research
∙
05/25/2023
EgoHumans: An Egocentric 3D Multi-Human Benchmark
We present EgoHumans, a new multi-view multi-human video benchmark to ad...
share
research
∙
10/08/2022
Sequential Ensembling for Semantic Segmentation
Ensemble approaches for deep-learning-based semantic segmentation remain...
research
∙
03/27/2022
Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking
Multi-Object Tracking (MOT) has rapidly progressed with the development ...
research
∙
03/24/2022
Occluded Human Mesh Recovery
Top-down methods for monocular human mesh recovery have two stages: (1) ...
research
∙
04/01/2021
RePOSE: Real-Time Iterative Rendering and Refinement for 6D Object Pose Estimation
The use of iterative pose refinement is a critical processing step for 6...
research
∙
01/27/2021
Multi-Hypothesis Pose Networks: Rethinking Top-Down Pose Estimation
A key assumption of top-down human pose estimation approaches is their e...
research
∙
12/03/2018
VADRA: Visual Adversarial Domain Randomization and Augmentation
We address the issue of learning from synthetic domain randomized data e...
research
∙
11/14/2018