Object Detection On Dsec

Metrics

mAP

Results

Performance results of various models on this benchmark

		Paper Title
CAFR	38.0	Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection
EFNet	30.0	Event-Based Fusion for Motion Deblurring with Cross-modal Attention
RENet	29.4	RGB-Event Fusion for Moving Object Detection in Autonomous Driving
CMX	29.1	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
SPNet	27.7	Specificity-preserving RGB-D Saliency Detection
SENet	26.2	Squeeze-and-Excitation Networks
CBAM	26.1	CBAM: Convolutional Block Attention Module
DCF	25.7	Calibrated RGB-D Salient Object Detection
ECANet	25.7	ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
FPN-Fusion	24.4	Fusing Event-based and RGB camera for Robust Object Detection in Adverse Conditions
SAGate	19.6	Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation
RAMNet	17.6	Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction

0 of 12 row(s) selected.

Object Detection On Dsec

Metrics

mAP

Results

Performance results of various models on this benchmark

		Paper Title
CAFR	38.0	Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection
EFNet	30.0	Event-Based Fusion for Motion Deblurring with Cross-modal Attention
RENet	29.4	RGB-Event Fusion for Moving Object Detection in Autonomous Driving
CMX	29.1	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
SPNet	27.7	Specificity-preserving RGB-D Saliency Detection
SENet	26.2	Squeeze-and-Excitation Networks
CBAM	26.1	CBAM: Convolutional Block Attention Module
DCF	25.7	Calibrated RGB-D Salient Object Detection
ECANet	25.7	ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
FPN-Fusion	24.4	Fusing Event-based and RGB camera for Robust Object Detection in Adverse Conditions
SAGate	19.6	Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation
RAMNet	17.6	Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction

0 of 12 row(s) selected.