{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T21:08:09Z","timestamp":1788988089576,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373557","type":"print"},{"value":"9783032373564","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\/978-3-032-37356-4_15","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:26:39Z","timestamp":1788985599000},"page":"262-279","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ScanFocus: A Coarse-to-Fine Framework for\u00a0Spatio-Temporal Video Grounding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9053-3469","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6133-0035","authenticated-orcid":false,"given":"Ming","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5915-9565","authenticated-orcid":false,"given":"Wenxuan","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6385-6776","authenticated-orcid":false,"given":"Wankou","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"15_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Anne\u00a0Hendricks, L., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.: Localizing moments in video with natural language. In: ICCV, pp. 5803\u20135812 (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"15_CR4","unstructured":"Bai, S., et al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"15_CR5","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Barrios, W., Soldan, M., Ceballos-Arroyo, A.M., Heilbron, F.C., Ghanem, B.: Localizing moments in long video via multimodal guidance. In: ICCV, pp. 13667\u201313678 (2023)","DOI":"10.1109\/ICCV51070.2023.01257"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Cao, M., Yang, T., Weng, J., Zhang, C., Wang, J., Zou, Y.: Locvtp: video-text pre-training for temporal localization. In: ECCV, pp. 38\u201356. Springer (2022)","DOI":"10.1007\/978-3-031-19809-0_3"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Cao, Z., Zhang, B., Du, H., Yu, X., Li, X., Wang, S.: Flashvtg: feature layering and adaptive score handling network for video temporal grounding. In: WACV, pp. 9226\u20139236. IEEE (2025)","DOI":"10.1109\/WACV61041.2025.00894"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: ECCV, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Chen, W., Chen, L., Wu, Y.: An efficient and effective transformer decoder-based framework for multi-task visual grounding. In: ECCV, pp. 125\u2013141. Springer (2024)","DOI":"10.1007\/978-3-031-72995-9_8"},{"key":"15_CR11","unstructured":"Chen, Y.W., Tsai, Y.H., Yang, M.H.: End-to-end multi-modal video temporal grounding. In: NeurIPS, vol. 34, pp. 28442\u201328453 (2021)"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Dai, M., et al.: Gc3vg: generalized multi-task visual grounding with coarse-to-fine consistency constraints. TCSVT (2025)","DOI":"10.1609\/aaai.v39i3.32265"},{"key":"15_CR13","unstructured":"Dai, M., et al.: Improving generalized visual grounding with instance-aware joint learning. TPAMI (2025)"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Dai, M., et al.: Deris: decoupling perception and cognition for enhanced referring image segmentation through loopback synergy. In: ICCV, pp. 19936\u201319946 (2025)","DOI":"10.1109\/ICCV51701.2025.01854"},{"key":"15_CR15","first-page":"121670","volume":"37","author":"M Dai","year":"2024","unstructured":"Dai, M., Yang, L., Xu, Y., Feng, Z., Yang, W.: Simvg: a simple framework for visual grounding with decoupled multi-modal fusion. NeurIPS 37, 121670\u2013121698 (2024)","journal-title":"NeurIPS"},{"key":"15_CR16","unstructured":"Dai, M., Yang, S., Duan, B., Yang, W., Wang, J.: Momentseg: moment-centric sampling for enhanced video pixel understanding. arXiv preprint arXiv:2510.09274 (2025)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: Tall: temporal activity localization via language query. In: ICCV, pp. 5267\u20135275 (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Gu, X., Chen, G., Wang, Y., Zhang, L., Luo, T., Wen, L.: Text with knowledge graph augmented transformer for video captioning. In: CVPR, pp. 18941\u201318951 (2023)","DOI":"10.1109\/CVPR52729.2023.01816"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Gu, X., Fan, H., Huang, Y., Luo, T., Zhang, L.: Context-guided spatio-temporal video grounding. In: CVPR, pp. 18330\u201318339 (2024)","DOI":"10.1109\/CVPR52733.2024.01735"},{"key":"15_CR20","unstructured":"Gu, X., et al.: Knowing your target: target-aware transformer makes better spatio-temporal video grounding. arXiv preprint arXiv:2502.11168 (2025)"},{"key":"15_CR21","unstructured":"Gu, X., et al.: Thinking with bounding boxes: enhancing spatio-temporal video grounding via reinforcement fine-tuning. arXiv preprint arXiv:2511.21375 (2025)"},{"key":"15_CR22","unstructured":"Guo, D., et al.: Deepseek-r1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"15_CR23","unstructured":"Guo, D., et al.: Seed1. 5-vl technical report. arXiv preprint arXiv:2505.07062 (2025)"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Hao, J., Sun, H., Ren, P., Wang, J., Qi, Q., Liao, J.: Can shuffling video benefit temporal bias problem: a novel training framework for temporal grounding. In: ECCV, pp. 130\u2013147. Springer (2022)","DOI":"10.1007\/978-3-031-20059-5_8"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Jiang, H., Misra, I., Rohrbach, M., Learned-Miller, E., Chen, X.: In defense of grid features for visual question answering. In: CVPR, pp. 10267\u201310276 (2020)","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"15_CR26","first-page":"29192","volume":"35","author":"Y Jin","year":"2022","unstructured":"Jin, Y., Yuan, Z., Mu, Y., et al.: Embracing consistency: a one-stage approach for spatio-temporal video grounding. NeurIPS 35, 29192\u201329204 (2022)","journal-title":"NeurIPS"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: Mdetr-modulated detection for end-to-end multi-modal understanding. In: ICCV, pp. 1780\u20131790 (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Kang, W., Liu, G., Shah, M., Yan, Y.: Segvg: transferring object bounding box to segmentation for visual grounding. In: ECCV, pp. 57\u201375. Springer (2024)","DOI":"10.1007\/978-3-031-72920-1_4"},{"key":"15_CR29","first-page":"11846","volume":"34","author":"J Lei","year":"2021","unstructured":"Lei, J., Berg, T.L., Bansal, M.: Detecting moments and highlights in videos via natural language queries. NeurIPS 34, 11846\u201311858 (2021)","journal-title":"NeurIPS"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: Llava-st: a multimodal large language model for fine-grained spatial-temporal understanding. In: CVPR, pp. 8592\u20138603 (2025)","DOI":"10.1109\/CVPR52734.2025.00803"},{"issue":"1","key":"15_CR31","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/TMI.2023.3291719","volume":"43","author":"Z Li","year":"2023","unstructured":"Li, Z., et al.: Lvit: language meets vision transformer in medical image segmentation. IEEE Trans. Med. Imaging 43(1), 96\u2013107 (2023)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"15_CR32","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":"15_CR33","doi-asserted-by":"crossref","unstructured":"Lin, Z., Tan, C., Hu, J.F., Jin, Z., Ye, T., Zheng, W.S.: Collaborative static and dynamic vision-language streams for spatio-temporal video grounding. In: CVPR, pp. 23100\u201323109 (2023)","DOI":"10.1109\/CVPR52729.2023.02212"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: R 2-tuning: efficient image-to-video transfer learning for video temporal grounding. In: ECCV, pp. 421\u2013438. Springer (2024)","DOI":"10.1007\/978-3-031-72940-9_24"},{"key":"15_CR35","unstructured":"Moon, W., Hyun, S., Lee, S., Heo, J.P.: Correlation-guided query-dependency calibration for video temporal grounding. arXiv preprint arXiv:2311.08835 (2023)"},{"key":"15_CR36","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":"15_CR37","doi-asserted-by":"crossref","unstructured":"Mun, J., Cho, M., Han, B.: Local-global video-text interactions for temporal grounding. In: CVPR, pp. 10810\u201310819 (2020)","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Ren, Z., et al.: Pixellm: pixel reasoning with large multimodal model. In: CVPR, pp. 26374\u201326383 (2024)","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Shen, Y., Gu, X., Xu, K., Fan, H., Wen, L., Zhang, L.: Accurate and fast compressed video captioning. In: ICCV, pp. 15558\u201315567 (2023)","DOI":"10.1109\/ICCV51070.2023.01426"},{"key":"15_CR40","doi-asserted-by":"crossref","unstructured":"Su, R., Yu, Q., Xu, D.: Stvgbert: a visual-linguistic transformer based framework for spatio-temporal video grounding. In: ICCV, pp. 1533\u20131542 (2021)","DOI":"10.1109\/ICCV48922.2021.00156"},{"key":"15_CR41","unstructured":"Tan, C., Lin, Z., Hu, J.F., Li, X., Zheng, W.S.: Augmented 2D-TAN: a two-stage approach for human-centric spatio-temporal video grounding. arXiv preprint arXiv:2106.10634 (2021)"},{"issue":"12","key":"15_CR42","first-page":"8238","volume":"32","author":"Z Tang","year":"2021","unstructured":"Tang, Z., et al.: Human-centric spatio-temporal video grounding with visual transformers. TCSVT 32(12), 8238\u20138249 (2021)","journal-title":"TCSVT"},{"key":"15_CR43","first-page":"10078","volume":"35","author":"Z Tong","year":"2022","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training. NeurIPS 35, 10078\u201310093 (2022)","journal-title":"NeurIPS"},{"key":"15_CR44","unstructured":"Vaswani, A., et al.: Attention is all you need. NeurIPS 30 (2017)"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Spacevllm: endowing multimodal large language model with spatio-temporal video grounding capability. arXiv preprint arXiv:2503.13983 (2025)","DOI":"10.1609\/aaai.v40i12.37956"},{"key":"15_CR46","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Protege: untrimmed pretraining for video temporal grounding by video temporal grounding. In: CVPR, pp. 6575\u20136585 (2023)","DOI":"10.1109\/CVPR52729.2023.00636"},{"key":"15_CR47","doi-asserted-by":"crossref","unstructured":"Wang, W., Liu, J., Su, Y., Nie, W.: Efficient spatio-temporal video grounding with semantic-guided feature decomposition. In: ACMMM, pp. 4867\u20134876 (2023)","DOI":"10.1145\/3581783.3612441"},{"key":"15_CR48","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Image as a foreign language: beit pretraining for vision and vision-language tasks. In: CVPR, pp. 19175\u201319186 (2023)","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"15_CR49","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, L., Wu, T., Li, T., Wu, G.: Negative sample matters: a renaissance of metric learning for temporal grounding. In: AAAI, vol.\u00a036, pp. 2613\u20132623 (2022)","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"15_CR50","doi-asserted-by":"crossref","unstructured":"Wasim, S.T., Naseer, M., Khan, S., Yang, M.H., Khan, F.S.: Videogrounding-dino: towards open-vocabulary spatio-temporal video grounding. In: CVPR, pp. 18909\u201318918 (2024)","DOI":"10.1109\/CVPR52733.2024.01789"},{"key":"15_CR51","doi-asserted-by":"crossref","unstructured":"Weng, Y., Han, M., He, H., Chang, X., Zhuang, B.: Longvlm: efficient long video understanding via large language models. In: ECCV, pp. 453\u2013470. Springer (2024)","DOI":"10.1007\/978-3-031-73414-4_26"},{"key":"15_CR52","doi-asserted-by":"crossref","unstructured":"Xu, H., He, K., Plummer, B.A., Sigal, L., Sclaroff, S., Saenko, K.: Multilevel language and vision integration for text-to-clip retrieval. In: AAAI, vol. 33, pp. 9062\u20139069 (2019)","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"15_CR53","doi-asserted-by":"crossref","unstructured":"Yang, A., Miech, A., Sivic, J., Laptev, I., Schmid, C.: Tubedetr: spatio-temporal video grounding with transformers. In: CVPR, pp. 16442\u201316453 (2022)","DOI":"10.1109\/CVPR52688.2022.01595"},{"key":"15_CR54","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: CVPR, pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"15_CR55","unstructured":"Yu, Y., Wang, X., Hu, W., Luo, X., Li, C.: 2rd place solutions in the HC-STVG track of person in context challenge 2021. arXiv preprint arXiv:2106.071663(7) (2021)"},{"key":"15_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, S., Peng, H., Fu, J., Luo, J.: Learning 2D temporal adjacent networks for moment localization with natural language. In: AAAI, vol. 34, pp. 12870\u201312877 (2020)","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"15_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chen, X., Jia, J., Liu, S., Ding, K.: Text-visual prompting for efficient 2D temporal video grounding. In: CVPR, pp. 14794\u201314804 (2023)","DOI":"10.1109\/CVPR52729.2023.01421"},{"key":"15_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhao, Z., Lin, Z., Huai, B., Yuan, N.J.: Object-aware multi-branch relation networks for spatio-temporal video grounding. arXiv preprint arXiv:2008.06941 (2020)","DOI":"10.24963\/ijcai.2020\/149"},{"key":"15_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhao, Z., Zhao, Y., Wang, Q., Liu, H., Gao, L.: Where does it exist: spatio-temporal video grounding for multi-form sentences. In: CVPR, pp. 10668\u201310677 (2020)","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"15_CR60","doi-asserted-by":"crossref","unstructured":"Zhao, H., Ong, Y.S., Zhou, J.T.: Agentic spatio-temporal grounding via collaborative reasoning. arXiv preprint arXiv:2602.13313 (2026)","DOI":"10.1145\/3805712.3809528"},{"key":"15_CR61","doi-asserted-by":"crossref","unstructured":"Zhu, C., et al.: Seqtr: a simple yet universal network for visual grounding. In: ECCV, pp. 598\u2013615. Springer (2022)","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"15_CR62","unstructured":"Zhu, J., et al.: Internvl3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"},{"key":"15_CR63","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"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\/978-3-032-37356-4_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:26:50Z","timestamp":1788985610000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37356-4_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373557","9783032373564"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37356-4_15","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":"10 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"}}]}}