• Publications
  • Influence
Aggregated Residual Transformations for Deep Neural Networks
TLDR
We present a simple, highly modularized network architecture for image classification. Expand
  • 2,880
  • 553
  • PDF
Holistically-Nested Edge Detection
TLDR
We develop a new edge detection algorithm that addresses two important issues in this long-standing vision problem: (1) holistic image training and prediction; and (2) multi-scale and multi-level feature learning. Expand
  • 1,473
  • 306
  • PDF
Integral Channel Features
TLDR
We study the performance of ‘integral channel features’ for image classification tasks, focusing in particular on pedestrian detection. Expand
  • 1,136
  • 153
  • PDF
Deeply Supervised Salient Object Detection with Short Connections
TLDR
We propose a new saliency method by introducing short connections to the skip-layer structures within the HED architecture. Expand
  • 539
  • 141
  • PDF
Similarity network fusion for aggregating data types on a genomic scale
TLDR
We used SNF to combine mRNA expression, DNA methylation and microRNA (miRNA) expression data for five cancer data sets. Expand
  • 687
  • 130
  • PDF
Detecting texts of arbitrary orientations in natural images
TLDR
In this paper, we propose a system which detects texts of arbitrary orientations in natural images. Expand
  • 518
  • 95
  • PDF
Probabilistic boosting-tree: learning discriminative models for classification, recognition, and clustering
  • Zhuowen Tu
  • Computer Science
  • Tenth IEEE International Conference on Computer…
  • 17 October 2005
TLDR
In this paper, a new learning framework - probabilistic boosting-tree (PBT), is proposed for learning two-class and multi-class discriminative models. Expand
  • 479
  • 76
  • PDF
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
TLDR
We show that it is possible to replace many of the 3D convolutions at the lowest layers of the network (the ones closest to the pixels), and use 2D convolution for the higher layers. Expand
  • 311
  • 74
  • PDF
Deeply-Supervised Nets
TLDR
Our proposed deeply-supervised nets (DSN) method simultaneously minimizes classification error while making the learning process of hidden layers direct and transparent. Expand
  • 1,102
  • 72
  • PDF
Auto-Context and Its Application to High-Level Vision Tasks and 3D Brain Image Segmentation
  • Zhuowen Tu, X. Bai
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1 October 2010
TLDR
The notion of using context information for solving high-level vision and medical image segmentation problems has been increasingly realized in the field. Expand
  • 506
  • 66
  • PDF