We are looking for an exceptionally talented Postdoctoral Research Fellow to join our interdisciplinary team at the forefront of machine learning, computer vision, 3D human understanding, motion prediction, and video understanding. This position is hosted by the Stanford Translational AI (STAI) Lab in collaboration with the Stanford Vision and Learning (SVL) Lab within the Computer Science Department. These dynamic research groups are renowned for their groundbreaking contributions to artificial intelligence, computer vision, and deep learning, particularly in human motion and video understanding.
Project Description
The successful candidate will work on cutting-edge projects aimed at building 3D human pose estimation/mesh reconstruction, multimodal motion generation (text/audio driven) and multimodal video understanding (text/audio). The postdoc will contribute to the development of advanced AI models that enable a deeper understanding of human motion and behavior in real-world environments. These models will be applied to various domains such as healthcare, human-computer interaction, sports analysis, and entertainment.
Key projects may involve:
-
Developing motion foundation models for 3D human motion generation, pose estimation, and human activity recognition.
-
Advancing video understanding models for tasks such as action recognition, scene understanding, and human-object interaction.
-
Leveraging multi-modal data (e.g., video, motion capture, depth sensors) to build robust, generalizable models of human behavior and interactions.
-
Exploring novel self-supervised and transfer learning techniques to improve the scalability and adaptability of these models.
Key Responsibilities
-
Conduct research in machine learning, computer vision, 3D human understanding, and video analysis.
-
Develop and implement algorithms for 3D human pose estimation, motion generation, and video understanding.
-
Design and train large-scale motion foundation models using multi-modal datasets.
-
Collaborate with a team of researchers and industry partners to apply these models in domains such as healthcare, robotics, and human-computer interaction.
-
Mentor graduate students (Ph.D. and MSc) in related research areas.
-
Publish findings in top-tier AI and computer vision conferences and journals.
-
Contribute to grant writing and proposal development to secure research funding.
Qualifications
-
Ph.D. in Computer Science, Electrical Engineering, Robotics, or a related field.
-
Proven track record of publications in high-impact journals and conferences including CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, and Nature.
-
Strong background in machine learning, computer vision, 3D human understanding, and video analysis.
-
Proficiency in Python, C++, or similar languages and experience with deep learning frameworks such as PyTorch or TensorFlow.
-
Experience with large-scale datasets and training motion or video-based models.
-
Excellent communication skills, both written and verbal, with a proven ability to work independently and collaboratively.
Benefits
-
Competitive salary and benefits package.
-
Access to state-of-the-art facilities and computational resources at Stanford.
-
Opportunities for professional development and international collaboration with leading experts in the field.
-
Participation in international conferences and workshops, fostering academic and industrial partnerships.
-
Working Environment. As a postdoctoral researcher at Stanford University, you will be part of a vibrant intellectual community with access to world-class research facilities. Stanford offers numerous opportunities for interdisciplinary collaboration, professional development, and innovation. The university's global network of leading experts and industry partners will enhance your career growth and research impact.