English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The ability to detect objects in all lighting (i.e., normal-, over-, andunder-exposed) conditions is crucial for real-world applications, such asself-driving.Traditional RGB-based detectors often fail under such varyinglighting conditions.Therefore, recent works utilize novel event cameras tosupplement or guide the RGB modality; however, these methods typically adoptasymmetric network structures that rely predominantly on the RGB modality,resulting in limited robustness for all-day detection. In this paper, wepropose EOLO, a novel object detection framework that achieves robust andefficient all-day detection by fusing both RGB and event modalities. Our EOLOframework is built based on a lightweight spiking neural network (SNN) toefficiently leverage the asynchronous property of events. Buttressed by it, wefirst introduce an Event Temporal Attention (ETA) module to learn the hightemporal information from events while preserving crucial edge information.Secondly, as different modalities exhibit varying levels of importance underdiverse lighting conditions, we propose a novel Symmetric RGB-Event Fusion(SREF) module to effectively fuse RGB-Event features without relying on aspecific modality, thus ensuring a balanced and adaptive fusion for all-daydetection. In addition, to compensate for the lack of paired RGB-Event datasetsfor all-day training and evaluation, we propose an event synthesis approachbased on the randomized optical flow that allows for directly generating theevent frame from a single exposure image. We further build two new datasets,E-MSCOCO and E-VOC based on the popular benchmarks MSCOCO and PASCAL VOC.Extensive experiments demonstrate that our EOLO outperforms thestate-of-the-art detectors,e.g.,RENet,by a substantial margin (+3.74% mAP50) inall lighting conditions.Our code and datasets will be available athttps://vlislab22.github.io/EOLO/

Chasing Day and Night: Towards Robust and Efficient All-Day Object Detection Guided by an Event Camera