Improve human motion estimate in video using physics with HUND+SO+GT+Dynamics

Explain image classifier by showing features in source and target domains with XSDA-Net

Enhance dark images in new untrained domain by simulating image pipeline for training

Classify small images accurately using little memory and CPU with ImageSig

Better object segmentation of unknown objects using region awareness with RAML

3D object reconstruction using a few views despite noisy camera poses with FvOR

Improve 3D object reconstruction using unsupervised learning on image collection with TARS

3D shape, segmentation, appearance, and object poses from images using neural fields with PNF

Better segment aerial photo by learning multi-resolution features with IFWM

Count crowds accurately even after add new domain with FLCB

Survey of surface reconstruction from point clouds

Get orientation of multiple objects in real-time with YOLOPose

Locate where in the world an image was taken with TransLocator

Track and segment occluded objects in video with occlusions-4d

Improved object orientation by doing keypoint correspondences iteratively with BD-PnP

Better weakly supervised object detection by using absolutely wrong data with NDI-WSOD

Highlight objects in image that need attention when driving with driver-gaze-yolov5

Convert nighttime infrared into daytime visible video with ROMA

Match an image taken at ground-level to an aerial photo with TransGCNN

Get orientation of object without an object model with Gen6D