• Publications
  • Influence
Zero-Shot Recognition via Semantic Embeddings and Knowledge Graphs
TLDR
We build upon the recently introduced Graph Convolutional Network and propose an approach that uses both semantic embeddings and the categorical relationships to predict the classifiers. Expand
  • 225
  • 33
  • PDF
Compositional Video Prediction
TLDR
We present an approach for pixel-level future prediction given an input image of a scene. Expand
  • 26
  • 5
  • PDF
Object-centric Forward Modeling for Model Predictive Control
TLDR
We present an approach to learn an object-centric forward model, and show that this allows us to plan for sequences of actions to achieve distant desired goals. Expand
  • 9
  • 1
  • PDF
Numerical investigations of the haemodynamic changes associated with stent malapposition in an idealised coronary artery.
The deployment of a coronary stent near complex lesions can sometimes lead to incomplete stent apposition (ISA), an undesirable side effect of coronary stent implantation. Three-dimensionalExpand
  • 16
Practical automatic background substitution for live video
TLDR
We use a color line model to improve the Gaussian mixture model in the background cut method to obtain a binary foreground segmentation result that is less sensitive to brightness differences. Expand
  • 12
  • PDF
[Determination of organophosphorus pesticide residues in vegetables by gas chromatography using back-flush technique].
The back-flush technique was used in the determination of organophosphorus pesticide residues in vegetables by gas chromatography. The pesticide residues were extracted with acetonitrile and sodiumExpand
  • 4
A Comparative Study of Data Skew in Hadoop
TLDR
We compare six algorithms in terms of architecture and main features, core algorithms, performance metrics and evaluation methods. Expand
  • 2
Leveraging Structure for Generalization and Prediction in Visual System
Our surrounding world is highly structured. Humans have a great capacity of understanding and leveraging those structures to generalize to novel scenarios and to predict the future. The thesisExpand
A New Approach for Resource Scheduling with Deep Reinforcement Learning
TLDR
We introduce online resource scheduling algorithm DeepRM2 and the offline resource scheduling algorithms DeepRM_Off. Expand
  • 1
  • PDF
Shelf-Supervised Mesh Prediction in the Wild
TLDR
We aim to infer 3D shape and pose of object from a single image and propose a learning-based approach that can train from unstructured image collections, supervised by only segmentation outputs from off-the-shelf recognition systems (i.e. ‘shelf-supervised’). Expand