Seminar: Self-Supervised Frameworks for 3D human Pose Estimation

NAVER LABS Europe (Grenoble, France) is the biggest industrial AI research lab in France with fundamental and applied research in the fields of machine learning and optimization, computer vision, natural language processing and human robot interaction. The main area of application  is  AI for Robotics where they work closely with  NAVER LABS Korea the R&D subsidiary of NAVER, Korea’s leading internet company. NAVER LABS is responsible for creating future technology in robotics, AI, autonomous driving, 3D/HD mapping and AR.LinkedIn-Bluesky

NAVER LABS Europe

NAVER LABS Europe seminar. Speaker: Jogendra, PhD student at Video Analytics Lab, CDS, Indian Institute of Science.

Title: Self-Supervised Frameworks for 3D human Pose EstimationAbout the speaker: Jogendra is wrapping up his PhD at Video Analytics Lab, CDS, Indian Institute of Science. He is broadly interested in self-supervised learning, domain adaptation, and their application to computer vision problems like 3D human pose estimation, semantic segmentation, etc. He is a recipient of several PhD fellowships, like Wipro PhD fellowship, Qualcomm Innovation Fellowship, and the Google PhD fellowship. He has worked as a Research Intern at Facebook Reality Labs during Fall 2021. He has authored papers in several top-tier venues such as CVPR, ICCV, ECCV, NeurIPS, AAAI, and WACV. He has also served as a reviewer in several top-tier conferences and journals (T-PAMI and IJCV) and has received Outstanding Reviewer awards at CVPR 2020 and NeurIPS 2021.********************************************************Abstract: Available 3D human pose estimation approaches leverage different forms of strong (2D/3D pose) or weak (multi-view or depth) paired supervision. Barring synthetic or in-studio domains, acquiring such supervision for each new target environment is highly inconvenient. To this end, we cast 3D pose learning as a self-supervised adaptation problem that aims to transfer the task knowledge from a labeled source domain to a completely unlabeled target. The main challenge is determining proper learning objectives in order to obtain supervision from the data itself. In one of our works, the key contribution is the effective use of new inter-entity relationships to discern the co-salient foreground appearance and thereby the corresponding pose from just a pair of images having diverse backgrounds. While in another work, we achieve the same by distilling well-formed latent non-local relations in the pose and motion space. Further, in a recent work, we propose a novel way to perform self-adaptive 3D human pose estimation by enabling uncertainty estimation. We develop learning techniques to make the model behave differently for the in-domain and out-of-domain scenarios. Later, the same instigated behavior is used to devise effective adaptation objectives. The ability to discern out-of-domain samples allows a model to assess when to perform re-adaptation while deployed in a continually changing environment. Such solutions are in high demand for enabling effective real-world deployment across various industries, from virtual and augmented reality to gaming and healthcare applications.

Our {communityGuidelinesLink} describe the sort of content we prohibit on Eventbrite. If you suspect an event may be in violation, you can report it to us so we can investigate.

To report other categories of prohibited or illegal content, submit {link}

Seminar: Self-Supervised Frameworks for 3D human Pose Estimation

More events from NAVER LABS Europe

Discover more events from NAVER LABS Europe, from Science & Tech to other experiences you might love.

Still looking for the right event?

Explore all online events to browse and filter by date, category, and more.

Seminar: Self-Supervised Frameworks for 3D human Pose Estimation

More events from NAVER LABS Europe

Discover more events from NAVER LABS Europe, from Science & Tech to other experiences you might love.

You might also like...

Browse more events with different dates, prices, and formats to find your next great experience.

Still looking for the right event?

Explore all online events to browse and filter by date, category, and more.