D. Tao

Publications1,164
h-index122
Citations54,144
Highly Influential Citations3,478
Claim Author Page
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • X. Li
  • 633 Publications • 31,309 Citations
  • Shuicheng Yan
  • 818 Publications • 52,250 Citations
  • Xinbo Gao
  • 613 Publications • 14,000 Citations
  • X. Tang
  • 495 Publications • 64,083 Citations
  • Publications
  • Influence
DehazeNet: An End-to-End System for Single Image Haze Removal
TLDR
In this paper, we propose a trainable end-to-end system called DehazeNet, for medium transmission estimation. Expand
Deep Ordinal Regression Network for Monocular Depth Estimation
TLDR
We introduce a spacing-increasing discretization (SID) strategy to discretize depth and recast depth network learning as an ordinal regression problem, which achieves state-of-the-art results on three challenging benchmarks. Expand
MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object tracking
TLDR
We propose MUlti-Store Tracker (MUSTer), a dual-component approach consisting of short- and long-term memory stores to process target appearance memories. Expand
GoDec: Randomized Lowrank & Sparse Matrix Decomposition in Noisy Case
TLDR
We develop "Go Decomposition" (GoDec) to efficiently and robustly estimate the low-rank part L and the sparse part S of a matrix X = L + S + G with noise G. Expand
Benchmarking Single-Image Dehazing and Beyond
TLDR
We present a comprehensive study and evaluation of existing single-image dehazing algorithms, using a large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single-Image DEhazing (RESIDE). Expand
General Tensor Discriminant Analysis and Gabor Features for Gait Recognition
TLDR
We use human gait recognition to validate the proposed GTDA. Expand
NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results
TLDR
This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results. Expand
A Survey on Multi-view Learning
TLDR
We review a number of representative multi-view learning algorithms in different areas and classify them into three groups: 1) co-training, 2) multiple kernel learning, and 3) subspace learning. Expand
Bregman Divergence-Based Regularization for Transfer Subspace Learning
  • Si Si, D. Tao, Bo Geng
  • Computer Science
  • IEEE Transactions on Knowledge and Data…
  • 1 July 2010
TLDR
In this paper, we present a family of subspace learning algorithms based on a new form of regularization, which transfers the knowledge gained in training samples to testing samples in the selected subspace. Expand
Multi-modal Factorized Bilinear Pooling with Co-attention Learning for Visual Question Answering
TLDR
We develop a Multi-modal Factorized Bilinear (MFB) pooling approach to efficiently and effectively combine multimodal features, which results in superior performance for VQA compared with other bilinear pooling approaches. Expand
...
1
2
3
4
5
...