• Publications
  • Influence
Generative Image Inpainting with Contextual Attention
TLDR
This work proposes a new deep generative model-based approach which can not only synthesize novel image structures but also explicitly utilize surrounding image features as references during network training to make better predictions.
Interactive Facial Feature Localization
TLDR
An improvement to the Active Shape Model is proposed that allows for greater independence among the facial components and improves on the appearance fitting step by introducing a Viterbi optimization process that operates along the facial contours.
Label Consistent K-SVD: Learning a Discriminative Dictionary for Recognition
TLDR
A label consistent K-SVD (LC-KSVD) algorithm to learn a discriminative dictionary for sparse coding and introduces a new label consistency constraint called "discriminative sparse-code error" to enforce discriminability in sparse codes during the dictionary learning process.
Free-Form Image Inpainting With Gated Convolution
TLDR
The proposed gated convolution solves the issue of vanilla convolution that treats all input pixels as valid ones, generalizes partial convolution by providing a learnable dynamic feature selection mechanism for each channel at each spatial location across all layers.
Learning a discriminative dictionary for sparse coding via label consistent K-SVD
TLDR
A label consistent K-SVD (LC-KSVD) algorithm to learn a discriminative dictionary for sparse coding is presented, which learns a single over-complete dictionary and an optimal linear classifier jointly and yields dictionaries so that feature points with the same class labels have similar sparse codes.
MAttNet: Modular Attention Network for Referring Expression Comprehension
TLDR
This work proposes to decompose expressions into three modular components related to subject appearance, location, and relationship to other objects, which allows for flexibly adapt to expressions containing different types of information in an end-to-end framework.
A convolutional neural network cascade for face detection
TLDR
This work proposes a cascade architecture built on convolutional neural networks (CNNs) with very powerful discriminative capability, while maintaining high performance, and introduces a CNN-based calibration stage after each of the detection stages in the cascade.
Top-Down Neural Attention by Excitation Backprop
TLDR
A new backpropagation scheme, called Excitation Backprop, is proposed to pass along top-down signals downwards in the network hierarchy via a probabilistic Winner-Take-All process, and the concept of contrastive attention is introduced to make the top- down attention maps more discriminative.
Minimum Barrier Salient Object Detection at 80 FPS
TLDR
A technique based on color whitening is proposed to extend the salient object detection method to leverage the appearance-based backgroundness cue, which further improves the performance, while still being one order of magnitude faster than all the other leading methods.
Photo Aesthetics Ranking Network with Attributes and Content Adaptation
TLDR
This work proposes to learn a deep convolutional neural network to rank photo aesthetics in which the relative ranking of photo aesthetics are directly modeled in the loss function.
...
...