Get object orientation without training and without 3D model with PIZZA

Survey of vision transformers for action recognition

Survey of transformers for remote sensing

Improve video retrieval with text by comparing coarse and fine features with X-CLIP

Better segmentation by using the distribution of categories with MCIBI++

Get depth and new views from one image by coding for shape, appearance, pose with im2nerf

Self-supervised segmentation by students using transformers and CNN with TCC

Complete point clouds with missing data by coarse to local method with SPCNet

Improve 3D object reconstruction by using point and normal features together with PCDNF

3D object retrieval using hand sketch, text, and image inputs with Schlachter

Survey of 3D mesh denoising using geometric and learning methods

Better 3D object reconstruction with volume representations with SRDF

Improve segmentation of unknown objects by using a single stage with SOIS

Fix noisy dark image and change after the fact camera viewpoint, focus, exposure, tones with RawNeRF

Better object detection with semi-supervised training by using offline out-of-domain with Liu

Improve pose estimation for small-scale persons using head and body centers with Cheng

Survey of semi-supervised and unsupervised deep learning for computer vision

Survey of real-time object detection networks

Turn any human pose estimation using images to use video for better performance with simple PoseBERT

Survey of synthetic data in human analysis