{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T00:33:54Z","timestamp":1759365234037,"version":"build-2065373602"},"reference-count":64,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Event-based cameras are sensors inspired by the human eye, offering advantages such as high-speed robustness and low power consumption. Established deep learning techniques have proven effective in processing event data, but there remains a significant space of possibilities that could be further explored to maximize the potential of such combinations. In this context, Chimera is a Block-Based Neural Architecture Search (NAS) framework specifically designed for Event-Based Object Detection, aiming to systematically adapt RGB-domain processing methods to the event domain. The Chimera design space is constructed from various macroblocks, including attention blocks, convolutions, State Space Models, and MLP-mixer-based architectures, providing a valuable trade-off between local and global processing capabilities, as well as varying levels of complexity. Results on Prophesee's GEN1 dataset demonstrated state-of-the-art mean Average Precision (mAP) while reducing the number of parameters by 1.6 \u00d7 and achieving a 2.1 \u00d7 speed-up. The project is available at: <jats:ext-link>https:\/\/github.com\/silvada95\/Chimera<\/jats:ext-link>.<\/jats:p>","DOI":"10.3389\/frai.2025.1644889","type":"journal-article","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T05:51:28Z","timestamp":1759297888000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Chimera: a block-based neural architecture search framework for event-based object detection"],"prefix":"10.3389","volume":"8","author":[{"given":"Diego A.","family":"Silva","sequence":"first","affiliation":[]},{"given":"Ahmed","family":"Elsheikh","sequence":"additional","affiliation":[]},{"given":"Kamilya","family":"Smagulova","sequence":"additional","affiliation":[]},{"given":"Mohammed E.","family":"Fouda","sequence":"additional","affiliation":[]},{"given":"Ahmed M.","family":"Eltawil","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"4064","DOI":"10.1109\/CVPRW59228.2023.00426","article-title":"\u201cPedro: an event-based dataset for person detection in robotics,\u201d","author":"Boretti","year":"2023"},{"key":"B2","doi-asserted-by":"crossref","DOI":"10.1201\/9781315139470","volume-title":"Classification and Regression Trees","author":"Breiman","year":"2017"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.23919\/MVA57639.2023.10215590","article-title":"\u201cObject detection for embedded systems using tiny spiking neural networks: filtering noise through visual attention,\u201d","author":"Bulzomi","year":"2023"},{"key":"B4","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/ICCV48922.2021.00041","article-title":"\u201cCrossvit: cross-attention multi-scale vision transformer for image classification,\u201d","author":"Chen","year":""},{"key":"B5","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1109\/ICCV48922.2021.00063","article-title":"\u201cVisformer: the vision-friendly transformer,\u201d","author":"Chen","year":""},{"key":"B6","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1007\/978-3-031-19211-1_33","article-title":"\u201cEdgevit: efficient visual modeling for edge computing,\u201d","author":"Chen","year":"2022"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IJCNN55064.2022.9892618","article-title":"\u201cObject detection with spiking neural networks on automotive event data,\u201d","author":"Cordone","year":"2022"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2001.08499","article-title":"A large scale event-based detection dataset for automotive","author":"De Tournemire","year":"2020","journal-title":"arXiv preprint"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.15151","article-title":"SpikSSD: better extraction and fusion for object detection with spiking neuron networks","author":"Fan","year":"2025","journal-title":"arXiv preprint"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.15192","article-title":"SFOD: Spiking fusion object detector","author":"Fan","year":"2024","journal-title":"arXiv preprint"},{"key":"B11","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/TPAMI.2020.3008413","article-title":"Event-based vision: a survey","volume":"44","author":"Gallego","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1038\/s41586-024-07409-w","article-title":"Low-latency automotive vision with event cameras","volume":"629","author":"Gehrig","year":"2024","journal-title":"Nature"},{"key":"B13","doi-asserted-by":"publisher","first-page":"13884","DOI":"10.1109\/CVPR52729.2023.01334","article-title":"\u201cRecurrent vision transformers for object detection with event cameras,\u201d","author":"Gehrig","year":"2023"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.00752","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"B15","doi-asserted-by":"publisher","first-page":"22867","DOI":"10.1109\/CVPR52729.2023.02190","article-title":"\u201cHierarchical neural memory network for low latency event processing,\u201d","author":"Hamaguchi","year":"2023"},{"key":"B16","article-title":"Escaping the big data paradigm with compact transformers","author":"Hassani","year":"2021","journal-title":"arXiv preprint"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2306.06189","article-title":"Fastervit: Fast vision transformers with hierarchical attention","author":"Hatamizadeh","year":"2023","journal-title":"arXiv preprint"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02352","article-title":"Mambavision: a hybrid mamba-transformer vision backbone","author":"Hatamizadeh","year":"2024","journal-title":"arXiv preprint"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"8","author":"Hochreiter","year":"1997"},{"key":"B21","doi-asserted-by":"publisher","first-page":"3981","DOI":"10.1007\/s11042-020-09749-x","article-title":"Real time object detection and trackingsystem for video surveillance system","volume":"80","author":"Jha","year":"2021","journal-title":"Multimed. Tools Appl"},{"key":"B22","first-page":"61020","article-title":"Meco: zero-shot nas with one data and single forward pass via minimum eigenvalue of correlation","volume":"36","author":"Jiang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B23","unstructured":"Jocher\n              G.\n            \n            \n              Chaurasia\n              A.\n            \n            \n              Qiu\n              J.\n            \n          \n          Version 8.0.0\n          Ultralytics YOLO\n          \n          2023"},{"key":"B24","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B25","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/978-3-030-92659-5_19","article-title":"\u201cHybrid SNN-ANN: energy-efficient classification and object detection for event-based vision,\u201d","author":"Kugele","year":"2021"},{"key":"B26","doi-asserted-by":"publisher","first-page":"5893","DOI":"10.1109\/CVPR52733.2024.00563","article-title":"\u201cAz-nas: Assembling zero-cost proxies for network architecture search,\u201d","author":"Lee","year":"2024"},{"key":"B27","doi-asserted-by":"publisher","first-page":"7618","DOI":"10.1109\/TPAMI.2024.3395423","article-title":"Zero-shot neural architecture search: Challenges, solutions, and opportunities","volume":"46","author":"Li","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B28","doi-asserted-by":"publisher","first-page":"6307","DOI":"10.1109\/CVPRW59228.2023.00671","article-title":"\u201cConvmlp: hierarchical convolutional mlps for vision,\u201d","author":"Li","year":"2023"},{"key":"B29","doi-asserted-by":"publisher","first-page":"2975","DOI":"10.1109\/TIP.2022.3162962","article-title":"Asynchronous spatio-temporal memory network for continuous event-based object detection","volume":"31","author":"Li","year":"","journal-title":"IEEE Trans. Image Process"},{"key":"B30","first-page":"12934","article-title":"Efficientformer: vision transformers at mobilenet speed","volume":"35","author":"Li","year":"","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B31","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1109\/JSSC.2007.914337","article-title":"A 128 \u00d7 128 120 db 15 \u03bcs latency asynchronous temporal contrast vision sensor","volume":"43","author":"Lichtsteiner","year":"2008","journal-title":"IEEE J. Solid-State Circuits"},{"key":"B32","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1109\/ICCV48922.2021.00040","article-title":"\u201cZen-nas: a zero-shot nas for high-performance image recognition,\u201d","author":"Lin","year":"2021"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3269780","article-title":"Motion robust high-speed light-weighted object detection with event camera","volume":"72","author":"Liu","year":"2023","journal-title":"IEEE Trans. Instrum. Meas"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1806.09055","article-title":"Darts: Differentiable architecture search","author":"Liu","year":"2018","journal-title":"arXiv preprint"},{"key":"B35","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","article-title":"Deep learning for generic object detection: a survey","volume":"128","author":"Liu","year":"2020","journal-title":"Int. J. Comput. Vis"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1907.07484","article-title":"Benchmarking robustness in object detection: autonomous driving when winter is coming","author":"Michaelis","year":"2019","journal-title":"arXiv preprint"},{"key":"B37","first-page":"6114","article-title":"\u201cStereo depth from events cameras: concentrate and focus on the future,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Nam","year":"2022"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2104.10350","article-title":"Carbon emissions and large neural network training","author":"Patterson","year":"2021","journal-title":"arXiv preprint"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32690","article-title":"Efficientvmamba: atrous selective scan for light weight visual mamba","author":"Pei","year":"2024","journal-title":"arXiv preprint"},{"key":"B40","first-page":"16794","article-title":"\u201cScene adaptive sparse transformer for event-based object detection,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Peng","year":"2024"},{"key":"B41","doi-asserted-by":"publisher","first-page":"2056","DOI":"10.1609\/aaai.v37i2.25298","article-title":"Better and faster: adaptive event conversion for event-based object detection","volume":"37","author":"Peng","year":"","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00555","article-title":"\u201cGet: group event transformer for event-based vision,\u201d","author":"Peng","year":"","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"B43","first-page":"16639","article-title":"Learning to detect objects with a 1 megapixel event camera","volume":"33","author":"Perot","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3447582","article-title":"A comprehensive survey of neural architecture search: challenges and solutions","volume":"54","author":"Ren","year":"2021","journal-title":"ACM Comput. Surv"},{"key":"B45","doi-asserted-by":"publisher","first-page":"12371","DOI":"10.1109\/CVPR52688.2022.01205","article-title":"\u201cAegnn: asynchronous event-based graph neural networks,\u201d","author":"Schaefer","year":"2022"},{"key":"B46","first-page":"802","article-title":"Convolutional lstm network: a machine learning approach for precipitation nowcasting","volume":"28","author":"Shi","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B47","doi-asserted-by":"publisher","first-page":"1477979","DOI":"10.3389\/fnins.2024.1477979","article-title":"A recurrent yolov8-based framework for event-based object detection","volume":"18","author":"Silva","year":"2025","journal-title":"Front. Neurosci"},{"key":"B48","doi-asserted-by":"publisher","first-page":"16519","DOI":"10.1109\/CVPR46437.2021.01625","article-title":"\u201cBottleneck transformers for visual recognition,\u201d","author":"Srinivas","year":"2021"},{"key":"B49","doi-asserted-by":"publisher","first-page":"6555","DOI":"10.1109\/ICCV51070.2023.00603","article-title":"\u201cDeep directly-trained spiking neural networks for object detection,\u201d","author":"Su","year":"2023"},{"key":"B50","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.1109\/DDCLS58216.2023.10166491","article-title":"\u201cEvent-based object detection using graph neural networks,\u201d","author":"Sun","year":"2023"},{"key":"B51","doi-asserted-by":"publisher","first-page":"10935","DOI":"10.1109\/CVPR52688.2022.01066","article-title":"\u201cAn image patch is a wave: phase-aware vision MLP,\u201d","author":"Tang","year":"2022"},{"key":"B52","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.3390\/make5040083","article-title":"A comprehensive review of yolo architectures in computer vision: from yolov1 to yolov8 and yolo-nas","volume":"5","author":"Terven","year":"2023","journal-title":"Mach. Learn. Knowl. Extr"},{"key":"B53","first-page":"24261","article-title":"Mlp-mixer: an all-mlp architecture for vision","volume":"34","author":"Tolstikhin","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B54","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/978-3-031-20053-3_27","article-title":"\u201cMaxvit: multi-axis vision transformer,\u201d","author":"Tu","year":"2022"},{"key":"B55","article-title":"\u201cAttention is all you need,\u201d","author":"Vaswani","year":"2017"},{"key":"B56","doi-asserted-by":"publisher","first-page":"5215","DOI":"10.1109\/ACCESS.2023.3236800","article-title":"Spike-event object detection for neuromorphic vision","volume":"11","author":"Wang","year":"2023","journal-title":"IEEE Access"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_18","article-title":"Eas-snn: end-to-end adaptive sampling and representation for event-based detection with recurrent spiking neural networks","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"B58","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/ICCV48922.2021.00009","article-title":"\u201cCVT: Introducing convolutions to vision transformers,\u201d","author":"Wu","year":"2021"},{"key":"B59","doi-asserted-by":"publisher","first-page":"e13","DOI":"10.4108\/airo.v1i1.2709","article-title":"The object detection, perspective and obstacles in robotic: a review","volume":"1","author":"Xu","year":"2022","journal-title":"EAI Endorsed Trans. AI Robot"},{"key":"B60","doi-asserted-by":"publisher","first-page":"9981","DOI":"10.1109\/ICCV48922.2021.00983","article-title":"\u201cCo-scale conv-attentional image transformers,\u201d","author":"Xu","year":"2021"},{"key":"B61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.32999","article-title":"Smamba: sparse mamba for event-based object detection","author":"Yang","year":"2025","journal-title":"arXiv preprint"},{"key":"B62","doi-asserted-by":"publisher","first-page":"1229951","DOI":"10.3389\/fnins.2023.1229951","article-title":"Direct training high-performance spiking neural networks for object recognition and detection","volume":"17","author":"Zhang","year":"2023","journal-title":"Front. Neurosci"},{"key":"B63","doi-asserted-by":"publisher","first-page":"12846","DOI":"10.1109\/ICCV51070.2023.01180","article-title":"\u201cFrom chaos comes order: ordering event representations for object recognition and detection,\u201d","author":"Zubi\u0107","year":"2023"},{"key":"B64","doi-asserted-by":"publisher","first-page":"5819","DOI":"10.1109\/CVPR52733.2024.00556","article-title":"\u201cState space models for event cameras,\u201d","author":"Zubic","year":"2024"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1644889\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T05:51:36Z","timestamp":1759297896000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1644889\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"references-count":64,"alternative-id":["10.3389\/frai.2025.1644889"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1644889","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,1]]},"article-number":"1644889"}}