Recurrent models reach 0.285 mAP50 from scratch and 0.329 mAP50 with GEN1 pretraining on MTevent, delivering a 9.6% gain over the 0.260 non-recurrent baseline while showing domain-specific pretraining effects.
Evimo2: An event camera dataset for motion segmentation, optical flow, structure from motion, and visual inertial odometry in indoor scenes with monocular or stereo algorithms,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Benchmarking Recurrent Event-Based Object Detection for Industrial Multi-Class Recognition on MTevent
Recurrent models reach 0.285 mAP50 from scratch and 0.329 mAP50 with GEN1 pretraining on MTevent, delivering a 9.6% gain over the 0.260 non-recurrent baseline while showing domain-specific pretraining effects.