution-biased uncertainty estimation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 25960\u201325970 (2025)","DOI":"10.1109\/CVPR52734.2025.02418"},{"key":"21_CR34","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML), pp. 8748\u20138763 (2021)"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Chen, X., Gupta, A.: Learning visual storylines with skipping recurrent neural networks. In: European Conference on Computer Vision (ECCV), pp. 71\u201388 (2016)","DOI":"10.1007\/978-3-319-46454-1_5"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Tang, Z., Yang, S., Peng, B., Wang, Z., Dong, J.: Revisiting mllm based image quality assessment: Errors and remedy. arXiv preprint arXiv:2511.07812 (2025)","DOI":"10.1609\/aaai.v40i11.37908"},{"key":"21_CR37","unstructured":"Team, K., et\u00a0al.: Kimi k2. 5: Visual agentic intelligence. arXiv preprint arXiv:2602.02276 (2026)"},{"issue":"1","key":"21_CR38","doi-asserted-by":"publisher","first-page":"58","DOI":"10.3758\/s13428-024-02510-4","volume":"57","author":"C Wakeland-Hart","year":"2025","unstructured":"Wakeland-Hart, C., Aly, M.: Predicting image memorability from evoked feelings. Behav. Res. Methods 57(1), 58 (2025)","journal-title":"Behav. Res. Methods"},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Wang, J., Chan, K.C., Loy, C.C.: Exploring clip for assessing the look and feel of images. In: AAAI Conference on Artificial Intelligence (AAAI) (2023)","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Wang, P., Cai, Z., Yang, H., Modolo, D., Swaminathan, A.: Enhancing numerical prediction of mllms with soft labeling. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3424\u20133434 (2025)","DOI":"10.1109\/ICCV51701.2025.00327"},{"key":"21_CR41","unstructured":"Wang, W., et al.: Internvl3. 5: Advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lin, Z., Shen, X., Mech, R., Miller, G., Cottrell, G.W.: Event-specific image importance. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4810\u20134819 (2016)","DOI":"10.1109\/CVPR.2016.520"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lin, Z., Shen, X., Mech, R., Miller, G., Cottrell, G.W.: Recognizing and curating photo albums via event-specific image importance. arXiv preprint arXiv:1707.05911 (2017)","DOI":"10.5244\/C.31.94"},{"issue":"1","key":"21_CR44","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1186\/1471-2288-13-61","volume":"13","author":"N Wongpakaran","year":"2013","unstructured":"Wongpakaran, N., Wongpakaran, T., Wedding, D., Gwet, K.L.: A comparison of cohen\u2019s kappa and gwet\u2019s ac1 when calculating inter-rater reliability coefficients: a study conducted with personality disorder samples. BMC Med. Res. Methodol. 13(1), 61 (2013)","journal-title":"BMC Med. Res. Methodol."},{"key":"21_CR45","unstructured":"Wu, H., et\u00a0al.: Q-align: Teaching lmms for visual scoring via discrete text-defined levels. arXiv preprint arXiv:2312.17090 (2023)"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Wysoczanska, M., et al.: Tell me what is good about this property: Leveraging reviews for segment-personalized image collection summarization. In: AAAI Conference on Artificial Intelligence (AAAI), pp. 22983\u201322989 (2024)","DOI":"10.1609\/aaai.v38i21.30339"},{"key":"21_CR47","doi-asserted-by":"crossref","unstructured":"Yang, J., Huang, Q., Ding, T., Lischinski, D., Cohen-Or, D., Huang, H.: Emoset: A large-scale visual emotion dataset with rich attributes. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 20383\u201320394 (2023)","DOI":"10.1109\/ICCV51070.2023.01864"},{"key":"21_CR48","doi-asserted-by":"crossref","unstructured":"You, Q., Luo, J., Jin, H., Yang, J.: Building a large scale dataset for image emotion recognition: The fine print and the benchmark. In: AAAI Conference on Artificial Intelligence (AAAI), vol. 30 (2016)","DOI":"10.1609\/aaai.v30i1.9987"},{"key":"21_CR49","doi-asserted-by":"crossref","unstructured":"Yu, L., Bansal, M., Berg, T.: Hierarchically-attentive rnn for album summarization and storytelling. In: Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 966\u2013971 (2017)","DOI":"10.18653\/v1\/D17-1101"},{"key":"21_CR50","doi-asserted-by":"publisher","first-page":"134747","DOI":"10.52202\/079017-4282","volume":"37","author":"C Zhao","year":"2024","unstructured":"Zhao, C., Shi, J., Nie, L., Yang, J.: To err like human: Affective bias-inspired measures for visual emotion recognition evaluation. Adv. Neural. Inf. Process. Syst. 37, 134747\u2013134769 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR51","unstructured":"Zhao, C., Zhou, Y., Yang, J.: Attention never lie: Visual attention defocus reveals and rectifies hallucinations in mllms. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8897\u20138906 (2026)"},{"key":"21_CR52","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Zhang, R., Zhang, J., Ye, Y., Luo, Z.: Llamafactory: Unified efficient fine-tuning of 100+ language models. In: Annual Meeting of the Association for Computational Linguistics (ACL), pp. 400\u2013410 (2024)","DOI":"10.18653\/v1\/2024.acl-demos.38"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-36984-0_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:01:41Z","timestamp":1790276501000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36984-0_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032369833","9783032369840"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36984-0_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"25 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}