Search Results for author: Shashank Tripathi

Found 3 papers, 2 papers with code

PoseNet3D: Learning Temporally Consistent 3D Human Pose via Knowledge Distillation

1 code implementation7 Mar 2020 Shashank Tripathi, Siddhant Ranade, Ambrish Tyagi, Amit Agrawal

Finally, both the teacher and the student networks are jointly fine-tuned in an end-to-end manner using temporal, self-consistency and adversarial losses, improving the accuracy of each individual network.

Ranked #14 on 3D Human Pose Estimation on MPI-INF-3DHP (using extra training data)

3D Human Pose Estimation Knowledge Distillation +1

Learning to Generate Synthetic Data via Compositing

no code implementations CVPR 2019 Shashank Tripathi, Siddhartha Chandra, Amit Agrawal, Ambrish Tyagi, James M. Rehg, Visesh Chari

The synthesizer and target networks are trained in an adversarial manner wherein each network is updated with a goal to outdo the other.

Data Augmentation Human Detection +2

Cannot find the paper you are looking for? You can Submit a new open access paper.