{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:06:26Z","timestamp":1773705986009,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031784439","type":"print"},{"value":"9783031784446","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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\/978-3-031-78444-6_2","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T10:38:56Z","timestamp":1733222336000},"page":"18-33","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["OVOSE: Open-Vocabulary Semantic Segmentation in Event-Based Cameras"],"prefix":"10.1007","author":[{"given":"Muhammad Rameez Ur","family":"Rahman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jhony H.","family":"Giraldo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Indro","family":"Spinelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"St\u00e9phane","family":"Lathuili\u00e8re","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"Galasso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Alonso, I., Murillo, A.C.: EV-SegNet: semantic segmentation for event-based cameras. In: IEEE\/CVF CVPRW (2019)","DOI":"10.1109\/CVPRW.2019.00205"},{"key":"2_CR2","unstructured":"Binas, J., Neil, D., Liu, S.C., Delbr\u00fcck, T.: Ddd17: End-to-End Davis Driving Dataset (2017). ArXiv : arxiv.org\/abs\/1711.01458"},{"key":"2_CR3","unstructured":"Bucher, M., Vu, T.H., Cord, M., P\u00e9rez, P.: Zero-shot semantic segmentation. Adv. Neural Inf. Process. Syst. 32, (2019)"},{"issue":"4","key":"2_CR4","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/MSP.2020.2985815","volume":"37","author":"G Chen","year":"2020","unstructured":"Chen, G., Cao, H., Conradt, J., Tang, H., Rohrbein, F., Knoll, A.: Event-based neuromorphic vision for autonomous driving: a paradigm shift for bio-inspired visual sensing and perception. IEEE Signal Process. Mag. 37(4), 34\u201349 (2020)","journal-title":"IEEE Signal Process. Mag."},{"issue":"4","key":"2_CR5","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Computer Vision ECCV 2018, p. 833\u2013851. Springer-Verlag, Berlin, Heidelberg (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF CVPR, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Cho, H., Kim, H., Chae, Y., Yoon, K.J.: Label-free event-based object recognition via joint learning with image reconstruction from events. In: Proceedings of the IEEE\/CVF ICCV, pp. 19866\u201319877 (2023)","DOI":"10.1109\/ICCV51070.2023.01819"},{"key":"2_CR9","unstructured":"Dosovitskiy, A., et\u00a0al.: An Image is Worth $$16\\times 16$$ Words: Transformers for Image Recognition at Scale (2020). arXiv preprint: arXiv:2010.11929"},{"issue":"1","key":"2_CR10","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/TPAMI.2020.3008413","volume":"44","author":"G Gallego","year":"2020","unstructured":"Gallego, G., Delbr\u00fcck, T., Orchard, G., Bartolozzi, C., Taba, B., Censi, A., Leutenegger, S., Davison, A.J., Conradt, J., Daniilidis, K., et al.: Event-based vision: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 44(1), 154\u2013180 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Gehrig, D., Gehrig, M., Hidalgo-Carri\u00f3, J., Scaramuzza, D.: Video to events: recycling video datasets for event cameras. In: Proceedings of the IEEE\/CVF CVPR, pp. 3586\u20133595 (2020)","DOI":"10.1109\/CVPR42600.2020.00364"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Gehrig, D., Loquercio, A., Derpanis, K.G., Scaramuzza, D.: End-to-end learning of representations for asynchronous event-based data. In: Proceedings of the IEEE\/CVF ICCV, pp. 5633\u20135643 (2019)","DOI":"10.1109\/ICCV.2019.00573"},{"key":"2_CR13","doi-asserted-by":"publisher","first-page":"4947","DOI":"10.1109\/LRA.2021.3068942","volume":"6","author":"M Gehrig","year":"2021","unstructured":"Gehrig, M., Aarents, W., Gehrig, D., Scaramuzza, D.: Dsec: a stereo event camera dataset for driving scenarios. IEEE Robot. Autom. Lett. 6, 4947\u20134954 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2_CR14","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the Knowledge in a Neural Network (2015). arXiv preprint: arXiv:1503.02531"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Jian, D., Rostami, M.: Unsupervised domain adaptation for training event-based networks using contrastive learning and uncorrelated conditioning. In: Proceedings of the IEEE\/CVF ICCV, pp. 18721\u201318731 (2023)","DOI":"10.1109\/ICCV51070.2023.01716"},{"key":"2_CR16","unstructured":"Li, B., Weinberger, K.Q., Belongie, S., Koltun, V., Ranftl, R.: Language-driven semantic segmentation. In: ICLR (2022)"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. In: 2023 IEEE\/CVF CVPR, pp. 7061\u20137070 (2022)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part V 13, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Messikommer, N., et al.: Multi-bracket high dynamic range imaging with event cameras. In: 2022 IEEE\/CVF CVPRW, pp. 546\u2013556 (2022)","DOI":"10.1109\/CVPRW56347.2022.00070"},{"issue":"2","key":"2_CR20","doi-asserted-by":"publisher","first-page":"3515","DOI":"10.1109\/LRA.2022.3145053","volume":"7","author":"N Messikommer","year":"2022","unstructured":"Messikommer, N., Gehrig, D., Gehrig, M., Scaramuzza, D.: Bridging the gap between events and frames through unsupervised domain adaptation. IEEE Robot. Autom. Lett. 7(2), 3515\u20133522 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2_CR21","unstructured":"Park, S., Kwak, N.: Feed: Feature-Level Ensemble for Knowledge Distillation (2019). arXiv preprint: arXiv:1909.10754"},{"key":"2_CR22","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"2_CR23","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical Text-Conditional Image Generation with Clip Latents, vol. 1, no. 2, pp. 3 (2022). arXiv preprint arXiv:2204.06125"},{"key":"2_CR24","unstructured":"Rebecq, H., Gehrig, D., Scaramuzza, D.: Esim: an open event camera simulator. In: Conference on Robot Learning (2018)"},{"key":"2_CR25","unstructured":"Rebecq, H., Ranftl, R., Koltun, V., Scaramuzza, D.: High speed and high dynamic range video with an event camera. IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI) (2019)"},{"key":"2_CR26","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 CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Scheerlinck, C., Rebecq, H., Gehrig, D., Barnes, N., Mahony, R., Scaramuzza, D.: Fast image reconstruction with an event camera. In: IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 156\u2013163 (2020)","DOI":"10.1109\/WACV45572.2020.9093366"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Sun, Z., Messikommer, N., Gehrig, D., Scaramuzza, D.: Ess: Learning event-based semantic segmentation from still images. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19830-4_20"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Bochicchio, A., Gehrig, D., Georgoulis, S., Li, Y., Scaramuzza, D.: Time Lens++: event-based frame interpolation with non-linear parametric flow and multi-scale fusion. In: IEEE\/CVF CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01723"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Wang, L., Chae, Y., Yoon, K.J.: Dual transfer learning for event-based end-task prediction via pluggable event to image translation. In: Proceedings of the IEEE\/CVF ICCV, pp. 2135\u20132145 (2021)","DOI":"10.1109\/ICCV48922.2021.00214"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Wang, L., Chae, Y., Yoon, S.H., Kim, T.K., Yoon, K.J.: Evdistill: Asynchronous events to end-task learning via bidirectional reconstruction-guided cross-modal knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 608\u2013619 (2021)","DOI":"10.1109\/CVPR46437.2021.00067"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Xian, Y., Choudhury, S., He, Y., Schiele, B., Akata, Z.: Semantic projection network for zero-and few-label semantic segmentation. In: Proceedings of the IEEE\/CVF CVPR, pp. 8256\u20138265 (2019)","DOI":"10.1109\/CVPR.2019.00845"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Xu, G., Liu, Z., Li, X., Loy, C.C.: Knowledge distillation meets self-supervision. In: European Conference on Computer Vision, pp. 588\u2013604. Springer (2020)","DOI":"10.1007\/978-3-030-58545-7_34"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De\u00a0Mello, S.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: Proceedings of the IEEE\/CVF CVPR, pp. 2955\u20132966 (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Yang, Y., Pan, L., Liu, L.: Event camera data pre-training. In: Proceedings of the IEEE\/CVF ICCV, pp. 10699\u201310709 (2023)","DOI":"10.1109\/ICCV51070.2023.00982"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, F., Zou, X., Liu, S., Li, C., Yang, J., Zhang, L.: A simple framework for open-vocabulary segmentation and detection. In: Proceedings of the IEEE\/CVF ICCV, pp. 1020\u20131031 (2023)","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Chen, Y., Kapadia, M., Metaxas, D.N.: Knowledge as priors: cross-modal knowledge generalization for datasets without superior knowledge. In: 2020 IEEE\/CVF CVPR, pp. 6527\u20136536 (2020)","DOI":"10.1109\/CVPR42600.2020.00656"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, A.Z., Yuan, L., Chaney, K., Daniilidis, K.: Unsupervised event-based learning of optical flow, depth, and egomotion. In: Proceedings of the IEEE\/CVF CVPR, pp. 989\u2013997 (2019)","DOI":"10.1109\/CVPR.2019.00108"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78444-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T11:33:02Z","timestamp":1733225582000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78444-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031784439","9783031784446"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78444-6_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}