• Publications
  • Influence
Indoor Segmentation and Support Inference from RGBD Images
TLDR
The goal is to parse typical, often messy, indoor scenes into floor, walls, supporting surfaces, and object regions, and to recover support relationships, to better understand how 3D cues can best inform a structured 3D interpretation.
KinectFusion: Real-time dense surface mapping and tracking
We present a system for accurate real-time mapping of complex and arbitrary indoor scenes in variable lighting conditions, using only a moving low-cost depth camera and commodity graphics hardware.
Highly accurate protein structure prediction with AlphaFold
TLDR
This work validated an entirely redesigned version of the neural network-based model, AlphaFold, in the challenging 14th Critical Assessment of protein Structure Prediction (CASP14)15, demonstrating accuracy competitive with experiment in a majority of cases and greatly outperforming other methods.
KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera
TLDR
Novel extensions to the core GPU pipeline demonstrate object segmentation and user interaction directly in front of the sensor, without degrading camera tracking or reconstruction, to enable real-time multi-touch interactions anywhere.
Relational inductive biases, deep learning, and graph networks
TLDR
It is argued that combinatorial generalization must be a top priority for AI to achieve human-like abilities, and that structured representations and computations are key to realizing this objective.
Robust Higher Order Potentials for Enforcing Label Consistency
TLDR
This paper proposes a novel framework for labelling problems which is able to combine multiple segmentations in a principled manner based on higher order conditional random fields and uses potentials defined on sets of pixels generated using unsupervised segmentation algorithms.
A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories
TLDR
A new framework for evaluating story understanding and script learning: the `Story Cloze Test’, which requires a system to choose the correct ending to a four-sentence story, and a new corpus of 50k five- Sentence commonsense stories, ROCStories, to enable this evaluation.
Associative hierarchical CRFs for object class image segmentation
TLDR
This work proposes a hierarchical random field model, that allows integration of features computed at different levels of the quantisation hierarchy, and evaluates its efficiency on some of the most challenging data-sets for object class segmentation, and shows it obtains state-of-the-art results.
Instructing people for training gestural interactive systems
TLDR
The results of the qualitative and quantitative analysis indicate that the choice of modality has a significant impact on the performance of the learnt gesture recognition system; particularly in terms of correctness and coverage.
Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
TLDR
This paper motivates the use of adversarial risk as an objective, although it cannot easily be computed exactly, and frames commonly used attacks and evaluation metrics as defining a tractable surrogate objective to the true adversarialrisk.
...
...