The image processing group at the Multimedia Technologies Unit focuses on computer vision technologies for image, video, and 3D multi-view content. The group has extensive experience in various areas such as object and feature detection, object segmentation and tracking, natural video alpha-matting, 2D-3D image and video inpainting, depth estimation, and multi-view 3D reconstruction. Latest applied activities are focused on solving multiple challenges under deep learning paradigms, such as object detection, 360 depth estimation, image super-resolution, food and fashion-style multi-label classification, cross-modal learning, or conditional generative models.
Eurecat wishes to incorporate into its Area of MULTIMEDIA TECHNOLOGY located in Barcelona a COMPUTER VISION RESEARCHER ON AI FOR MULTIMEDIA APPLICATIONS .
FUNCTIONS AND RESPONSIBILITIES
* R&D tasks solving various Computer Vision problems using Deep Learning neural network architectures.
* Participation in different innovation projects with multimedia components focusing on various use cases and sectors in the field of Computer Vision and Deep Learning (object detection, semantic segmentation, gesture recognition, etc).
* Reporting and presenting results derived from R&D tasks.
* Collaboration in the drafting of proposals and execution of private industry projects.
KNOWLEDGE AND STUDIES
* Degree in Computer Science, Mathematics, Physics, or related field.
* MSc or PhD in Computer Vision or related field.
EXPERIENCE
* Academic or professional experience in research projects in the field of computer vision.
* Depth working knowledge of Deep Learning frameworks (PyTorch, TensorFlow).
* Advanced skills in Python, writing clean, maintainable code.
* Other programming languages such as C++ or frameworks such as OpenCV will be valued positively.
* Linux and Git are in your daily toolbox.
* Valuable experience in public and private research projects.
LANGUAGES
* Desirable: Spanish or Catalan
#J-18808-Ljbffr