{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:09:33Z","timestamp":1766138973652,"version":"3.40.3"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729393"},{"type":"electronic","value":"9783031729409"}],"license":[{"start":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T00:00:00Z","timestamp":1731801600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T00:00:00Z","timestamp":1731801600000},"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\/978-3-031-72940-9_16","type":"book-chapter","created":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T20:40:39Z","timestamp":1731789639000},"page":"275-292","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["TrajPrompt: Aligning Color Trajectory with Vision-Language Representations"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0935-3842","authenticated-orcid":false,"given":"Li-Wu","family":"Tsao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5696-6726","authenticated-orcid":false,"given":"Hao-Tang","family":"Tsui","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9983-8311","authenticated-orcid":false,"given":"Yu-Rou","family":"Tuan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4082-9301","authenticated-orcid":false,"given":"Pei-Chi","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0048-3245","authenticated-orcid":false,"given":"Kuan-Lin","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4071-3980","authenticated-orcid":false,"given":"Jhih-Ciang","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2216-077X","authenticated-orcid":false,"given":"Hong-Han","family":"Shuai","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4662-7875","authenticated-orcid":false,"given":"Wen-Huang","family":"Cheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,17]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L., Savarese, S.: Social LSTM: human trajectory prediction in crowded spaces. In: CVPR, pp. 961\u2013971 (2016)","DOI":"10.1109\/CVPR.2016.110"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Amirian, J., Hayet, J.B., Pettr\u00e9, J.: Social ways: learning multi-modal distributions of pedestrian trajectories with GANs. In: CVPRW (2019)","DOI":"10.1109\/CVPRW.2019.00359"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Aydemir, G., Akan, A.K., G\u00fcney, F.: ADAPT: efficient multi-agent trajectory prediction with adaptation. In: ICCV, pp. 8295\u20138305 (2023)","DOI":"10.1109\/ICCV51070.2023.00762"},{"key":"16_CR4","unstructured":"Bao, H., et al.: VLMo: unified vision-language pre-training with mixture-of-modality-experts. In: NeurIPS, vol.\u00a035, pp. 32897\u201332912 (2022)"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: CVPR, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"16_CR6","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-031-20065-6_3","volume-title":"ECCV 2022","author":"Y Cao","year":"2022","unstructured":"Cao, Y., Xiao, C., Anandkumar, A., Xu, D., Pavone, M.: AdvDO: realistic adversarial attacks for trajectory prediction. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13665, pp. 36\u201352. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_3"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Chang, M.F., et\u00a0al.: Argoverse: 3D tracking and forecasting with rich maps. In: CVPR, pp. 8748\u20138757 (2019)","DOI":"10.1109\/CVPR.2019.00895"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Traj-MAE: masked autoencoders for trajectory prediction. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00767"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Dharmadhikari, M., et al.: Motion primitives-based path planning for fast and agile exploration using aerial robots. In: ICRA, pp. 179\u2013185 (2020)","DOI":"10.1109\/ICRA40945.2020.9196964"},{"key":"16_CR10","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2020)"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Giuliari, F., Hasan, I., Cristani, M., Galasso, F.: Transformer networks for trajectory forecasting. In: ICPR, pp. 10335\u201310342 (2021)","DOI":"10.1109\/ICPR48806.2021.9412190"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Gu, J., et al.: ViP3D: end-to-end visual trajectory prediction via 3D agent queries. In: CVPR, pp. 5496\u20135506 (2023)","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Gu, J., Sun, C., Zhao, H.: DenseTNT: end-to-end trajectory prediction from dense goal sets. In: ICCV, pp. 15303\u201315312 (2021)","DOI":"10.1109\/ICCV48922.2021.01502"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Guo, K., Liu, W., Pan, J.: End-to-end trajectory distribution prediction based on occupancy grid maps. In: CVPR, pp. 2242\u20132251 (2022)","DOI":"10.1109\/CVPR52688.2022.00228"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Gupta, A., Johnson, J., Fei-Fei, L., Savarese, S., Alahi, A.: Social GAN: socially acceptable trajectories with generative adversarial networks. In: CVPR, pp. 2255\u20132264 (2018)","DOI":"10.1109\/CVPR.2018.00240"},{"key":"16_CR16","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/978-3-031-19827-4_41","volume-title":"ECCV 2022","author":"M Jia","year":"2022","unstructured":"Jia, M., et al.: Visual prompt tuning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13693, pp. 709\u2013727. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19827-4_41"},{"key":"16_CR17","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"16_CR18","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: ICML (2023)"},{"key":"16_CR19","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML, pp. 12888\u201312900 (2022)"},{"key":"16_CR20","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. In: NeurIPS, vol.\u00a034, pp. 9694\u20139705 (2021)"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: What does BERT with vision look at? In: ACL, pp. 5265\u20135275 (2020)","DOI":"10.18653\/v1\/2020.acl-main.469"},{"key":"16_CR22","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. In: ACL, pp. 4582\u20134597 (2021)"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, J., Fang, L., Jiang, Q., Zhou, B.: Multimodal motion prediction with stacked transformers. In: CVPR, pp. 7577\u20137586 (2021)","DOI":"10.1109\/CVPR46437.2021.00749"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Maeda, T., Ukita, N.: Fast inference and update of probabilistic density estimation on trajectory prediction. In: ICCV, pp. 9795\u20139805 (2023)","DOI":"10.1109\/ICCV51070.2023.00898"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Mangalam, K., An, Y., Girase, H., Malik, J.: From goals, waypoints & paths to long term human trajectory forecasting. In: ICCV, pp. 15233\u201315242 (2021)","DOI":"10.1109\/ICCV48922.2021.01495"},{"key":"16_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1007\/978-3-030-58536-5_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Mangalam","year":"2020","unstructured":"Mangalam, K., et al.: It is not the journey but the destination: endpoint conditioned trajectory prediction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 759\u2013776. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_45"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Mao, W., Xu, C., Zhu, Q., Chen, S., Wang, Y.: Leapfrog diffusion model for stochastic trajectory prediction. In: CVPR, pp. 5517\u20135526 (2023)","DOI":"10.1109\/CVPR52729.2023.00534"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Pellegrini, S., Ess, A., Schindler, K., Van\u00a0Gool, L.: You\u2019ll never walk alone: modeling social behavior for multi-target tracking. In: ICCV, pp. 261\u2013268 (2009)","DOI":"10.1109\/ICCV.2009.5459260"},{"key":"16_CR30","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"16_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-319-46484-8_33","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Robicquet","year":"2016","unstructured":"Robicquet, A., Sadeghian, A., Alahi, A., Savarese, S.: Learning social etiquette: human trajectory understanding in crowded scenes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 549\u2013565. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_33"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Sadeghian, A., Kosaraju, V., Sadeghian, A., Hirose, N., Rezatofighi, H., Savarese, S.: Sophie: an attentive GAN for predicting paths compliant to social and physical constraints. In: CVPR, pp. 1349\u20131358 (2019)","DOI":"10.1109\/CVPR.2019.00144"},{"key":"16_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1007\/978-3-030-58523-5_40","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Salzmann","year":"2020","unstructured":"Salzmann, T., Ivanovic, B., Chakravarty, P., Pavone, M.: Trajectron++: dynamically-feasible trajectory forecasting with heterogeneous data. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 683\u2013700. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_40"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Shafiee, N., Padir, T., Elhamifar, E.: Introvert: Human trajectory prediction via conditional 3d attention. In: CVPR, pp. 16815\u201316825 (2021)","DOI":"10.1109\/CVPR46437.2021.01654"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Shi, L., Wang, L., Zhou, S., Hua, G.: Trajectory unified transformer for pedestrian trajectory prediction. In: ICCV, pp. 9675\u20139684 (2023)","DOI":"10.1109\/ICCV51070.2023.00887"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Shtedritski, A., Rupprecht, C., Vedaldi, A.: What does clip knows about a red circle? Visual prompt engineering for VLMs. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Sun, J., Li, Y., Chai, L., Fang, H.S., Li, Y.L., Lu, C.: Human trajectory prediction with momentary observation. In: CVPR, pp. 6467\u20136476 (2022)","DOI":"10.1109\/CVPR52688.2022.00636"},{"key":"16_CR38","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-031-20047-2_14","volume-title":"ECCV 2022","author":"LW Tsao","year":"2022","unstructured":"Tsao, L.W., Wang, Y.K., Lin, H.S., Shuai, H.H., Wong, L.K., Cheng, W.H.: Social-SSL: self-supervised cross-sequence representation learning based on transformers for multi-agent trajectory prediction. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 234\u2013250. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_14"},{"key":"16_CR39","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD birds-200-2011 dataset. Technical report. CNS-TR-2011-001, California Institute of Technology (2011)"},{"issue":"1\u20132","key":"16_CR40","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/s10032-020-00360-2","volume":"24","author":"Z Wang","year":"2021","unstructured":"Wang, Z., Liu, J.C.: Translating math formula images to latex sequences using deep neural networks with sequence-level training. Int. J. Doc. Anal. Recogn. 24(1\u20132), 63\u201375 (2021)","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Wen, L., et\u00a0al.: Detection, tracking, and counting meets drones in crowds: a benchmark. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00772"},{"key":"16_CR42","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1007\/978-3-031-20047-2_39","volume-title":"ECCV 2022","author":"C Wong","year":"2022","unstructured":"Wong, C., et al.: View vertically: a hierarchical network for trajectory prediction via Fourier spectrums. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 682\u2013700. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_39"},{"key":"16_CR43","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-031-19842-7_3","volume-title":"ECCV 2022","author":"C Xu","year":"2022","unstructured":"Xu, C., et al.: PreTraM: self-supervised pre-training via connecting trajectory and map. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13699, pp. 34\u201350. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19842-7_3"},{"key":"16_CR44","unstructured":"Yao, Y., Zhang, A., Zhang, Z., Liu, Z., Chua, T.S., Sun, M.: CPT: colorful prompt tuning for pre-trained vision-language models. arXiv preprint arXiv:2109.11797 (2021)"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Weng, X., Ou, Y., Kitani, K.M.: AgentFormer: agent-aware transformers for socio-temporal multi-agent forecasting. In: ICCV, pp. 9813\u20139823 (2021)","DOI":"10.1109\/ICCV48922.2021.00967"},{"key":"16_CR46","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1007\/978-3-031-19830-4_22","volume-title":"ECCV 2022","author":"J Yue","year":"2022","unstructured":"Yue, J., Manocha, D., Wang, H.: Human trajectory prediction via neural social physics. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13694, pp. 376\u2013394. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19830-4_22"},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: CVPR, pp. 16816\u201316825 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"16_CR48","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. IJCV 130(9), 2337\u20132348 (2022)","journal-title":"IJCV"}],"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\/978-3-031-72940-9_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T21:33:44Z","timestamp":1731792824000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72940-9_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,17]]},"ISBN":["9783031729393","9783031729409"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72940-9_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,17]]},"assertion":[{"value":"17 November 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"}}]}}