UDAPose improves low-light human pose estimation by synthesizing realistic images via DHF and LCIM modules and dynamically balancing image cues with pose priors using DCA, yielding AP gains of 10.1 and 7.4 over prior methods.
Microsoft COCO: Common objects in context
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
YOLO-NAS-Bench samples 1500 YOLO architectures trained on COCO-mini, trains a LightGBM surrogate with self-evolving selection to reach R2 of 0.815, and uses it to evolve architectures outperforming official YOLOv8-12 baselines at similar latency.
citing papers explorer
-
UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimation
UDAPose improves low-light human pose estimation by synthesizing realistic images via DHF and LCIM modules and dynamically balancing image cues with pose priors using DCA, yielding AP gains of 10.1 and 7.4 over prior methods.
-
YOLO-NAS-Bench: A Surrogate Benchmark with Self-Evolving Predictors for YOLO Architecture Search
YOLO-NAS-Bench samples 1500 YOLO architectures trained on COCO-mini, trains a LightGBM surrogate with self-evolving selection to reach R2 of 0.815, and uses it to evolve architectures outperforming official YOLOv8-12 baselines at similar latency.