{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:51:57Z","timestamp":1780764717628,"version":"3.54.1"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726576","type":"print"},{"value":"9783031726583","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"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\/978-3-031-72658-3_21","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T03:32:37Z","timestamp":1727839957000},"page":"361-379","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["VisionTrap: Vision-Augmented Trajectory Prediction Guided by\u00a0Textual Descriptions"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0506-5958","authenticated-orcid":false,"given":"Seokha","family":"Moon","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5217-6379","authenticated-orcid":false,"given":"Hyun","family":"Woo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2633-288X","authenticated-orcid":false,"given":"Hongbeen","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8347-7432","authenticated-orcid":false,"given":"Haeji","family":"Jung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4457-8395","authenticated-orcid":false,"given":"Reza","family":"Mahjourian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5454-3404","authenticated-orcid":false,"given":"Hyung-gun","family":"Chi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3369-8169","authenticated-orcid":false,"given":"Hyerin","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7349-0018","authenticated-orcid":false,"given":"Sangpil","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6520-2074","authenticated-orcid":false,"given":"Jinkyu","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,2]]},"reference":[{"key":"21_CR1","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR2","unstructured":"Buhet, T., Wirbel, E., Bursuc, A., Perrotton, X.: Plop: probabilistic polynomial objects trajectory planning for autonomous driving. arXiv preprint arXiv:2003.08744 (2020)"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuscenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"21_CR4","unstructured":"Casas, S., Luo, W., Urtasun, R.: Intentnet: learning to predict intention from raw sensor data. In: Conference on Robot Learning, pp. 947\u2013956. PMLR (2018)"},{"key":"21_CR5","unstructured":"Chai, Y., Sapp, B., Bansal, M., Anguelov, D.: Multipath: multiple probabilistic anchor trajectory hypotheses for behavior prediction. arXiv preprint arXiv:1910.05449 (2019)"},{"key":"21_CR6","first-page":"8765","volume":"33","author":"CY Chuang","year":"2020","unstructured":"Chuang, C.Y., Robinson, J., Lin, Y.C., Torralba, A., Jegelka, S.: Debiased contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 8765\u20138775 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR7","unstructured":"Deo, N., Trivedi, M.M.: Trajectory forecasts in unknown environments conditioned on grid-based plans. arXiv preprint arXiv:2001.00735 (2020)"},{"key":"21_CR8","unstructured":"Deo, N., Wolff, E., Beijbom, O.: Multimodal trajectory prediction conditioned on lane-graph traversals. In: Conference on Robot Learning, pp. 203\u2013212. PMLR (2022)"},{"key":"21_CR9","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":"21_CR10","doi-asserted-by":"crossref","unstructured":"Fang, L., Jiang, Q., Shi, J., Zhou, B.: Tpnet: trajectory proposal network for motion prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6797\u20136806 (2020)","DOI":"10.1109\/CVPR42600.2020.00683"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Gao, J., et al.: Vectornet: encoding hd maps and agent dynamics from vectorized representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11525\u201311533 (2020)","DOI":"10.1109\/CVPR42600.2020.01154"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Gilles, T., Sabatini, S., Tsishkou, D., Stanciulescu, B., Moutarde, F.: Home: heatmap output for future motion estimation. In: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pp. 500\u2013507. IEEE (2021)","DOI":"10.1109\/ITSC48978.2021.9564944"},{"key":"21_CR13","unstructured":"Gilles, T., Sabatini, S., Tsishkou, D., Stanciulescu, B., Moutarde, F.: Thomas: trajectory heatmap output with learned multi-agent sampling. arXiv preprint arXiv:2110.06607 (2021)"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Gilles, T., Sabatini, S., Tsishkou, D., Stanciulescu, B., Moutarde, F.: Gohome: graph-oriented heatmap output for future motion estimation. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 9107\u20139114. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812253"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Girase, H., et al.: Loki: long term and key intentions for trajectory prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9803\u20139812 (2021)","DOI":"10.1109\/ICCV48922.2021.00966"},{"key":"21_CR16","first-page":"14345","volume":"35","author":"I Hwang","year":"2022","unstructured":"Hwang, I., et al.: Selecmix: debiased learning by contradicting-pair sampling. Adv. Neural. Inf. Process. Syst. 35, 14345\u201314357 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Jang, T., Wang, X.: Difficulty-based sampling for debiased contrastive representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 24039\u201324048 (2023)","DOI":"10.1109\/CVPR52729.2023.02302"},{"key":"21_CR18","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"21_CR19","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Bevdepth: acquisition of reliable depth for multi-view 3d object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1477\u20131485 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"21_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1007\/978-3-030-58536-5_32","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Liang","year":"2020","unstructured":"Liang, M., et al.: Learning lane graph representations for motion forecasting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 541\u2013556. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_32"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"issue":"2","key":"21_CR23","doi-asserted-by":"publisher","first-page":"3485","DOI":"10.1109\/LRA.2020.2976305","volume":"5","author":"B Liu","year":"2020","unstructured":"Liu, B., et al.: Spatiotemporal relationship reasoning for pedestrian intent prediction. IEEE Rob. Autom. Lett. 5(2), 3485\u20133492 (2020)","journal-title":"IEEE Rob. Autom. Lett."},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Liu, M., et al.: Laformer: trajectory prediction for autonomous driving with lane-aware scene constraints. arXiv preprint arXiv:2302.13933 (2023)","DOI":"10.1109\/CVPRW63382.2024.00209"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, J., Fang, L., Jiang, Q., Zhou, B.: Multimodal motion prediction with stacked transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7577\u20137586 (2021)","DOI":"10.1109\/CVPR46437.2021.00749"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Malla, S., Choi, C., Dwivedi, I., Choi, J.H., Li, J.: Drama: Joint risk localization and captioning in driving. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1043\u20131052 (2023)","DOI":"10.1109\/WACV56688.2023.00110"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Malla, S., Dariush, B., Choi, C.: Titan: future forecast using action priors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11186\u201311196 (2020)","DOI":"10.1109\/CVPR42600.2020.01120"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"McInnes, L., Healy, J., Melville, J.: Umap: uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426 (2018)","DOI":"10.21105\/joss.00861"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Messaoud, K., Deo, N., Trivedi, M.M., Nashashibi, F.: Trajectory prediction for autonomous driving based on multi-head attention with joint agent-map representation (2020)","DOI":"10.1109\/IV48863.2021.9576054"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Miao, P., Du, Z., Zhang, J.: Debcse: rethinking unsupervised contrastive sentence embedding learning in the debiasing perspective. In: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, pp. 1847\u20131856 (2023)","DOI":"10.1145\/3583780.3614833"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Nayakanti, N., Al-Rfou, R., Zhou, A., Goel, K., Refaat, K.S., Sapp, B.: Wayformer: motion forecasting via simple & efficient attention networks. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 2980\u20132987. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160609"},{"key":"21_CR32","unstructured":"Ngiam, J., et\u00a0al.: Scene transformer: a unified architecture for predicting multiple agent trajectories. arXiv preprint arXiv:2106.08417 (2021)"},{"key":"21_CR33","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Phan-Minh, T., Grigore, E.C., Boulton, F.A., Beijbom, O., Wolff, E.M.: Covernet: multimodal behavior prediction using trajectory sets. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14074\u201314083 (2020)","DOI":"10.1109\/CVPR42600.2020.01408"},{"key":"21_CR35","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Rasouli, A., Kotseruba, I., Kunic, T., Tsotsos, J.K.: Pie: a large-scale dataset and models for pedestrian intention estimation and trajectory prediction. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00636"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Rasouli, A., Rohani, M., Luo, J.: Bifold and semantic reasoning for pedestrian behavior prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15600\u201315610 (October 2021)","DOI":"10.1109\/ICCV48922.2021.01531"},{"key":"21_CR38","unstructured":"Rasouli, A., Yau, T., Lakner, P., Malekmohammadi, S., Rohani, M., Luo, J.: Pepscenes: a novel dataset and baseline for pedestrian action prediction in 3d. arXiv preprint arXiv:2012.07773 (2020)"},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Rasouli, A., Yau, T., Rohani, M., Luo, J.: Multi-modal hybrid architecture for pedestrian action prediction. In: 2022 IEEE Intelligent Vehicles Symposium (IV), pp. 91\u201397. IEEE (2022)","DOI":"10.1109\/IV51971.2022.9827055"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Rowe, L., Ethier, M., Dykhne, E.H., Czarnecki, K.: Fjmp: factorized joint multi-agent motion prediction over learned directed acyclic interaction graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13745\u201313755 (2023)","DOI":"10.1109\/CVPR52729.2023.01321"},{"key":"21_CR41","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":"21_CR42","doi-asserted-by":"crossref","unstructured":"Su, D.A., Douillard, B., Al-Rfou, R., Park, C., Sapp, B.: Narrowing the coordinate-frame gap in behavior prediction models: Distillation for efficient and accurate scene-centric motion forecasting. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 653\u2013659. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812368"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Varadarajan, B., et\u00a0al.: Multipath++: efficient information fusion and trajectory aggregation for behavior prediction. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 7814\u20137821. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812107"},{"key":"21_CR44","unstructured":"Wu, D., Wu, Y.: Air$$^2$$ for interaction prediction. arXiv preprint arXiv:2111.08184 (2021)"},{"key":"21_CR45","doi-asserted-by":"crossref","unstructured":"Yuan, X., et al.: Multimodal contrastive training for visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6995\u20137004 (2021)","DOI":"10.1109\/CVPR46437.2021.00692"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Weng, X., Ou, Y., Kitani, K.: Agentformer: agent-aware transformers for socio-temporal multi-agent forecasting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00967"},{"key":"21_CR47","doi-asserted-by":"crossref","unstructured":"Zeng, W., Liang, M., Liao, R., Urtasun, R.: Lanercnn: distributed representations for graph-centric motion forecasting. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 532\u2013539. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9636035"},{"key":"21_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, K., Zhang, B., Zhao, X., Wen, J.R.: Debiased contrastive learning of unsupervised sentence representations (2022)","DOI":"10.18653\/v1\/2022.acl-long.423"},{"key":"21_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Wang, J., Li, Y.H., Huang, Y.K.: Query-centric trajectory prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17863\u201317873 (2023)","DOI":"10.1109\/CVPR52729.2023.01713"},{"key":"21_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Ye, L., Wang, J., Wu, K., Lu, K.: Hivt: hierarchical vector transformer for multi-agent motion prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8823\u20138833 (2022)","DOI":"10.1109\/CVPR52688.2022.00862"},{"key":"21_CR51","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 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72658-3_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T03:41:26Z","timestamp":1727840486000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72658-3_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,2]]},"ISBN":["9783031726576","9783031726583"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72658-3_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,2]]},"assertion":[{"value":"2 October 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"}}]}}