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
N2F2: hierarchical scene understanding with nested neural feature fields
N2F2: hierarchical scene understanding with nested neural feature fields
Contrastive lift: 3D object instance segmentation by slow-fast contrastive fusion
Contrastive lift: 3D object instance segmentation by slow-fast contrastive fusion
Dissecting Temporal Understanding in Text-to-Audio Retrieval
Dissecting Temporal Understanding in Text-to-Audio Retrieval
HelloFresh: LLM evaluations on streams of real-world human editorial actions across X community notes and Wikipedia edits
HelloFresh: LLM evaluations on streams of real-world human editorial actions across X community notes and Wikipedia edits
Neural fields for co-reconstructing 3D objects from incidental 2D data
Neural fields for co-reconstructing 3D objects from incidental 2D data
Most Recent Publications
N2F2: hierarchical scene understanding with nested neural feature fields
N2F2: hierarchical scene understanding with nested neural feature fields
Contrastive lift: 3D object instance segmentation by slow-fast contrastive fusion
Contrastive lift: 3D object instance segmentation by slow-fast contrastive fusion
Dissecting Temporal Understanding in Text-to-Audio Retrieval
Dissecting Temporal Understanding in Text-to-Audio Retrieval
HelloFresh: LLM evaluations on streams of real-world human editorial actions across X community notes and Wikipedia edits
HelloFresh: LLM evaluations on streams of real-world human editorial actions across X community notes and Wikipedia edits
Neural fields for co-reconstructing 3D objects from incidental 2D data
Neural fields for co-reconstructing 3D objects from incidental 2D data
