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.
Event-based vision: A survey,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Extends DEVO by exposing its estimated 3D structure as an explicit sparse point cloud, with experiments showing local consistency to EMVS at 5 cm on one sequence.
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.
-
Extending Deep Event Visual Odometry with Sparse Point-Cloud Export
Extends DEVO by exposing its estimated 3D structure as an explicit sparse point cloud, with experiments showing local consistency to EMVS at 5 cm on one sequence.