• Publications
  • Influence
Mask Scoring R-CNN
TLDR
In this paper, we study this problem and propose Mask Scoring R-CNN which contains a network block to learn the quality of the predicted instance masks. Expand
  • 141
  • 30
  • PDF
Genetic effects of introgression genomic components from Sea Island cotton (Gossypium barbadense L.) on fiber related traits in upland cotton (G. hirsutum L.)
The germplasm with exotic genomic components especially from Sea Island cotton (Gossypium barbadense L. Gb) is the dominant genetic resources to enhance fiber quality of upland cotton (G. hirsutumExpand
  • 33
  • 4
Genetic dissection of the introgressive genomic components from Gossypium barbadense L. that contribute to improved fiber quality in Gossypiumhirsutum L.
We crossed Luyuan343, containing the Gossypium barbadense (GB) genomic component, with Lumianyan22, a high-yielding Gossypium hirsutum (GH) variety, to evaluate the introgressive exogenous genomicExpand
  • 36
  • 2
Urban road extraction via graph cuts based probability propagation
TLDR
In this paper, we propose a graph cuts (GC) based probability propagation approach to automatically extract road network from complex remote sensing images. Expand
  • 20
  • 2
Genomic location and expression analysis of expansin gene family reveals the evolutionary and functional significance in Triticum aestivum
The plant-specific expansin proteins constitute an ancient and major gene family known to have roles in regulating diverse biological processes in plants. Although the functions of many expansinExpand
  • 7
  • 1
Fine-structured object segmentation via edge-guided graph cut with interaction simplification
TLDR
Fine-structured object segmentation is a challenging problem inobject segmentation community. Expand
  • 3
  • PDF
DeepPlane: a unified deep model for aircraft detection and recognition in remote sensing images
TLDR
We propose a unified deep CNN, called DeepPlane, to simultaneously detect the position and classify the category of aircraft in remote sensing images. Expand
  • 6
Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation
TLDR
We propose a unified framework consisting of object proposal, tracking and segmentation components for semi-supervised video object segmentation with dynamic-reference based model adaptation. Expand
  • 2
  • PDF
Fine-structured object segmentation via local and nonlocal neighborhood propagation
TLDR
In this paper, we present a novel method for the challenging task of fine-structured (FS) object segmentation. Expand
  • 1
Fine-structured object segmentation via neighborhood propagation
TLDR
This paper presents a novel method for the challenging task of fine-structured (FS) object segmentation. Expand
  • 1