ANMG

Angel Martínez-González

I am a computer vision scientist at Amazon Berlin. I received my PhD from the Doctoral School of Electrical Engineering at École Polytechnique Fédérale de Lausanne (EPFL), Switzerland under the supervision of Dr. Jean-Marc Odobez in the Perception Group at Idiap Research Institute. Under the course of my PhD I interned at Google and Amazon working with deep learning and computer vision.

I obtained a MSc degree in Computer Science at Matematical Research Center (CIMAT) during which I did a research internship at the Laboratoire d'Analyse et d'Architecture des Systèmes (LAAS-CNRS). Before that, I was a SWE at Intel.

Email / CV / Google Scholar

Publications

I'm interested in computer vision, machine learning, and applications for Human-Computer Interaction.

	Pose Transformers: Human Motion Prediction with Non-Autoregressive Transformers Angel Martínez-González, Michael Villamizar, Jean-Marc Odobez IEEE/CVF International Conference on Computer Vision , 2021 paper / project page / poster A new non-autoregressive Transformer architecture to predict 3D human motion and activities.
	An Efficient Image-to-Image Translation HourGlass-based Architecture for Object Pushing Policy Learning Marco Ewerton, Angel Martínez-González, Jean-Marc Odobez IEEE/RSJ International Conference on Intelligent Robots and Systems, 2021 paper / project page An object pushing policy based using an Hourglass-based CNN architecture.
	Residual Pose: A Decoupled Approach for Depth-Based 3D Human Pose Estimation Angel Martínez-González, Michael Villamizar, Olivier Canévet, Jean-Marc Odobez IEEE/RSJ International Conference on Intelligent Robots and Systems, 2020 paper / project page / video A new 3D pose estimation method that relies in residual pose modeling suitable for multi-person scenarios.
	WatchNet++: Efficient and accurate depth-based network for detecting people attacks and intrusion Michael Villamizar, Angel Martínez-González, Olivier Canévet, Jean-Marc Odobez Machine Vision and Applications (MVAP), 2020 paper / video / BibTex Detecting people from top-view images for atack detection in security airlocks
	Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimation Angel Martínez-González, Michael Villamizar, Olivier Canévet, Jean-Marc Odobez IEEE Transactions on Circuits and Systems for Video Technology, 2020 (accepted Nov. 2019) paper / data / project page Leveraging lightweight CNN, domain adaptation and knowledge distillation for 2D pose estimation.
	Investigating Depth Domain Adaptation for Efficient Human Pose Estimation Angel Martínez-González, Michael Villamizar, Olivier Canévet, Jean-Marc Odobez ECCV Workshop on Human Behavior Understanding, 2018 paper / data Investigates domain adaptation to close the covariance shift gap from learning with synthetic data.
	WatchNet: Efficient and Depth-based Network for People Detection in Video Surveillance Systems Michael Villamizar, Angel Martínez-González, Olivier Canévet, Jean-Marc Odobez IEEE Int. Conf. on Advanced Video and Signal-Based Processing (AVSS), 2018 paper People detection from top-to-down facing images for security systems..
	Real-time Convolutional Networks for Depth-based Human Pose Estimation Angel Martínez-González, Michael Villamizar, Olivier Canévet, Jean-Marc Odobez IEEE/RSJ International Conference on Intelligent Robots and Systems, 2018 paper Introducing a new CNN architecture for real time pose estimation from synthetic depth images.
	Real Time Face Detection Using Neural Networks Angel Martínez-González, Victor Ayala Ramirez IEEE Mexican International Conference on Artificial Intelligence, 2011 paper Skin color-based searching and face detection with neural networks.

Cool Projects

	DepthHuman: A tool for depth image synthesis for human pose estimation We have created the DIH dataset a large scale dataset of synthetic depth images with annotations for depth-based 2D pose estimation with this tool. code / dataset
	ViZDoom and Reinforcement Learning Solving navigation tasks in a 3d FPS game environment for autonomous agents with deep reinforcement learning methods. project page
	Montecarlo Localization. When an autonomous drone needs to localize itself in a map, motion models and particle filters come to place to save the day. code
	3D object culling methods for virtual reality gaming (collaboration with GCS). GameCoder Studios (GCS)

Amazing profile page!