BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth
2017 · 852 citations
https://doi.org/10.1109/iccv.2017.413
M
Mahdi Rad
Claim or correct this author profile
Claim this profile or suggest corrections to the name, affiliation, bio, photo, or paper titles. Approved changes appear as verified CitedEvidence overlays.
52
Papers
2.0K
Citations
14
h-index
17
i10-index
Mahdi Rad is an academic researcher from Microsoft (Switzerland). The author has contributed to research in topics: Human Pose and Action Recognition & Robot Manipulation and Learning & Robotics and Sensor-Based Localization. The author has an h-index of 14, co-authored 45 publications.
ORCID: 0000-0002-4011-4729Papers by this author
worksKeypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation
2022 · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 149 citations
https://doi.org/10.1109/cvpr52688.2022.01081
HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World
2023 · 34 citations
https://doi.org/10.1109/iccv51070.2023.01854
Upscaling mesoscopic simulation results to develop constitutive relations for macroscopic modeling of equiaxed dendritic solidification
2019 · Materialia · 9 citations
https://doi.org/10.1016/j.mtla.2019.100231
Research topics
topicsChat about Author
Papers
Chat
Click to start Chat