{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T06:40:34Z","timestamp":1776494434352,"version":"3.51.2"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U25B2044"],"award-info":[{"award-number":["U25B2044"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62502068"],"award-info":[{"award-number":["62502068"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s11263-026-02749-8","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T09:37:29Z","timestamp":1772789849000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["You Only Look Intensity Once: Event-Driven Long-Term High-Speed Object Detection"],"prefix":"10.1007","volume":"134","author":[{"given":"Wen","family":"Dong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyang","family":"Mei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinglian","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutong","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqi","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8046-722X","authenticated-orcid":false,"given":"Xin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,6]]},"reference":[{"key":"2749_CR1","unstructured":"Alif, M.A.R., & Hussain, M. (2025). Yolov12: A breakdown of the key architectural features. arXiv preprint arXiv:2502.14740"},{"issue":"2","key":"2749_CR2","doi-asserted-by":"publisher","first-page":"2519","DOI":"10.1109\/TPAMI.2022.3172212","volume":"45","author":"RW Baldwin","year":"2022","unstructured":"Baldwin, R. W., Liu, R., Almatrafi, M., Asari, V., & Hirakawa, K. (2022). Time-ordered recent event (tore) volumes for event cameras. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2), 2519\u20132532.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2749_CR3","unstructured":"Berner, R., Brandli, C., Yang, M., Liu, S. C., & Delbruck, T. (2013). A 240x180 120db 10mw 12us-latency sparse output vision sensor for mobile applications. In: Proceedings of the International Image Sensors Workshop, (pp. 41\u201344)."},{"key":"2749_CR4","doi-asserted-by":"crossref","unstructured":"Cao, J., Zheng, X., Lyu, Y., Wang, J., Xu, R., & Wang, L. (2024). Chasing day and night: Towards robust and efficient all-day object detection guided by an event camera. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), (pp. 9026\u20139032). IEEE.","DOI":"10.1109\/ICRA57147.2024.10611705"},{"key":"2749_CR5","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In: European conference on computer vision, (pp. 213\u2013229). Springer.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2749_CR6","doi-asserted-by":"crossref","unstructured":"Chen, N. F. (2018). Pseudo-labels for supervised learning on dynamic vision sensor data, applied to object detection under ego-motion. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, (pp. 644\u2013653).","DOI":"10.1109\/CVPRW.2018.00107"},{"key":"2749_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, (pp. 248\u2013255). Ieee.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2749_CR8","doi-asserted-by":"crossref","unstructured":"Dey, R., & Salem, F. M. (2017). Gate-variants of gated recurrent unit (gru) neural networks. In: 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS), (pp. 1597\u20131600). IEEE.","DOI":"10.1109\/MWSCAS.2017.8053243"},{"issue":"1","key":"2749_CR9","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. (2020). Event-based vision: A survey. IEEE transactions on pattern analysis and machine intelligence, 44(1), 154\u2013180.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"2749_CR10","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., & Sun, J. (2021). YOLOX: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430"},{"issue":"3","key":"2749_CR11","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. (2021). Dsec: A stereo event camera dataset for driving scenarios. IEEE Robotics and Automation Letters, 6(3), 4947\u20134954.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"2749_CR12","doi-asserted-by":"crossref","unstructured":"Gehrig, M., & Scaramuzza, D. (2023). Recurrent vision transformers for object detection with event cameras. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR),.","DOI":"10.1109\/CVPR52729.2023.01334"},{"key":"2749_CR13","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815706","volume-title":"Spiking neuron models: Single neurons, populations, plasticity","author":"W Gerstner","year":"2002","unstructured":"Gerstner, W., & Kistler, W. M. (2002). Spiking neuron models: Single neurons, populations, plasticity. Cambridge: Cambridge University Press."},{"key":"2749_CR14","doi-asserted-by":"crossref","unstructured":"Graves, A., & Graves, A. (2012). Long short-term memory. Supervised sequence labelling with recurrent neural networks (pp. 37\u201345).","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"2749_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2749_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, J., Zhou, B., Zhou, T., & Zhong, Y.(2024). Deep eventbased object detection in autonomous driving: A survey. In: 2024 10th International Conference on Big Data and Information Analytics (BigDIA), (pp. 447\u2013454). IEEE.","DOI":"10.1109\/BigDIA63733.2024.10808654"},{"key":"2749_CR17","unstructured":"Jocher, G., & Qiu, J. (2024). Ultralytics yolo11. https:\/\/github.com\/ultralytics\/ultralytics"},{"issue":"11","key":"2749_CR18","doi-asserted-by":"publisher","first-page":"14020","DOI":"10.1109\/TPAMI.2023.3298925","volume":"45","author":"D Li","year":"2023","unstructured":"Li, D., Tian, Y., & Li, J. (2023). Sodformer: Streaming object detection with transformer using events and frames. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(11), 14020\u201314037.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2749_CR19","doi-asserted-by":"crossref","unstructured":"Li, H., Peng, Y., Yuan, J., Wu, P., Wang, J., Zhang, Y., & Sun, X. (2025). Efficient event-based semantic segmentation via exploiting frame-event fusion: A hybrid neural network approach. In: Proceedings of the AAAI Conference on Artificial Intelligence, (vol.\u00a039, pp. 18296\u201318304).","DOI":"10.1609\/aaai.v39i17.34013"},{"key":"2749_CR20","doi-asserted-by":"crossref","unstructured":"Li, J., Dong, S., Yu, Z., Tian, Y., & Huang, T. (2019). Event-based vision enhanced: A joint detection framework in autonomous driving. In: 2019 ieee international conference on multimedia and expo (icme), (pp. 1396\u20131401). IEEE.","DOI":"10.1109\/ICME.2019.00242"},{"key":"2749_CR21","doi-asserted-by":"publisher","first-page":"2975","DOI":"10.1109\/TIP.2022.3162962","volume":"31","author":"J Li","year":"2022","unstructured":"Li, J., Li, J., Zhu, L., Xiang, X., Huang, T., & Tian, Y. (2022). Asynchronous spatio-temporal memory network for continuous event-based object detection. IEEE Transactions on Image Processing, 31, 2975\u20132987.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2749_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., Mao, H., Girshick, R., & He, K. (2022). Exploring plain vision transformer backbones for object detection. In: European conference on computer vision, (pp. 280\u2013296). Springer.","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"2749_CR23","first-page":"1","volume":"72","author":"B Liu","year":"2023","unstructured":"Liu, B., Xu, C., Yang, W., Yu, H., & Yu, L. (2023). Motion robust high-speed light-weighted object detection with event camera. IEEE Transactions on Instrumentation and Measurement, 72, 1\u201313.","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"2749_CR24","doi-asserted-by":"crossref","unstructured":"Liu, M., Qi, N., Shi, Y., & Yin, B. (2021). An attention fusion network for event-based vehicle object detection. In: 2021 IEEE International Conference on Image Processing (ICIP), (pp. 3363\u20133367). IEEE.","DOI":"10.1109\/ICIP42928.2021.9506561"},{"key":"2749_CR25","unstructured":"Liu, S. (2025). Rstformer. https:\/\/github.com\/shaoyu-liu\/RSTFormer"},{"key":"2749_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision, (pp. 10012\u201310022).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2749_CR27","unstructured":"Lyu, C., Zhang, W., Huang, H., Zhou, Y., Wang, Y., Liu, Y., Zhang, S., & Chen, K. (2022). Rtmdet: An empirical study of designing real-time object detectors."},{"issue":"3","key":"2749_CR28","doi-asserted-by":"publisher","first-page":"1378","DOI":"10.1109\/TCSVT.2021.3069848","volume":"32","author":"H Mei","year":"2021","unstructured":"Mei, H., Liu, Y., Wei, Z., Zhou, D., Wei, X., Zhang, Q., & Yang, X. (2021). Exploring dense context for salient object detection. IEEE Transactions on Circuits and Systems for Video Technology, 32(3), 1378\u20131389.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2749_CR29","doi-asserted-by":"crossref","unstructured":"Mei, H., Wang, Z., Yang, X., Wei, X., & Delbruck, T. (2023). Deep polarization reconstruction with pdavis events. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 22149\u201322158).","DOI":"10.1109\/CVPR52729.2023.02121"},{"key":"2749_CR30","doi-asserted-by":"crossref","unstructured":"Mei, H., Zhang, P., & Shou, M. Z. (2025). Sam-i2v: Upgrading sam to support promptable video segmentation with less than 0.2% training cost. In: Proceedings of the Computer Vision and Pattern Recognition Conference, (pp. 3417\u20133426).","DOI":"10.1109\/CVPR52734.2025.00324"},{"key":"2749_CR31","doi-asserted-by":"crossref","unstructured":"Peng, Y., Li, H., Zhang, Y., Sun, X., & Wu, F. (2024). Scene adaptive sparse transformer for event-based object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 16794\u201316804).","DOI":"10.1109\/CVPR52733.2024.01589"},{"issue":"6","key":"2749_CR32","doi-asserted-by":"publisher","first-page":"1964","DOI":"10.1109\/TPAMI.2019.2963386","volume":"43","author":"H Rebecq","year":"2019","unstructured":"Rebecq, H., Ranftl, R., Koltun, V., & Scaramuzza, D. (2019). High speed and high dynamic range video with an event camera. IEEE transactions on pattern analysis and machine intelligence, 43(6), 1964\u20131980.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"2749_CR33","unstructured":"Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767."},{"key":"2749_CR34","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"2749_CR35","doi-asserted-by":"crossref","unstructured":"Su, Q., Chou, Y., Hu, Y., Li, J., Mei, S., Zhang, Z., & Li, G. (2023). Deep directly-trained spiking neural networks for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 6555\u20136565).","DOI":"10.1109\/ICCV51070.2023.00603"},{"key":"2749_CR36","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., & Le, Q. V. (2020). Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, (pp. 10781\u201310790).","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"2749_CR37","doi-asserted-by":"crossref","unstructured":"Tomy, A., Paigwar, A., Mann, K. S., Renzaglia, A., & Laugier, C. (2022). Fusing event-based and rgb camera for robust object detection in adverse conditions. In: 2022 International conference on robotics and automation (ICRA), (pp. 933\u2013939). IEEE.","DOI":"10.1109\/ICRA46639.2022.9812059"},{"key":"2749_CR38","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Fleuret, F., Kiefel, M., Gehler, P., & Hirsch, M. (2019). Learning an event sequence embedding for dense event-based deep stereo. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 1527\u20131537).","DOI":"10.1109\/ICCV.2019.00161"},{"key":"2749_CR39","doi-asserted-by":"crossref","unstructured":"Wang, C. Y., Bochkovskiy, A., & Liao, H. Y. M. (2023). Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, (pp. 7464\u20137475).","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"2749_CR40","unstructured":"Wang, Y., Mei, H., Bao, Q., Wei, Z., Shou, M. Z., Li, H., Dong, B., & Yang, X. (2024). Apprenticeship-inspired elegance: Synergistic knowledge distillation empowers spiking neural networks for efficient single-eye emotion recognition. In Proceedings of the thirty-third international joint conference on artificial intelligence (pp. 3160\u20133168)."},{"key":"2749_CR41","doi-asserted-by":"crossref","unstructured":"Wang, D., Jia, X., Zhang, Y., Zhang, X., Wang, Y., Zhang, Z., Wang, D., & Lu, H. (2023). Dual memory aggregation network for event-based object detection with learnable representation. In: Proceedings of the AAAI Conference on Artificial Intelligence, (vol.\u00a037, pp. 2492\u20132500).","DOI":"10.1609\/aaai.v37i2.25346"},{"key":"2749_CR42","doi-asserted-by":"crossref","unstructured":"Yu, N., Ma, T., Zhang, J., Zhang, Y., Bao, Q., Wei, X., & Yang, X. (2024). Adaptive vision transformer for event-based human pose estimation. In Proceedings of the 32nd ACM International Conference on Multimedia (pp. 2833\u20132841).","DOI":"10.1145\/3664647.3681401"},{"key":"2749_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, Y., He, B., Fan, X., Wang, Y., & Zhang, Y. (2023). Direct training high-performance spiking neural networks for object recognition and detection. Frontiers in Neuroscience, 17, 1229951.","DOI":"10.3389\/fnins.2023.1229951"},{"key":"2749_CR44","unstructured":"Zhang, H., Wang, X., Xu, C., Wang, X., Xu, F., Yu, H., Yu, L., & Yang, W. (2024). Frequency-adaptive low-latency object detection using events and frames. arXiv preprint arXiv:2412.04149"},{"key":"2749_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhang, J., Dong, B., Peers, P., Wu, W., Wei, X., Heide, F., & Yang, X. (2023). In the blink of an eye: Event-based emotion recognition. In: ACM SIGGRAPH 2023 Conference Proceedings, (pp. 1\u201311).","DOI":"10.1145\/3588432.3591511"},{"key":"2749_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, J., Dong, B., Fu, Y., Wang, Y., Wei, X., Yin, B., & Yang, X. (2024). A universal event-based plug-in module for visual object tracking in degraded conditions. International Journal of Computer Vision, 132(5), 1857\u20131879.","DOI":"10.1007\/s11263-023-01959-8"},{"key":"2749_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, Q., Li, X., He, L., Yang, Y., Cheng, G., Tong, Y., Ma, L., & Tao, D. (2022). Transvod: End-to-end video object detection with spatial-temporal transformers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(6), 7853\u20137869.","DOI":"10.1109\/TPAMI.2022.3223955"},{"key":"2749_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Wu, Z., Boutteau, R., Yang, F., Demonceaux, C., & Ginhac, D. (2023). Rgb-event fusion for moving object detection in autonomous driving. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), (pp. 7808\u20137815). IEEE.","DOI":"10.1109\/ICRA48891.2023.10161563"},{"key":"2749_CR49","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020). Deformable detr: Deformable transformers for end-to-end object detection. In: International Conference on Learning Representations,."},{"key":"2749_CR50","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020). Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02749-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02749-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02749-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T05:44:47Z","timestamp":1776491087000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02749-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":50,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["2749"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02749-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,6]]},"assertion":[{"value":"6 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"149"}}