{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:43:57Z","timestamp":1778049837317,"version":"3.51.4"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729065","type":"print"},{"value":"9783031729072","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-72907-2_10","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:22:17Z","timestamp":1730301737000},"page":"161-177","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Embracing Events and\u00a0Frames with\u00a0Hierarchical Feature Refinement Network for\u00a0Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8225-858X","authenticated-orcid":false,"given":"Hu","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9220-2441","authenticated-orcid":false,"given":"Zehua","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6684-9814","authenticated-orcid":false,"given":"Yan","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4883-0073","authenticated-orcid":false,"given":"Xinyi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9628-9563","authenticated-orcid":false,"given":"Jiahao","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7416-592X","authenticated-orcid":false,"given":"Guang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4840-076X","authenticated-orcid":false,"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"10_CR1","unstructured":"Binas, J., Neil, D., Liu, S., Delbr\u00fcck, T.: DDD17: end-to-end DAVIS driving dataset. CoRR (2017)"},{"key":"10_CR2","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint (2020)"},{"issue":"10","key":"10_CR3","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.: A 240 $$\\times $$ 180 130 db 3 $$\\mu $$s latency global shutter spatiotemporal vision sensor. IEEE J. Solid-State Circuits 49(10), 2333\u20132341 (2014)","journal-title":"IEEE J. Solid-State Circuits"},{"key":"10_CR4","first-page":"1","volume":"71","author":"H Cao","year":"2022","unstructured":"Cao, H., Chen, G., Li, Z., Hu, Y., Knoll, A.: NeuroGrasp: multimodal neural network with Euler region regression for neuromorphic vision-based grasp pose estimation. IEEE Trans. Instrum. Meas. 71, 1\u201311 (2022)","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"21","key":"10_CR5","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.: Fusion-based feature attention gate component for vehicle detection based on event camera. IEEE Sens. J. 21(21), 24540\u201324548 (2021)","journal-title":"IEEE Sens. J."},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Cao, H., et al.: SDPT: semantic-aware dimension-pooling transformer for image segmentation. IEEE Trans. Intell. Transp. Syst. 1\u201313 (2024)","DOI":"10.1109\/TITS.2024.3417813"},{"issue":"4","key":"10_CR7","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."},{"key":"10_CR8","doi-asserted-by":"publisher","first-page":"10","DOI":"10.3389\/fnbot.2019.00010","volume":"13","author":"G Chen","year":"2019","unstructured":"Chen, G., et al.: Multi-cue event information fusion for pedestrian detection with neuromorphic vision sensors. Front. Neurorobot. 13, 10 (2019)","journal-title":"Front. Neurorobot."},{"key":"10_CR9","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1007\/s42154-021-00157-x","volume":"4","author":"G Chen","year":"2021","unstructured":"Chen, G., Chen, K., Zhang, L., Zhang, L., Knoll, A.: VCANet: vanishing-point-guided context-aware network for small road object detection. Autom. Innov. 4, 400\u2013412 (2021)","journal-title":"Autom. Innov."},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Chen, N.F.Y.: Pseudo-labels for supervised learning on dynamic vision sensor data, applied to object detection under ego-motion. In: CVPRW (2018)","DOI":"10.1109\/CVPRW.2018.00107"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Bi-directional cross-modality feature propagation with separation-and-aggregation gate for RGB-d semantic segmentation. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Dodge, S., Karam, L.: Understanding how image quality affects deep neural networks. In: QoMEX (2016)","DOI":"10.1109\/QoMEX.2016.7498955"},{"issue":"1","key":"10_CR13","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/TPAMI.2020.3008413","volume":"44","author":"G Gallego","year":"2020","unstructured":"Gallego, G., 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."},{"issue":"2","key":"10_CR14","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.: Combining events and frames using recurrent asynchronous multimodal networks for monocular depth prediction. IEEE Robot. Autom. Lett. 6(2), 2822\u20132829 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"3","key":"10_CR15","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(3), 4947\u20134954 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Gehrig, M., Scaramuzza, D.: Recurrent vision transformers for object detection with event cameras. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01334"},{"key":"10_CR17","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":"10_CR18","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint (2019)"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Hu, Y., Delbruck, T., Liu, S.C.: Learning to exploit multiple vision modalities by using grafted networks. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58517-4_6"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Ji, W., et\u00a0al.: Calibrated RGB-d salient object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00935"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Jiang, Z., et al.: Mixed frame-\/event-driven fast pedestrian detection. In: ICRA (2019)","DOI":"10.1109\/ICRA.2019.8793924"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Li, J., Dong, S., Yu, Z., Tian, Y., Huang, T.: Event-based vision enhanced: a joint detection framework in autonomous driving. In: ICME (2019)","DOI":"10.1109\/ICME.2019.00242"},{"key":"10_CR25","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.: Asynchronous spatio-temporal memory network for continuous event-based object detection. IEEE Trans. Image Process. 31, 2975\u20132987 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"10_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"10_CR29","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","volume":"128","author":"L Liu","year":"2020","unstructured":"Liu, L., et al.: Deep learning for generic object detection: a survey. Int. J. Comput. Vision 128, 261\u2013318 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Liu, M., Qi, N., Shi, Y., Yin, B.: An attention fusion network for event-based vehicle object detection. In: ICIP (2021)","DOI":"10.1109\/ICIP42928.2021.9506561"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Liu, W., et al.: SSD: Single shot multibox detector. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"10_CR32","unstructured":"Michaelis, C., et al.: Benchmarking robustness in object detection: autonomous driving when winter is coming. arXiv preprint (2019)"},{"issue":"1","key":"10_CR33","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1109\/TBCAS.2017.2759783","volume":"12","author":"DP Moeys","year":"2017","unstructured":"Moeys, D.P., et al.: A sensitive dynamic and active pixel vision sensor for color or neural imaging applications. IEEE Trans. Biomed. Circuits Syst. 12(1), 123\u2013136 (2017)","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"10_CR34","doi-asserted-by":"publisher","first-page":"107087","DOI":"10.1016\/j.engappai.2023.107087","volume":"126","author":"F Munir","year":"2023","unstructured":"Munir, F., Azam, S., Yow, K.C., Lee, B.G., Jeon, M.: Multimodal fusion for sensorimotor control in steering angle prediction. Eng. Appl. Artif. Intell. 126, 107087 (2023)","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"10","key":"10_CR35","doi-asserted-by":"publisher","first-page":"3388","DOI":"10.1109\/TPAMI.2020.2981890","volume":"43","author":"K Oksuz","year":"2020","unstructured":"Oksuz, K., Cam, B.C., Kalkan, S., Akbas, E.: Imbalance problems in object detection: a review. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3388\u20133415 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR36","unstructured":"Perot, E., De\u00a0Tournemire, P., Nitti, D., Masci, J., Sironi, A.: Learning to detect objects with a 1 megapixel event camera. In: NeurIPS (2020)"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"issue":"6","key":"10_CR38","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Sun, K., et al.: Fab: a robust facial landmark detection framework for motion-blurred videos. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00556"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Sun, L., et al.: Event-based fusion for motion deblurring with cross-modal attention. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19797-0_24"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Tomy, A., Paigwar, A., Mann, K.S., Renzaglia, A., Laugier, C.: Fusing event-based and RGB camera for robust object detection in adverse conditions. In: ICRA (2022)","DOI":"10.1109\/ICRA46639.2022.9812059"},{"key":"10_CR42","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-Net: efficient channel attention for deep convolutional neural networks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"10_CR44","doi-asserted-by":"crossref","unstructured":"Xia, Y., et al.: CASSPR: cross attention single scan place recognition. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00777"},{"key":"10_CR45","doi-asserted-by":"crossref","unstructured":"Xia, Y., et al.: SOE-Net: a self-attention and orientation encoding network for point cloud based place recognition. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01119"},{"issue":"12","key":"10_CR46","doi-asserted-by":"publisher","first-page":"14679","DOI":"10.1109\/TITS.2023.3300537","volume":"24","author":"J Zhang","year":"2023","unstructured":"Zhang, J., Liu, H., Yang, K., Hu, X., Liu, R., Stiefelhagen, R.: CMX: cross-modal fusion for RGB-x semantic segmentation with transformers. IEEE Trans. Intell. Transp. Syst. 24(12), 14679\u201314694 (2023)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, T., Fu, H., Chen, G., Zhou, Y., Fan, D.P., Shao, L.: Specificity-preserving RGB-d saliency detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00464"},{"key":"10_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Wu, Z., Boutteau, R., Yang, F., Demonceaux, C., Ginhac, D.: RGB-event fusion for moving object detection in autonomous driving. In: ICRA (2023)","DOI":"10.1109\/ICRA48891.2023.10161563"},{"key":"10_CR49","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: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00108"}],"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\/978-3-031-72907-2_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:26:56Z","timestamp":1730302016000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72907-2_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031729065","9783031729072"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72907-2_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}