More details to appear before the conference.

Papers

Cascade-DETR: Delving into High-Quality Universal Object Detection
We jointly tackle the generalization to diverse domains and localization accuracy by proposing the Cascade Attention layer.
[Code] [Paper]

Dual Aggregation Transformer for Image Super-Resolution
[Webpage][Code][Paper]

3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection Transformers
[Webpage] [Code] [Paper]

Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving
[Webpage] [Code] [Paper]

R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras
[Webpage] [Code] [Paper]

MolGrapher: Graph-based Visual Recognition of Chemical Structures
[Webpage] [Code] [Paper]

DARTH: Holistic Test-time Adaptation for Multiple Object Tracking
[Webpage] [Code] [Paper]

Video OWL-ViT: Temporally-consistent open-world localization in video
[Webpage] [Code] [Paper]

Organized Workshop

1st Workshop on Visual Continual Learning
[Website]