Ciliary-DETR adds a learnable scale predictor and parametric loss objectives to enable test-time image scale adjustment for object detection in a single forward pass.
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 2verdicts
UNVERDICTED 2representative citing papers
A diagnostic study shows that two-stage HOI models fail differently across scene configurations like multi-person and rare interactions, revealing that aggregate benchmark accuracy does not imply robust visual reasoning.
citing papers explorer
-
Visual Accommodation: Rethinking Image Scale as a Learnable Variable for Object Detection
Ciliary-DETR adds a learnable scale predictor and parametric loss objectives to enable test-time image scale adjustment for object detection in a single forward pass.
-
A Study of Failure Modes in Two-Stage Human-Object Interaction Detection
A diagnostic study shows that two-stage HOI models fail differently across scene configurations like multi-person and rare interactions, revealing that aggregate benchmark accuracy does not imply robust visual reasoning.