{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:27:59Z","timestamp":1777656479477,"version":"3.51.4"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733826","type":"print"},{"value":"9783031733833","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-3-031-73383-3_1","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T12:04:17Z","timestamp":1730549057000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking"],"prefix":"10.1007","author":[{"given":"Siyuan","family":"Li","sequence":"first","affiliation":[]},{"given":"Lei","family":"Ke","sequence":"additional","affiliation":[]},{"given":"Yung-Hsu","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Luigi","family":"Piccinelli","sequence":"additional","affiliation":[]},{"given":"Mattia","family":"Seg\u00f9","sequence":"additional","affiliation":[]},{"given":"Martin","family":"Danelljan","sequence":"additional","affiliation":[]},{"given":"Luc Van","family":"Gool","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Meinhardt, T., Leal-Taixe, L.: Tracking without bells and whistles. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00103"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., Upcroft, B.: Simple online and realtime tracking. In: ICIP (2016)","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Bras\u00f3, G., Leal-Taix\u00e9, L.: Learning a neural solver for multiple object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6247\u20136257 (2020)","DOI":"10.1109\/CVPR42600.2020.00628"},{"key":"1_CR4","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":"1_CR5","doi-asserted-by":"crossref","unstructured":"Cao, J., Pang, J., Weng, X., Khirodkar, R., Kitani, K.: Observation-centric sort: rethinking sort for robust multi-object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9686\u20139696 (2023)","DOI":"10.1109\/CVPR52729.2023.00934"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Cetintas, O., Bras\u00f3, G., Leal-Taix\u00e9, L.: Unifying short and long-term tracking with graph hierarchies. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22877\u201322887, June 2023","DOI":"10.1109\/CVPR52729.2023.02191"},{"key":"1_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1007\/978-3-030-58558-7_26","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Dave","year":"2020","unstructured":"Dave, A., Khurana, T., Tokmakov, P., Schmid, C., Ramanan, D.: TAO: a large-scale benchmark for tracking any object. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 436\u2013454. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_26"},{"key":"1_CR8","unstructured":"Dendorfer, P., et al.: Mot20: a benchmark for multi object tracking in crowded scenes. arXiv preprint arXiv:2003.09003 (2020)"},{"key":"1_CR9","unstructured":"Du, F., Xu, B., Tang, J., Zhang, Y., Wang, F., Li, H.: 1st place solution to ECCV-TAO-2020: detect and represent any object for tracking. arXiv preprint arXiv:2101.08040 (2021)"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Du, Y., Wei, F., Zhang, Z., Shi, M., Gao, Y., Li, G.: Learning to prompt for open-vocabulary object detection with vision-language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14084\u201314093 (2022)","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"1_CR11","doi-asserted-by":"publisher","first-page":"8725","DOI":"10.1109\/TMM.2023.3240881","volume":"25","author":"Y Du","year":"2023","unstructured":"Du, Y., et al.: StrongSORT: make deepSORT great again. IEEE Trans. Multimedia 25, 8725\u20138737 (2023)","journal-title":"IEEE Trans. Multimedia"},{"issue":"11","key":"1_CR12","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the kitti dataset. Int. J. Robot. Res. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"1_CR13","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588\u20133597 (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"1_CR17","unstructured":"Kim, V., Jung, G., Lee, S.W.: AM-SORT: adaptable motion predictor with historical trajectory embedding for multi-object tracking. arXiv preprint arXiv:2401.13950 (2024)"},{"key":"1_CR18","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-031-20047-2_29","volume-title":"ECCV 2022","author":"S Li","year":"2022","unstructured":"Li, S., Danelljan, M., Ding, H., Huang, T.E., Yu, F.: Tracking every thing in the wild. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 498\u2013515. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_29"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Li, S., Fischer, T., Ke, L., Ding, H., Danelljan, M., Yu, F.: OVTrack: open-vocabulary multiple object tracking. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00539"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Li, S., et al.: Matching anything by segmenting anything. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18963\u201318973 (2024)","DOI":"10.1109\/CVPR52733.2024.01794"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Opening up open world tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19045\u201319055 (2022)","DOI":"10.1109\/CVPR52688.2022.01846"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1_CR24","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/978-3-031-54605-1_29","volume-title":"DAGM GCPR 2023","author":"Z Liu","year":"2023","unstructured":"Liu, Z., Segu, M., Yu, F.: COOLer: class-incremental learning for appearance-based multiple object tracking. In: K\u00f6the, U., Rother, C. (eds.) DAGM GCPR 2023. LNCS, vol. 14264, pp. 443\u2013458. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-54605-1_29"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: TrackFormer: multi-object tracking with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8844\u20138854 (2022)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"1_CR26","unstructured":"Milan, A., Leal-Taix\u00e9, L., Reid, I., Roth, S., Schindler, K.: MOT16: a benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831 (2016)"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Pang, J., et al.: Quasi-dense similarity learning for multiple object tracking. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"1_CR28","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":"1_CR29","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4938\u20134947 (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Segu, M., Piccinelli, L., Li, S., Van\u00a0Gool, L., Yu, F., Schiele, B.: Walker: self-supervised multiple object tracking by walking on temporal appearance graphs. In: Computer Vision\u2013ECCV 2024: 18th European Conference, Milan, Italy, September 29\u2013October 4, 2024, Proceedings. Springer (2024)","DOI":"10.1007\/978-3-031-73242-3_1"},{"key":"1_CR32","unstructured":"Segu, M., Piccinelli, L., Li, S., Yang, Y.H., Schiele, B., Van\u00a0Gool, L.: Samba: synchronized set-of-sequences modeling for end-to-end multiple object tracking. arXiv preprint (2024)"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Segu, M., Schiele, B., Yu, F.: Darth: holistic test-time adaptation for multiple object tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9717\u20139727 (2023)","DOI":"10.1109\/ICCV51070.2023.00891"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Sun, P., et\u00a0al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"1_CR35","unstructured":"Sun, P., et al.: TransTrack: multiple object tracking with transformer. arXiv preprint arXiv:2012.15460 (2020)"},{"key":"1_CR36","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/978-3-030-58621-8_7","volume-title":"ECCV 2020","author":"Z Wang","year":"2020","unstructured":"Wang, Z., Zheng, L., Liu, Y., Wang, S.: Towards real-time multi-object tracking. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 107\u2013122. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_7"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. In: ICIP (2017)","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Wu, J., Jiang, Y., Liu, Q., Yuan, Z., Bai, X., Bai, S.: General object foundation model for images and videos at scale. arXiv preprint arXiv:2312.09158 (2023)","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"1_CR39","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1007\/978-3-031-19815-1_34","volume-title":"ECCV 2022","author":"J Wu","year":"2022","unstructured":"Wu, J., Liu, Q., Jiang, Y., Bai, S., Yuille, A., Bai, X.: In defense of online models for video instance segmentation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 588\u2013605. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_34"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Yan, B., et al.: Universal instance perception as object discovery and retrieval. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Ye, M., et al.: Cascade-DETR: delving into high-quality universal object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6704\u20136714 (2023)","DOI":"10.1109\/ICCV51070.2023.00617"},{"key":"1_CR42","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1007\/978-3-031-19812-0_38","volume-title":"ECCV 2022","author":"F Zeng","year":"2022","unstructured":"Zeng, F., Dong, B., Zhang, Y., Wang, T., Zhang, X., Wei, Y.: MOTR: end-to-end multiple-object tracking with transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13687, pp. 659\u2013675. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_38"},{"key":"1_CR43","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-20047-2_1","volume-title":"ECCV 2022","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., et al.: ByteTrack: multi-object tracking by associating every detection box. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 1\u201321. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_1"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, C., Wang, X., Zeng, W., Liu, W.: FairMOT: On the fairness of detection and re-identification in multiple object tracking. IJCV (2021)","DOI":"10.1007\/s11263-021-01513-4"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Zheng, G., Lin, S., Zuo, H., Fu, C., Pan, J.: NetTrack: tracking highly dynamic objects with a net. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19145\u201319155 (2024)","DOI":"10.1109\/CVPR52733.2024.01811"},{"key":"1_CR46","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1007\/978-3-031-20077-9_21","volume-title":"ECCV 2022","author":"X Zhou","year":"2022","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 350\u2013368. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_21"}],"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\/978-3-031-73383-3_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T18:05:52Z","timestamp":1732989952000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73383-3_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031733826","9783031733833"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73383-3_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 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"}}]}}