1

FQDet: Fast-converging Query-based Detector
A new query-based two-stage object detection head combining the best of both classical and DETR-based detectors, by improving the cross-attention prior with anchors and introducing the effective top-k matching scheme.
Cédric Picron, Punarjay Chakravarty, Tinne Tuytelaars
PDF Cite Code Poster
FQDet: Fast-converging Query-based Detector
Trident Pyramid Networks for Object Detection
Feature pyramids have become ubiquitous in multi-scale computer vision tasks such as object detection. Given their importance, a …
Cédric Picron, Tinne Tuytelaars
PDF Cite Code Poster
Trident Pyramid Networks for Object Detection
Category-level pose retrieval with contrastive features learnt with occlusion augmentation
Pose estimation is usually tackled as either a bin classification or a regression problem. In both cases, the idea is to directly …
Georgios Kouros, Shubham Shrivastava, Cédric Picron, Sushruth Nagesh, Punarjay Chakravarty, Tinne Tuytelaars
PDF Cite Code Poster
Category-level pose retrieval with contrastive features learnt with occlusion augmentation
What My Motion tells me about Your Pose: A Self-Supervised Monocular 3D Vehicle Detector
The estimation of the orientation of an observed vehicle relative to an Autonomous Vehicle (AV) from monocular camera data is an …
Cédric Picron, Punarjay Chakravarty, Tom Roussel, Tinne Tuytelaars
PDF Cite Code
What My Motion tells me about Your Pose: A Self-Supervised Monocular 3D Vehicle Detector