{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:08:59Z","timestamp":1789124939682,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370372","type":"print"},{"value":"9783032370389","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\/978-3-032-37038-9_28","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:41:44Z","timestamp":1789123304000},"page":"502-519","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TRINITY: A Multi-perspective Benchmark for\u00a0Personal-Style Video Highlight Detection"],"prefix":"10.1007","author":[{"given":"Qianqian","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyun Bin","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Denzel Elden","family":"Wijaya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangkai","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"issue":"6","key":"28_CR1","doi-asserted-by":"publisher","first-page":"680","DOI":"10.3390\/sym16060680","volume":"16","author":"F Alharbi","year":"2024","unstructured":"Alharbi, F., Habib, S., Albattah, W., Jan, Z., Alanazi, M.D., Islam, M.: Effective video summarization using channel attention-assisted encoder-decoder framework. Symmetry 16(6), 680 (2024)","journal-title":"Symmetry"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Badamdorj, T., Rochan, M., Wang, Y., Cheng, L.: Joint visual and audio learning for video highlight detection. In: ICCV, pp. 8127\u20138137 (2021)","DOI":"10.1109\/ICCV48922.2021.00802"},{"key":"28_CR3","unstructured":"Bai, S., et al.: Qwen3-VL technical report (2025)"},{"key":"28_CR4","unstructured":"Beedu, A., Essa, I.: HierSum: a global and local attention mechanism for video summarization. arXiv preprint arXiv:2504.18689 (2025)"},{"key":"28_CR5","unstructured":"Cha, C., You, T., Yeh, R.A., Vitelli, S., Wang, S.H.: Conflict-averse gradient descent for multi-task learning. In: Advances in Neural Information Processing Systems, vol. 34, pp. 18803\u201318816 (2021)"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Chang, A., De Melo, C., Lukin, S.M.: Aha! - predicting what matters next: online highlight detection without looking ahead. In: NeurIPS (2025)","DOI":"10.52202\/085713-0275"},{"key":"28_CR7","unstructured":"Grauman, K., Westbury, A., et\u00a0al.: Ego4D: around the world in 3,000 hours of egocentric video. In: CVPR, pp. 18995\u201319012 (2022)"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Gygli, M., Song, Y., Cao, L.: Video2GIF: automatic generation of animated GIFs from video. In: CVPR, pp. 1001\u20131009 (2016)","DOI":"10.1109\/CVPR.2016.114"},{"key":"28_CR9","unstructured":"Hong, S.E., Choi, G.M., Kim, J.H.: CSTA: CNN-based spatiotemporal attention for video summarization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18859\u201318868 (2024)"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Islam, Z., Paul, S., Rochan, M.: Unsupervised video highlight detection by learning from audio and visual recurrence. In: Proceedings of the WACV, pp. 8702\u20138711 (2025)","DOI":"10.1109\/WACV61041.2025.00843"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Jang, J., Park, J., Kim, J., Kwon, H., Sohn, K.: Knowing where to focus: event-aware transformer for video grounding. In: ICCV, pp. 13846\u201313856 (2023)","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"28_CR12","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Ultralytics YOLOv8 (2023)"},{"issue":"6","key":"28_CR13","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1111\/j.1467-9280.1993.tb00589.x","volume":"4","author":"D Kahneman","year":"1993","unstructured":"Kahneman, D., Fredrickson, B.L., Schreiber, C.A., Redelmeier, D.A.: When more pain is preferred to less: adding a better end. Psychol. Sci. 4(6), 401\u2013405 (1993)","journal-title":"Psychol. Sci."},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Ke, J., Wang, Q., Wang, Y., Milanfar, P., Yang, F.: MUSIQ: multi-scale image quality transformer. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Kim, K., Hahm, J., Kim, S., Sul, J., Kim, B., Lee, J.: SummDiff: generative modeling of video summarization with diffusion. In: ICCV, pp. 15096\u201315106 (2025)","DOI":"10.1109\/ICCV51701.2025.01401"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Kirk, D., Sellen, A., Harper, R., Wood, K.: Understanding videowork. In: Proceedings of the CHI, pp. 61\u201370 (2007)","DOI":"10.1145\/1240624.1240634"},{"key":"28_CR17","unstructured":"Koutras, P., Maragos, P.: Combining global and local attention with positional encoding for video summarization. In: 2021 IEEE International Symposium on Multimedia (ISM), pp. 41\u201348 (2021)"},{"key":"28_CR18","unstructured":"Lee, H.B., Yang, E., Hwang, S.J.: Deep asymmetric multi-task feature learning. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 2956\u20132964. PMLR (2018)"},{"key":"28_CR19","unstructured":"Lei, J., Berg, T.L., Bansal, M.: Detecting moments and highlights in videos via natural language queries. In: NeurIPS, vol. 34, pp. 11846\u201311858 (2021)"},{"key":"28_CR20","first-page":"1911","volume":"33","author":"T Li","year":"2024","unstructured":"Li, T., Sun, Z., Xiao, X.: Unsupervised modality-transferable video highlight detection with representation activation sequence learning. IEEE TIP 33, 1911\u20131922 (2024)","journal-title":"IEEE TIP"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Lin, K.Q., et al.: UniVTG: towards unified video-language temporal grounding. In: ICCV, pp. 2794\u20132804 (2023)","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, S., Wu, Y., Chen, C.W., Shan, Y., Qie, X.: UMT: unified multi-modal transformers for joint video moment retrieval and highlight detection. In: CVPR, pp. 3042\u20133051 (2022)","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Psychology of Learning and Motivation, vol.\u00a024, pp. 109\u2013165. Academic Press (1989)","DOI":"10.1016\/S0079-7421(08)60536-8"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Garcia\u00a0del Molino, A., Gygli, M.: PHD-GIFs: personalized highlight detection for automatic GIF creation. In: ACM MM, pp. 600\u2013608 (2018)","DOI":"10.1145\/3240508.3240599"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Moon, W., Hyun, S., Park, S., Park, D., Heo, J.P.: Query-dependent video representation for moment retrieval and highlight detection. In: CVPR, pp. 23023\u201323033 (2023)","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"28_CR26","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Ren, Z., et al.: VEATIC: video-based emotion and affect tracking in context dataset. In: Proceedings of the WACV, pp. 4467\u20134477 (2024)","DOI":"10.1109\/WACV57701.2024.00441"},{"key":"28_CR28","unstructured":"Ren, Z., Wang, Y., Ke, T.W., Guo, Y., Yu, S.X., Whitney, D.: Region-based emotion recognition via superpixel feature pooling. In: CVPRW (2024)"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Saigo, S., Hayami, T., Watanabe, H.: Enhancing continuous emotion recognition via visually diverse frame selection. In: Proceedings of the IEEE Global Conference on Consumer Electronics (GCCE), pp. 1275\u20131278 (2025)","DOI":"10.1109\/GCCE65946.2025.11274966"},{"key":"28_CR30","unstructured":"Savchenko, A.: Facial expression recognition with adaptive frame rate based on multiple testing correction. In: ICML, pp. 30119\u201330129 (2023)"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Savchenko, A.V., Savchenko, L.V., Makarov, I.: Classifying emotions and engagement in online learning based on a single facial expression recognition neural network. IEEE Trans. Affect Comput. (2022)","DOI":"10.1109\/TAFFC.2022.3188390"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Sellen, A.J., Fogg, A., Aitken, M., Hodges, S., Rother, C., Wood, K.: Do life-logging technologies support memory for the past? An experimental study using SenseCam. In: Proceedings of the CHI, pp. 81\u201390 (2007)","DOI":"10.1145\/1240624.1240636"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Senushkin, D., Belikov, N., Galimaldinov, A., Konushin, A.: Independent component alignment for multi-task learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20083\u201320093 (2023)","DOI":"10.1109\/CVPR52729.2023.01923"},{"key":"28_CR34","doi-asserted-by":"crossref","unstructured":"Song, Y., Vallmitjana, J., Stent, A., Jaimes, A.: TvSum: summarizing web videos using titles. In: CVPR, pp. 5179\u20135187 (2015)","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"28_CR35","unstructured":"Su, J., Lu, Y., Pan, S., Wen, B., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. arXiv preprint arXiv:2104.09864 (2021)"},{"key":"28_CR36","doi-asserted-by":"crossref","unstructured":"Sul, J., Han, J., Lee, J.: Mr. HiSum: a large-scale dataset for video highlight detection and summarization. In: NeurIPS (2023)","DOI":"10.52202\/075280-1764"},{"key":"28_CR37","doi-asserted-by":"crossref","unstructured":"Sun, H., Zhou, M., Chen, W., Xie, W.: TR-DETR: task-reciprocal transformer for joint moment retrieval and highlight detection. In: AAAI, vol. 38, pp. 4998\u20135007 (2024)","DOI":"10.1609\/aaai.v38i5.28304"},{"key":"28_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1007\/978-3-319-10590-1_51","volume-title":"Computer Vision \u2013 ECCV 2014","author":"M Sun","year":"2014","unstructured":"Sun, M., Farhadi, A., Seitz, S.: Ranking domain-specific highlights by analyzing edited videos. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 787\u2013802. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_51"},{"key":"28_CR39","unstructured":"Wang, P., et\u00a0al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"28_CR40","doi-asserted-by":"crossref","unstructured":"Wei, F., Wang, B., Ge, T., Jiang, Y., Li, W., Duan, L.: Learning pixel-level distinctions for video highlight detection. In: CVPR, pp. 3073\u20133082 (2022)","DOI":"10.1109\/CVPR52688.2022.00308"},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Xu, M., Wang, H., Ni, B., Zhu, R., Sun, Z., Wang, C.: Cross-category video highlight detection via set-based learning. In: ICCV, pp. 7970\u20137979 (2021)","DOI":"10.1109\/ICCV48922.2021.00787"},{"key":"28_CR42","doi-asserted-by":"crossref","unstructured":"Yao, T., Mei, T., Rui, Y.: Highlight detection with pairwise deep ranking for first-person video summarization. In: CVPR, pp. 982\u2013990 (2016)","DOI":"10.1109\/CVPR.2016.112"},{"key":"28_CR43","doi-asserted-by":"crossref","unstructured":"Ye, Q., et al.: Temporal cue guided video highlight detection with low-rank audio-visual fusion. In: ICCV, pp. 7950\u20137959 (2021)","DOI":"10.1109\/ICCV48922.2021.00785"},{"key":"28_CR44","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 5824\u20135836 (2020)"},{"key":"28_CR45","doi-asserted-by":"crossref","unstructured":"Zeng, X., et al.: PromptEmo: learning emotion with bilateral textual prompts in multi-domain open-set scenarios. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a040, pp. 12322\u201312330 (2026)","DOI":"10.1609\/aaai.v40i15.38224"},{"key":"28_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, C., Zhao, Z., Zhao, X.: Weakly-supervised video highlight detection by characteristic and commonality modeling. In: ICASSP, pp.\u00a01\u20135 (2025)","DOI":"10.1109\/ICASSP49660.2025.10888111"}],"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\/978-3-032-37038-9_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:41:58Z","timestamp":1789123318000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37038-9_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370372","9783032370389"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37038-9_28","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":"12 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"}}]}}