• Publications
  • Influence
Learning to Detect Salient Objects with Image-Level Supervision
  • L. Wang, H. Lu, +4 authors X. Ruan
  • Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 21 July 2017
TLDR
We leverage the observation that image-level tags provide important cues of foreground salient objects, and develop a weakly supervised learning method for saliency detection using image- level tags only. Expand
  • 256
  • 96
  • PDF
Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
TLDR
In this paper, we present Amulet, a generic aggregating multi-level convolutional feature framework for salient object detection. Expand
  • 352
  • 89
  • PDF
Learning Uncertain Convolutional Features for Accurate Saliency Detection
TLDR
In this paper, we propose a novel deep fully convolutional network model for accurate salient object detection for pixel-wise vision tasks. Expand
  • 260
  • 55
  • PDF
Least Soft-Threshold Squares Tracking
TLDR
In this paper, we propose a generative tracking method based on a novel robust linear regression algorithm. Expand
  • 267
  • 37
Online Object Tracking With Sparse Prototypes
TLDR
We propose a novel online object tracking algorithm with sparse prototypes, which exploits both classic principal component analysis (PCA) algorithms with recent sparse representation schemes for learning effective appearance models. Expand
  • 401
  • 35
  • PDF
Stepwise Metric Promotion for Unsupervised Video Person Re-identification
  • Zimo Liu, D. Wang, H. Lu
  • Computer Science
  • IEEE International Conference on Computer Vision…
  • 1 October 2017
TLDR
The intensive annotation cost and the rich but unlabeled data contained in videos motivate us to propose an unsupervised video-based person re-identification (re-ID) method. Expand
  • 109
  • 24
  • PDF
Visual Tracking via Probability Continuous Outlier Model
  • D. Wang, H. Lu
  • Mathematics, Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 23 June 2014
TLDR
We present a novel probability continuous outlier model (PCOM) to depict the continuous outliers in the linear representation model. Expand
  • 109
  • 15
  • PDF
Visual Tracking via Adaptive Spatially-Regularized Correlation Filters
TLDR
In this work, we propose a novel adaptive spatially-regularized correlation filters (ASRCF) model to simultaneously optimize the filter coefficients and the spatial regularization weight. Expand
  • 70
  • 14
Inverse Sparse Tracker With a Locally Weighted Distance Metric
TLDR
In this paper, we propose a sparsity-based tracking algorithm that is featured with two components: 1) an inverse sparse representation formulation and 2) a locally weighted distance metric. Expand
  • 93
  • 12
  • PDF
Structured Siamese Network for Real-Time Visual Tracking
TLDR
We propose a local structure learning method, which simultaneously considers the local patterns of the target and their structural relationships for more accurate target tracking. Expand
  • 101
  • 12
  • PDF