{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T15:44:20Z","timestamp":1788018260659,"version":"build-2784847793"},"reference-count":108,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":["62027804"],"award-info":[{"award-number":["62027804"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62425101"],"award-info":[{"award-number":["62425101"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62506190"],"award-info":[{"award-number":["62506190"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62088102"],"award-info":[{"award-number":["62088102"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012401","name":"Beijing Science and Technology Planning Project","doi-asserted-by":"publisher","award":["Z:241100004224011"],"award-info":[{"award-number":["Z:241100004224011"]}],"id":[{"id":"10.13039\/501100012401","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":[[2026,7]]},"DOI":"10.1007\/s11263-026-02927-8","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T17:02:11Z","timestamp":1783616531000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Rethinking Neuromorphic Object Detection with Hybrid Dynamic Interaction Transformers"],"prefix":"10.1007","volume":"134","author":[{"given":"Dianze","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaokun","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaopeng","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-5935","authenticated-orcid":false,"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"key":"2927_CR1","unstructured":"Ahmed, S. H., Finkbeiner, J., & Neftci, E. (2024). A hybrid snn-ann network for event-based object detection with spatial and temporal attention arXiv."},{"key":"2927_CR2","doi-asserted-by":"crossref","unstructured":"Aydin, A., Gehrig, M., Gehrig, D., & Scaramuzza, D. (2023). A hybrid ann-snn architecture for low-power and low-latency visual perception., In: arXiv.","DOI":"10.1109\/CVPRW63382.2024.00579"},{"key":"2927_CR3","doi-asserted-by":"crossref","unstructured":"Bartolozzi, C., Indiveri, G., & Donati, E. (2022). Embodied neuromorphic intelligence. Nature communications,13(1), 1024.","DOI":"10.1038\/s41467-022-28487-2"},{"key":"2927_CR4","doi-asserted-by":"crossref","unstructured":"Bodden, L., Schwaiger, F., Ha, D. B., Kreuzberg, L., & Behnke, S. (2024). Spiking centernet: A distillation-boosted spiking neural network for object detection. arXiv.","DOI":"10.1109\/IJCNN60899.2024.10650418"},{"issue":"10","key":"2927_CR5","doi-asserted-by":"publisher","first-page":"2333","DOI":"10.1109\/JSSC.2014.2342715","volume":"49","author":"C Brandli","year":"2014","unstructured":"Brandli, C., Berner, R., Yang, M., Liu, S. C., & Delbruck, T. (2014). A 240$$\\times $$ 180 130 db 3 $$\\mu $$s latency global shutter spatiotemporal vision sensor. IEEE Journal of Solid-State Circuits, 49(10), 2333\u20132341.","journal-title":"IEEE Journal of Solid-State Circuits"},{"issue":"21","key":"2927_CR6","doi-asserted-by":"publisher","first-page":"24540","DOI":"10.1109\/JSEN.2021.3115016","volume":"21","author":"H Cao","year":"2021","unstructured":"Cao, H., Chen, G., Xia, J., Zhuang, G., & Knoll, A. (2021). Fusion-based feature attention gate component for vehicle detection based on event camera. IEEE Sensors Journal, 21(21), 24540\u201324548.","journal-title":"IEEE Sensors Journal"},{"key":"2927_CR7","doi-asserted-by":"crossref","unstructured":"Cao, H., Zhang, Z., Xia, Y., Li, X., Xia, J., Chen, G., & Knoll, A. (2024). Embracing events and frames with hierarchical feature refinement network for object detection. Proceedings of the European Conference on Computer Vision, pp 161\u2013177.","DOI":"10.1007\/978-3-031-72907-2_10"},{"key":"2927_CR8","doi-asserted-by":"crossref","unstructured":"Cao, J., Zheng, X., Lyu, Y., Wang, J., Xu, R., & Wang, L. (2023). Chasing day and night: Towards robust and efficient all-day object detection guided by an event camera.,In: arXiv.","DOI":"10.1109\/ICRA57147.2024.10611705"},{"key":"2927_CR9","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. Proceedings of the IEEE International Conference on Robotics and Automation, pp 9026\u20139032.","DOI":"10.1109\/ICRA57147.2024.10611705"},{"key":"2927_CR10","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. Proceedings of the European conference on computer vision pp. 213\u2013229.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2927_CR11","doi-asserted-by":"publisher","first-page":"9014","DOI":"10.1109\/TIP.2021.3122092","volume":"30","author":"B Chakraborty","year":"2021","unstructured":"Chakraborty, B., She, X., & Mukhopadhyay, S. (2021). A fully spiking hybrid neural network for energy-efficient object detection. IEEE Transactions on Image Processing, 30, 9014\u20139029.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"4","key":"2927_CR12","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. (2020). Event-based neuromorphic vision for autonomous driving: A paradigm shift for bio-inspired visual sensing and perception. IEEE Signal Processing Magazine, 37(4), 34\u201349.","journal-title":"IEEE Signal Processing Magazine"},{"key":"2927_CR13","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. Proceedings of the IEEE conference on computer vision and pattern recognition workshops pp. 644\u2013653.","DOI":"10.1109\/CVPRW.2018.00107"},{"key":"2927_CR14","doi-asserted-by":"crossref","unstructured":"Cordone, L., Miramond, B., & Thierion, P. (2022). Object detection with spiking neural networks on automotive event data. Proceedings of the International Joint Conference on Neural Networks pp. 1\u20138.","DOI":"10.1109\/IJCNN55064.2022.9892618"},{"key":"2927_CR15","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1016\/j.neunet.2019.09.005","volume":"121","author":"L Deng","year":"2020","unstructured":"Deng, L., Wu, Y., Hu, X., Liang, L., Ding, Y., Li, G., Zhao, G., Li, P., & Xie, Y. (2020). Rethinking the performance comparison between snns and anns. Neural networks, 121, 294\u2013307.","journal-title":"Neural networks"},{"key":"2927_CR16","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., & Sun, J. (2021). Repvgg: Making vgg-style convnets great again. Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition, pp 13733\u201313742.","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"2927_CR17","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. Proceedings of the International Conference on Learning Representations."},{"key":"2927_CR18","doi-asserted-by":"crossref","unstructured":"Fan, Y., Zhang, W., Liu, C., Li, M., & Lu, W. (2024). Sfod: Spiking fusion object detector. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 17191\u201317200.","DOI":"10.1109\/CVPR52733.2024.01627"},{"key":"2927_CR19","unstructured":"Fan, Y., Liu, C., Li, M., & Zhang, W. (2025). Spikssd: Better extraction and fusion for object detection with spiking neuron networks arXiv."},{"issue":"12","key":"2927_CR20","doi-asserted-by":"publisher","first-page":"5841","DOI":"10.1007\/s11263-024-02148-x","volume":"132","author":"X Fu","year":"2024","unstructured":"Fu, X., Cao, C., Xu, S., Zhang, F., Wang, K., & Zha, Z. J. (2024). Event-driven heterogeneous network for video deraining. International Journal of Computer Vision, 132(12), 5841\u20135861.","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"2927_CR21","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":"2927_CR22","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., & Sun, J. (2021). Yolox: Exceeding yolo series in 2021. arXiv."},{"issue":"8014","key":"2927_CR23","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1038\/s41586-024-07409-w","volume":"629","author":"D Gehrig","year":"2024","unstructured":"Gehrig, D., & Scaramuzza, D. (2024). Low-latency automotive vision with event cameras. Nature, 629(8014), 1034\u20131040.","journal-title":"Nature"},{"key":"2927_CR24","doi-asserted-by":"crossref","unstructured":"Gehrig, D., & Scaramuzza, D. (2024). Low latency automotive vision with event cameras. Nature.","DOI":"10.1038\/s41586-024-07409-w"},{"key":"2927_CR25","doi-asserted-by":"crossref","unstructured":"Gehrig, D., Loquercio, A., Derpanis, K. G., & Scaramuzza, D. (2019). End-to-end learning of representations for asynchronous event-based data. Proceedings of the IEEE\/CVF International Conference on Computer Vision pp. 5633\u20135643.","DOI":"10.1109\/ICCV.2019.00573"},{"issue":"2","key":"2927_CR26","doi-asserted-by":"publisher","first-page":"2822","DOI":"10.1109\/LRA.2021.3060707","volume":"6","author":"D Gehrig","year":"2021","unstructured":"Gehrig, D., R\u00fcegg, M., Gehrig, M., Hidalgo-Carri\u00f3, J., & Scaramuzza, D. (2021). Combining events and frames using recurrent asynchronous multimodal networks for monocular depth prediction. IEEE Robotics and Automation Letters, 6(2), 2822\u20132829.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"2927_CR27","doi-asserted-by":"crossref","unstructured":"Gehrig, M., & Scaramuzza, D. (2023). Recurrent vision transformers for object detection with event cameras. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 13884\u201313893,","DOI":"10.1109\/CVPR52729.2023.01334"},{"key":"2927_CR28","doi-asserted-by":"crossref","unstructured":"Guo, M., Chen, S., Gao, Z., Yang, W., Bartkovjak, P., Qin, Q., Hu, X., Zhou, D., Huang, Q., Uchiyama, M., et al. (2023). A three-wafer-stacked hybrid 15-mpixel cis $$+ $$1-mpixel evs with 4.6-gevent\/s readout, in-pixel tdc, and on-chip isp and esp function. IEEE Journal of Solid-State Circuits.","DOI":"10.1109\/JSSC.2023.3303154"},{"key":"2927_CR29","doi-asserted-by":"crossref","unstructured":"Han, B., & Roy, K. (2020). Deep spiking neural network: Energy efficiency through time based coding. Proceedings of the European Conference on Computer Vision pp. 388\u2013404.","DOI":"10.1007\/978-3-030-58607-2_23"},{"key":"2927_CR30","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision pp. 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"2927_CR31","doi-asserted-by":"crossref","unstructured":"Horowitz, M. (2014). 1.1 computing\u2019s energy problem (and what we can do about it). IEEE International Solid-state Circuits Conference pp. 10\u201314.","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"2927_CR32","doi-asserted-by":"crossref","unstructured":"Hu, Y., Zheng, Q., Jiang, X., & Pan, G. (2023). Fast-snn: Fast spiking neural network by converting quantized ann. IEEE Transactions on Pattern Analysis and Machine Intelligence.","DOI":"10.1109\/TPAMI.2023.3275769"},{"key":"2927_CR33","doi-asserted-by":"crossref","unstructured":"Iaboni, C., Kelly, T., & Abichandani, P. (2025). Nu-air: A neuromorphic urban aerial dataset for detection and localization of pedestrians and vehicles. International Journal of Computer Vision, 1\u201319.","DOI":"10.1007\/s11263-025-02418-2"},{"key":"2927_CR34","unstructured":"Jiang, Y., Wang, Y., Zhao, M., Zhang, Y., & Qi, H. (2023). Nighttime traffic object detection via adaptively integrating event and frame domains. Fundamental Research."},{"key":"2927_CR35","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Xia, P., Huang, K., Stechele, W., Chen, G., Bing, Z., & Knoll, A. (2019). Mixed frame-\/event-driven fast pedestrian detection. Proceedings of the International Conference on Robotics and Automation pp. 8332\u20138338.","DOI":"10.1109\/ICRA.2019.8793924"},{"key":"2927_CR36","doi-asserted-by":"crossref","unstructured":"Kang, Z., Li, J., Zhu, L., & Tian, Y. (2021). Retinomorphic sensing: A novel paradigm for future multimedia computing. Proceedings of the 29th ACM International Conference on Multimedia pp. 144\u2013152.","DOI":"10.1145\/3474085.3479237"},{"issue":"10s","key":"2927_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3505244","volume":"54","author":"S Khan","year":"2022","unstructured":"Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022). Transformers in vision: A survey. ACM Computing Surveys, 54(10s), 1\u201341.","journal-title":"ACM Computing Surveys"},{"key":"2927_CR38","doi-asserted-by":"crossref","unstructured":"Kim, S., Park, S., Na, B., & Yoon, S. (2020). Spiking-yolo: Spiking neural network for energy-efficient object detection. Proceedings of the AAAI conference on artificial intelligence pp. 11270\u201311277.","DOI":"10.1609\/aaai.v34i07.6787"},{"key":"2927_CR39","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. Proceedings of the International Conference on Learning Representations pp. 1\u201315."},{"key":"2927_CR40","doi-asserted-by":"crossref","unstructured":"Kodama, K., Sato, Y., Yorikado, Y., Berner, R., Mizoguchi, K., Miyazaki, T., Tsukamoto, M., Matoba, Y., Shinozaki, H., Niwa, A., et al. (2023). 1.22 $$\\mu $$m 35.6 mpixel rgb hybrid event-based vision sensor with 4.88 $$\\mu $$m-pitch event pixels and up to 10k event frame rate by adaptive control on event sparsity. In: Proceedings of the IEEE International Solid-State Circuits Conference pp 92\u201394.","DOI":"10.1109\/ISSCC42615.2023.10067520"},{"key":"2927_CR41","doi-asserted-by":"crossref","unstructured":"Kugele, A., Pfeil, T., Pfeiffer, M., & Chicca, E. (2021). Hybrid snn-ann: Energy-efficient classification and object detection for event-based vision. Proceedings of the DAGM German Conference on Pattern Recognition pp. 297\u2013312.","DOI":"10.1007\/978-3-030-92659-5_19"},{"key":"2927_CR42","doi-asserted-by":"crossref","unstructured":"Lee, C., Kosta, A. K., Zhu, A. Z., Chaney, K., Daniilidis, K., & Roy, K. (2020). Spike-flownet: Event-based optical flow estimation with energy-efficient hybrid neural networks. Proceedings of the European Conference on Computer Vision, pp 366\u2013382.","DOI":"10.1007\/978-3-030-58526-6_22"},{"key":"2927_CR43","doi-asserted-by":"crossref","unstructured":"Li, C., Liu, W., Gong, G., Ding, X., & Zhong, X. (2025). Su-yolo: Spiking neural network for efficient underwater object detection. Neurocomputing, p 130310.","DOI":"10.1016\/j.neucom.2025.130310"},{"key":"2927_CR44","doi-asserted-by":"crossref","unstructured":"Li, D., Li, J., & Tian, Y. (2023). Sodformer: Streaming object detection with transformer using events and frames. IEEE Transactions on Pattern Analysis and Machine Intelligence.","DOI":"10.1109\/TPAMI.2023.3298925"},{"key":"2927_CR45","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. Proceedings of the IEEE International Conference on Multimedia and Expo pp. 1396\u20131401.","DOI":"10.1109\/ICME.2019.00242"},{"issue":"4","key":"2927_CR46","doi-asserted-by":"publisher","first-page":"1742","DOI":"10.1109\/TNNLS.2021.3061122","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Fu, Y., Dong, S., Yu, Z., Huang, T., & Tian, Y. (2021). Asynchronous spatiotemporal spike metric for event cameras. IEEE Transactions on Neural Networks and Learning Systems, 34(4), 1742\u20131753.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2927_CR47","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":"2927_CR48","doi-asserted-by":"crossref","unstructured":"Li, J., Mao, Z., Fang, S., & Li, H. (2022). Er-san: Enhanced-adaptive relation self-attention network for image captioning. Proceedings of the International Joint Conference on Artificial Intelligence, pp 1081\u20131087.","DOI":"10.24963\/ijcai.2022\/151"},{"key":"2927_CR49","doi-asserted-by":"crossref","unstructured":"Li, L., Liniger, A., Millhaeusler, M., Tsiminaki, V., Li, Y., & Dai, D. (2023). Object-centric cross-modal feature distillation for event-based object detection., In: arXiv.","DOI":"10.1109\/ICRA57147.2024.10610325"},{"key":"2927_CR50","doi-asserted-by":"crossref","unstructured":"Li, Y., He, X., Dong, Y., Kong, Q., & Zeng, Y. (2022). Spike calibration: Fast and accurate conversion of spiking neural network for object detection and segmentation. In: arXiv.","DOI":"10.24963\/ijcai.2022\/345"},{"key":"2927_CR51","doi-asserted-by":"crossref","unstructured":"Li, Y., Geller, T., Kim, Y., & Panda, P. (2023). Seenn: towards temporal spiking early exit neural networks. Advances in Neural Information Processing Systems,36, 63327\u201363342.","DOI":"10.52202\/075280-2764"},{"issue":"1","key":"2927_CR52","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1007\/s11263-024-02197-2","volume":"133","author":"S Lin","year":"2025","unstructured":"Lin, S., Ma, Y., Chen, J., & Wen, B. (2025). Compressed event sensing (ces) volumes for event cameras. International Journal of Computer Vision, 133(1), 435\u2013455.","journal-title":"International Journal of Computer Vision"},{"key":"2927_CR53","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. Proceedings of the European Conference on Computer Vision pp. 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2927_CR54","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2017). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"2927_CR55","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":"2927_CR56","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.949142","volume":"16","author":"F Liu","year":"2022","unstructured":"Liu, F., & Zhao, R. (2022). Enhancing spiking neural networks with hybrid top-down attention. Frontiers in Neuroscience, 16, Article 949142.","journal-title":"Frontiers in Neuroscience"},{"issue":"2","key":"2927_CR57","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","volume":"128","author":"L Liu","year":"2020","unstructured":"Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietik\u00e4inen, M. (2020). Deep learning for generic object detection: A survey. International Journal of Computer Vision, 128(2), 261\u2013318.","journal-title":"International Journal of Computer Vision"},{"key":"2927_CR58","doi-asserted-by":"crossref","unstructured":"Liu, M., Qi, N., Shi, Y., & Yin, B. (2021). An attention fusion network for event-based vehicle object detection. Proceedings of the IEEE International Conference on Image Processing, pp 3363\u20133367.","DOI":"10.1109\/ICIP42928.2021.9506561"},{"key":"2927_CR59","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016). Ssd: Single shot multibox detector. Proceedings of the European Conference on Computer Vision, pp 21\u201337.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2927_CR60","doi-asserted-by":"crossref","unstructured":"Liu, X., Fan, X., Li, J., Li, D., Zhang, W., Ma, Z., & Tian, Y. (2025). High-rate monocular depth estimation via cross frame-rate collaboration of frames and events. International Journal of Computer Vision, pp 1\u201320.","DOI":"10.1007\/s11263-025-02488-2"},{"key":"2927_CR61","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. Proceedings of the IEEE\/CVF international conference on computer vision, pppp 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2927_CR62","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C. Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022). A convnet for the 2020s. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 11976\u201311986.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"2927_CR63","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yang, N., Wang, Y., Li, Y., Zhao, X., & Wang, F. Y. (2024). Enhancing traffic object detection in variable illumination with rgb-event fusion. IEEE Transactions on Intelligent Transportation Systems.","DOI":"10.1109\/TITS.2024.3456108"},{"key":"2927_CR64","doi-asserted-by":"crossref","unstructured":"Long, S., He, X., & Yao, C. (2020). Scene text detection and recognition: The deep learning era. International Journal of Computer Vision, pp. 1\u201324.","DOI":"10.1007\/s11263-020-01369-0"},{"key":"2927_CR65","doi-asserted-by":"crossref","unstructured":"Luo, C., Wu, J., Sun, S., & Ren, P. (2023). Transcodnet: Underwater transparently camouflaged object detection via rgb and event frames collaboration. IEEE Robotics and Automation Letters.","DOI":"10.1109\/LRA.2023.3346754"},{"key":"2927_CR66","doi-asserted-by":"crossref","unstructured":"Luo, X., Yao, M., Chou, Y., Xu, B., & Li, G. (2024). Integer-valued training and spike-driven inference spiking neural network for high-performance and energy-efficient object detection. Proceedings of the European Conference on Computer Vision pp. 253\u2013272.","DOI":"10.1007\/978-3-031-73411-3_15"},{"issue":"9","key":"2927_CR67","doi-asserted-by":"publisher","first-page":"1659","DOI":"10.1016\/S0893-6080(97)00011-7","volume":"10","author":"W Maass","year":"1997","unstructured":"Maass, W. (1997). Networks of spiking neurons: the third generation of neural network models. Neural networks, 10(9), 1659\u20131671.","journal-title":"Neural networks"},{"key":"2927_CR68","doi-asserted-by":"crossref","unstructured":"Messikommer, N., Gehrig, D., Loquercio, A., & Scaramuzza, D. (2020). Event-based asynchronous sparse convolutional networks. Proceedings of the European Conference on Computer Vision pp. 415\u2013431.","DOI":"10.1007\/978-3-030-58598-3_25"},{"issue":"1","key":"2927_CR69","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1109\/TBCAS.2017.2759783","volume":"12","author":"DP Moeys","year":"2017","unstructured":"Moeys, D. P., Corradi, F., Li, C., Bamford, S. A., Longinotti, L., Voigt, F. F., Berry, S., Taverni, G., Helmchen, F., & Delbruck, T. (2017). A sensitive dynamic and active pixel vision sensor for color or neural imaging applications. IEEE Transactions on Biomedical Circuits and Systems, 12(1), 123\u2013136.","journal-title":"IEEE Transactions on Biomedical Circuits and Systems"},{"issue":"4","key":"2927_CR70","doi-asserted-by":"publisher","first-page":"900","DOI":"10.1007\/s11263-020-01410-2","volume":"129","author":"M Mostafavi","year":"2021","unstructured":"Mostafavi, M., Wang, L., & Yoon, K. J. (2021). Learning to reconstruct hdr images from events, with applications to depth and flow prediction. International Journal of Computer Vision, 129(4), 900\u2013920.","journal-title":"International Journal of Computer Vision"},{"key":"2927_CR71","doi-asserted-by":"crossref","unstructured":"Nagaraj, M., Liyanagedera, C. M., & Roy, K. (2023). Dotie-detecting objects through temporal isolation of events using a spiking architecture. Proceedings of the IEEE International Conference on Robotics and Automation pp. 4858\u20134864.","DOI":"10.1109\/ICRA48891.2023.10161164"},{"issue":"6","key":"2927_CR72","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1109\/MSP.2019.2931595","volume":"36","author":"EO Neftci","year":"2019","unstructured":"Neftci, E. O., Mostafa, H., & Zenke, F. (2019). Surrogate gradient learning in spiking neural networks: Bringing the power of gradient-based optimization to spiking neural networks. IEEE Signal Processing Magazine, 36(6), 51\u201363.","journal-title":"IEEE Signal Processing Magazine"},{"issue":"1","key":"2927_CR73","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1167\/jov.22.1.10","volume":"22","author":"A Nuthmann","year":"2022","unstructured":"Nuthmann, A., & Canas-Bajo, T. (2022). Visual search in naturalistic scenes from foveal to peripheral vision: A comparison between dynamic and static displays. Journal of Vision, 22(1), 1\u201310.","journal-title":"Journal of Vision"},{"issue":"10","key":"2927_CR74","doi-asserted-by":"publisher","first-page":"3388","DOI":"10.1109\/TPAMI.2020.2981890","volume":"43","author":"K Oksuz","year":"2021","unstructured":"Oksuz, K., Cam, B. C., Kalkan, S., & Akbas, E. (2021). Imbalance problems in object detection: A review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(10), 3388\u20133415.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"7767","key":"2927_CR75","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1038\/s41586-019-1424-8","volume":"572","author":"J Pei","year":"2019","unstructured":"Pei, J., Deng, L., Song, S., Zhao, M., Zhang, Y., Wu, S., Wang, G., Zou, Z., Wu, Z., He, W., et al. (2019). Towards artificial general intelligence with hybrid tianjic chip architecture. Nature, 572(7767), 106\u2013111.","journal-title":"Nature"},{"key":"2927_CR76","first-page":"16639","volume":"33","author":"E Perot","year":"2020","unstructured":"Perot, E., De Tournemire, P., Nitti, D., Masci, J., & Sironi, A. (2020). Learning to detect objects with a 1 megapixel event camera. Proceedings of the Advances in Neural Information Processing Systems, 33, 16639\u201316652.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"issue":"10","key":"2927_CR77","doi-asserted-by":"publisher","first-page":"1470","DOI":"10.1109\/JPROC.2014.2346153","volume":"102","author":"C Posch","year":"2014","unstructured":"Posch, C., Serrano-Gotarredona, T., Linares-Barranco, B., & Delbruck, T. (2014). Retinomorphic event-based vision sensors: Bioinspired cameras with spiking output. Proceedings of the IEEE, 102(10), 1470\u20131484.","journal-title":"Proceedings of the IEEE"},{"key":"2927_CR78","unstructured":"Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement arXiv."},{"key":"2927_CR79","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Proceedings of the Advances in Neural Information Processing Systems."},{"issue":"7784","key":"2927_CR80","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1038\/s41586-019-1677-2","volume":"575","author":"K Roy","year":"2019","unstructured":"Roy, K., Jaiswal, A., & Panda, P. (2019). Towards spike-based machine intelligence with neuromorphic computing. Nature, 575(7784), 607\u2013617.","journal-title":"Nature"},{"key":"2927_CR81","doi-asserted-by":"crossref","unstructured":"Schaefer, S., Gehrig, D., & Scaramuzza, D. (2022). Aegnn: Asynchronous event-based graph neural networks. Proceedings of the IEEE\/CVF Conference on Computer vision and Pattern Recognition pp. 12371\u201312381.","DOI":"10.1109\/CVPR52688.2022.01205"},{"issue":"12","key":"2927_CR82","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1167\/jov.20.12.2","volume":"20","author":"EE Stewart","year":"2020","unstructured":"Stewart, E. E., Valsecchi, M., & Sch\u00fctz, A. C. (2020). A review of interactions between peripheral and foveal vision. Journal of Vision, 20(12), 2\u20132.","journal-title":"Journal of Vision"},{"key":"2927_CR83","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. Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 6555\u20136565.","DOI":"10.1109\/ICCV51070.2023.00603"},{"key":"2927_CR84","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. Proceedings of the International Conference on Robotics and Automation, pp. 933\u2013939.","DOI":"10.1109\/ICRA46639.2022.9812059"},{"key":"2927_CR85","unstructured":"Torbunov, D., Ren, Y., Ghose, A., Dim, O., & Cui, Y. (2024). Evrt-detr: The surprising effectiveness of detr-based detection for event cameras arXiv."},{"key":"2927_CR86","doi-asserted-by":"crossref","unstructured":"Tu, Z., Talebi, H., Zhang, H., Yang, F., Milanfar, P., Bovik, A., & Li, Y. (2022). Maxvit: Multi-axis vision transformer. Proceedings of the European conference on computer vision (pp. 459\u2013479). Springer.","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"2927_CR87","first-page":"4712","volume":"34","author":"S Vemprala","year":"2021","unstructured":"Vemprala, S., Mian, S., & Kapoor, A. (2021). Representation learning for event-based visuomotor policies. Proceedings of the Advances in Neural Information Processing Systems, 34, 4712\u20134724.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"2927_CR88","doi-asserted-by":"crossref","unstructured":"Wan, Z., Fan, B., Hui, L., Dai, Y., & Lee, G. H. (2025). Instance-level moving object segmentation from a single image with events. International Journal of Computer Vision, pp 1\u201322.","DOI":"10.1007\/s11263-025-02380-z"},{"key":"2927_CR89","doi-asserted-by":"crossref","unstructured":"Wang, X., Yu, H., Yu, L., Yang, W., & Xia, G. S. (2024). Towards robust keypoint detection and tracking: A fusion approach with event-aligned image features. IEEE Robotics and Automation Letters.","DOI":"10.1109\/LRA.2024.3440099"},{"key":"2927_CR90","doi-asserted-by":"publisher","first-page":"5215","DOI":"10.1109\/ACCESS.2023.3236800","volume":"11","author":"YK Wang","year":"2023","unstructured":"Wang, Y. K., Wang, S. E., & Wu, P. H. (2023). Spike-event object detection for neuromorphic vision. IEEE Access, 11, 5215\u20135230.","journal-title":"IEEE Access"},{"issue":"9","key":"2927_CR91","doi-asserted-by":"publisher","first-page":"9229","DOI":"10.1609\/aaai.v39i9.32999","volume":"39","author":"N Yang","year":"2025","unstructured":"Yang, N., Wang, Y., Liu, Z., Li, M., An, Y., & Zhao, X. (2025). Smamba: Sparse mamba for event-based object detection. Proceedings of the AAAI Conference on Artificial Intelligence, 39(9), 9229\u20139237.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2927_CR92","unstructured":"Yang, Z., Wu, Y., Wang, G., Yang, Y., Li, G., Deng, L., Zhu, J., & Shi, L. (2019). Dashnet A hybrid artificial and spiking neural network for high-speed object tracking., In: arXiv."},{"issue":"4","key":"2927_CR93","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1109\/TCDS.2024.3375620","volume":"16","author":"H You","year":"2024","unstructured":"You, H., Zhong, X., Liu, W., Wei, Q., Huang, W., Yu, Z., & Huang, T. (2024). Converting artificial neural networks to ultralow-latency spiking neural networks for action recognition. IEEE Transactions on Cognitive and Developmental Systems, 16(4), 1533\u20131545.","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"key":"2927_CR94","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.106092","volume":"172","author":"M Yuan","year":"2024","unstructured":"Yuan, M., Zhang, C., Wang, Z., Liu, H., Pan, G., & Tang, H. (2024). Trainable spiking-yolo for low-latency and high-performance object detection. Neural Networks, 172, Article 106092.","journal-title":"Neural Networks"},{"key":"2927_CR95","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."},{"key":"2927_CR96","doi-asserted-by":"publisher","first-page":"1371290","DOI":"10.3389\/fnins.2024.1371290","volume":"18","author":"H Zhang","year":"2024","unstructured":"Zhang, H., Zhou, C., Yu, L., Huang, L., Ma, Z., Fan, X., Zhou, H., & Tian, Y. (2024). Sglformer: spiking global-local-fusion transformer with high performance. Frontiers in Neuroscience, 18, 1371290.","journal-title":"Frontiers in Neuroscience"},{"key":"2927_CR97","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wang, Y., Liu, W., Li, M., Bai, J., Yin, B., & Yang, X. (2023). Frame-event alignment and fusion network for high frame rate tracking. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 9781\u20139790.","DOI":"10.1109\/CVPR52729.2023.00943"},{"issue":"5","key":"2927_CR98","doi-asserted-by":"publisher","first-page":"1857","DOI":"10.1007\/s11263-023-01959-8","volume":"132","author":"J Zhang","year":"2024","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.","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"2927_CR99","doi-asserted-by":"publisher","first-page":"3427","DOI":"10.1038\/s41467-022-30964-7","volume":"13","author":"R Zhao","year":"2022","unstructured":"Zhao, R., Yang, Z., Zheng, H., Wu, Y., Liu, F., Wu, Z., Li, L., Chen, F., Song, S., Zhu, J., et al. (2022). A framework for the general design and computation of hybrid neural networks. Nature Communications, 13(1), 3427.","journal-title":"Nature Communications"},{"key":"2927_CR100","doi-asserted-by":"crossref","unstructured":"Zhong, X., Hu, S., Liu, W., Huang, W., Ding, J., Yu, Z., & Huang, T. (2024). Towards low-latency event-based visual recognition with hybrid step-wise distillation spiking neural networks., In: Proceedings of the 32nd ACM international conference on multimedia, pp 9828\u20139836.","DOI":"10.1145\/3664647.3680832"},{"key":"2927_CR101","doi-asserted-by":"crossref","unstructured":"Zhou, C., Zhang, H., Zhou, Z., Yu, L., Huang, L., Fan, X., Yuan, L., Ma, Z., Zhou, H., & Tian, Y. (2024). Qkformer: Hierarchical spiking transformer using qk attention. In: arXiv.","DOI":"10.52202\/079017-0416"},{"key":"2927_CR102","unstructured":"Zhou, X., Wang, D., & Kr\u00e4henb\u00fchl, P. (2019). Objects as points. In: arXiv."},{"key":"2927_CR103","unstructured":"Zhou, Z., Zhu, Y., He, C., Wang, Y., Shuicheng, Y., Tian, Y., & Yuan, L. (2022). Spikformer: When spiking neural network meets transformer. Proceedings of the Eleventh International Conference on Learning Representations."},{"key":"2927_CR104","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. Proceedings of the IEEE International Conference on Robotics and Automation, pp 7808\u20137815.","DOI":"10.1109\/ICRA48891.2023.10161563"},{"key":"2927_CR105","unstructured":"Zhou, Z., Zhu, Y., He, C., Wang, Y., YAN, S., Tian, Y., & Yuan, L. (2023b). Spikformer: When spiking neural network meets transformer. In: The Eleventh International Conference on Learning Representations, https:\/\/openreview.net\/forum?id=frE4fUwz_h"},{"key":"2927_CR106","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wang, X., Chang, Y., Li, J., Huang, T., & Tian, Y. (2022). Event-based video reconstruction via potential-assisted spiking neural network. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 3594\u20133604.","DOI":"10.1109\/CVPR52688.2022.00358"},{"key":"2927_CR107","doi-asserted-by":"crossref","unstructured":"Zhu, X., Lyu, S., Wang, X., & Zhao, Q. (2021). Tph-yolov5: Improved yolov5 based on transformer prediction head for object detection on drone-captured scenarios. Proceedings of the IEEE\/CVF International Conference on Computer Vision pp. 2778\u20132788.","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"2927_CR108","doi-asserted-by":"crossref","unstructured":"Zubic, N., Gehrig, M., & Scaramuzza, D. (2024). State space models for event cameras. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 5819\u20135828.","DOI":"10.1109\/CVPR52733.2024.00556"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02927-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02927-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02927-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T05:50:29Z","timestamp":1785304229000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02927-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":108,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["2927"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02927-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"20 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors have no conflict of interest to declare that are relevant to the content of this article.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This article does not contain any studies with human participants performed by any of the authors.","order":2,"name":"Ethics","label":"Ethics Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Informed consent was obtained from all individual participants included in the study.","order":3,"name":"Ethics","label":"Consent to Participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Consent for publication was obtained from the participants.","order":4,"name":"Ethics","label":"Consent for Publication","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"340"}}