research
∙
06/01/2023
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
Modern hierarchical vision transformers have added several vision-specif...
share
research
∙
08/04/2022
Occupancy Planes for Single-view RGB-D Human Reconstruction
Single-view RGB-D human reconstruction with implicit functions is often ...
research
∙
04/07/2022
Total Variation Optimization Layers for Computer Vision
Optimization within a layer of a deep-net has emerged as a new direction...
research
∙
04/07/2022
Equivariance Discovery by Learned Parameter-Sharing
Designing equivariance as an inductive bias into deep-nets has been a pr...
research
∙
05/18/2021
SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data
Extracting detailed 3D information of objects from video data is an impo...
research
∙
10/31/2019
Chirality Nets for Human Pose Regression
We propose Chirality Nets, a family of deep nets that is equivariant to ...
research
∙
04/11/2019
Max-Sliced Wasserstein Distance and its use for GANs
Generative adversarial nets (GANs) and variational auto-encoders have si...
research
∙
09/04/2018
Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation
Unsupervised video segmentation plays an important role in a wide variet...
research
∙
09/04/2018
VideoMatch: Matching based Video Object Segmentation
Video object segmentation is challenging yet important in a wide variety...
research
∙
03/29/2018
MaskRNN: Instance Level Video Object Segmentation
Instance level video object segmentation is an important technique for v...
research
∙
12/13/2014