Biography
Dr. João Henriques is a Research Fellow of the Royal Academy of Engineering, working at the Visual Geometry Group (VGG) at the University of Oxford. His research focuses on computer vision and deep learning, with the goal of making machines more perceptive, intelligent and capable of helping people. He created the KCF and SiameseFC visual object trackers, which won the highly competitive VOT Challenge twice, and are widely deployed in consumer hardware, from Facebook apps to commercial drones. His research spans many topics: robot mapping and navigation, including reinforcement learning and 3D geometry; multi-agent cooperation and "friendly" AI; as well as various forms of learning, from self-supervised, causal, and meta-learning, including optimisation theory. For the latest research please refer to: https://www.robots.ox.ac.uk/~joao/
Most Recent Publications
A sound approach: using large language models to generate audio descriptions for egocentric text-audio retrieval
A sound approach: using large language models to generate audio descriptions for egocentric text-audio retrieval
N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields
N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields
SCENES: Subpixel Correspondence EstimationWith Epipolar Supervision
SCENES: Subpixel Correspondence EstimationWith Epipolar Supervision
Select to perfect: imitating desired behavior from large multi-agent data
Select to perfect: imitating desired behavior from large multi-agent data
LoCUS: Learning Multiscale 3D-consistent Features from Posed Images
LoCUS: Learning Multiscale 3D-consistent Features from Posed Images
Most Recent Publications
A sound approach: using large language models to generate audio descriptions for egocentric text-audio retrieval
A sound approach: using large language models to generate audio descriptions for egocentric text-audio retrieval
N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields
N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields
SCENES: Subpixel Correspondence EstimationWith Epipolar Supervision
SCENES: Subpixel Correspondence EstimationWith Epipolar Supervision
Select to perfect: imitating desired behavior from large multi-agent data
Select to perfect: imitating desired behavior from large multi-agent data
LoCUS: Learning Multiscale 3D-consistent Features from Posed Images
LoCUS: Learning Multiscale 3D-consistent Features from Posed Images
