• Publications
  • Influence
DeepSkeleton: Learning Multi-Task Scale-Associated Deep Side Outputs for Object Skeleton Extraction in Natural Images
This paper presents a novel fully convolutional network with multiple scale-associated side outputs to address object skeleton extraction from natural images, and achieves promising results on two skeleton extraction datasets, and significantly outperforms other competitors.
Deep Hough Transform for Semantic Line Detection
The problem of detecting semantic lines in the spatial domain is transformed to spotting individual points in the parametric domain, making the post-processing steps, i.e., non-maximal suppression, more efficient.
Deep Differentiable Random Forests for Age Estimation
Two Deterministic Annealing processes are introduced into the learning of the split and leaf nodes, respectively, to avoid poor local optima and obtain better estimates of tree parameters free of initial values.
Dependency Aware Filter Pruning
The norm-based importance estimation is further developed by taking the dependency between the adjacent layers into consideration and a novel mechanism to dynamically control the sparsity-inducing regularization so as to achieve the desired sparsity is proposed.
Deep Hough Transform for Semantic Line Detection.
This paper incorporates the classical Hough transform technique into deeply learned representations and proposes a one-shot end-to-end learning framework for line detection, by parameterizing lines with slopes and biases to translate deep representations into the parametric domain, in which it performs line detection.
Model-Agnostic Structured Sparsification with Learnable Channel Shuffle
A model-agnostic structured sparsification method for efficient network compression that automatically induces structurally sparse representations of the convolutional weights, thereby facilitating the implementation of the compressed model with the highly-optimized group convolution.
This is the title of an example SEG abstract using Microsoft Word 11-point bold type
Ideal datasets for stratigraphic interpretation have high resolution, high level of continuity, high S/N, and high amplitude fidelity. In the deep water Gulf of Mexico (DW GOM), detailed geologic
The elimination of cross-terms based on the fusion of time-frequency features and its application in machine fault diagnosis
Time-frequency representation, as a commonly method for non-stationary signals processing, includes linear time-frequency representation and bilinear time-frequency representation. Though low in