Better object detection by combining scores of multiple detectors using probability with DBF
Improve face recognition by using image quality to mark hard examples with AdaFace
Find location in video matching a sentence with TAN
Classification of long videos using state-space with ViS4mer
In image identify activity, box entities, and name their roles with CoFormer
Detect occluded object in image and get orientation without train using CAD model with template-pose
Segment object in image described by text more simply using SeqTR
Remove shadows in images using weak supervision with UnShadowNet
Better video object segmentation with few examples by using consistency over time with TTI
Super-resolution face image by using reference facial images with HIME
Get 3D models of multiple objects in RGB video with RayTran
Re-identify people in images using multi-stage transformers with COAT
Train object detector by labeling only 1 point of object with NSS
Fix incomplete 3D depth data by using RGB image and GAN with RDF-GAN
Scene segmentation without labeling by combining images and LiDAR with Drive&Segment
Real-time HybridNets detects traffic object, drivable area, and road lane
Object detection using one example by using scale and features with SaFT
Image segmentation without training labels by clustering features with STEGO
Real-time 3D reconstruction despite occlusion using motion prediction with OcclusionFusion
Faster and more accurate scene segmentation by being aware of the decoder stages with SFANet