EvRT-DETR, a frozen RT-DETR with lightweight ConvLSTM adapters in its latent space, sets new state-of-the-art mAP on Gen1 (52.7) and 1Mpx (50.1) event-camera benchmarks.
Cubuk, Barret Zoph, Jonathon Shlens, and Quoc V
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
EvRT-DETR: Latent Space Adaptation of Image Detectors for Event-based Vision
EvRT-DETR, a frozen RT-DETR with lightweight ConvLSTM adapters in its latent space, sets new state-of-the-art mAP on Gen1 (52.7) and 1Mpx (50.1) event-camera benchmarks.