Computer vision engineer
Summary
Research Assistant, Media Communications Lab, USC
Designed and implemented a pose invariant light-weight model for 3d Point cloud object classification.
Achieved 84% accuracy on unseen data with inference time less than 0.5sec and model size of 900kb.
Publications
S3I-POINTHOP: SO(3)-INVARIANT POINTHOP FOR 3D POINT CLOUD CLASSIFICATION (ICASSP 2023) Contact
Expectations
In my new role, I am looking for an opportunity to apply my skills and knowledge in computer vision to solve challenging problems and contribute to the development of innovative solutions. I am passionate about leveraging technology to make a positive impact on society, and I am eager to work with a team that shares this goal. I hope to be able to collaborate with talented and driven individuals who are committed to pushing the boundaries of what is possible in the field of computer vision. Additionally, I am looking for a role that provides opportunities for continued learning and growth, both in terms of technical skills and professional development. I am excited to take on new challenges and expand my knowledge in areas such as machine learning, data science, and software development. Ultimately, I am seeking a role that aligns with my career aspirations and allows me to make meaningful contributions to the organization and the broader community
Employment Preferences
Relocation destinations:
- United States
Expected Base Salary
**,000 USD
Academic Degree
Experience
Total Professional Experience
Startup Experience
Big-Tech Companies
Enterprise Experience
Skills
- Image Segmentation
- Object Detection-Classification
- Pose Estimation
- 3d Point Cloud Classification
- Camera Calibration
- OpenCV
- PyTorch
- PCL
- Python
- C++
- MATLAB
- LabView
- Arduino
- Data Structures
- Algorithms
- GIT
- Unit Testing
- Linux
- High Performance Computing
- SLURM Jobs
- Remote Clusters
- Multi-threading
- GPU Programming
Contacts are hidden
Send a connection request to the candidate to get their contact details.
Contact Candidate
