• Publications
  • Influence
Deep High-Resolution Representation Learning for Visual Recognition
TLDR
We present a novel architecture, namely High-Resolution Network (HRNet), which is able to maintain high-resolution representations through the whole process. Expand
  • 188
  • 43
  • PDF
High-Resolution Representations for Labeling Pixels and Regions
TLDR
We introduce a simple modification by exploring the representations from all the high-to-low resolution parallel convolutions in parallel and apply it to a wide range of vision tasks. Expand
  • 142
  • 42
  • PDF
Application of STBC-encoded cooperative transmissions in wireless sensor networks
TLDR
The efficiency of space-time block code-encoded cooperative transmission is studied within low-energy adaptive clustering hierarchy (LEACH), which is a typical networking/communication protocol for wireless sensor networks. Expand
  • 188
  • 14
  • PDF
Densely Connected Search Space for More Flexible Neural Architecture Search
TLDR
In this paper, we propose to search block counts and block widths by designing a densely connected search space, i.e., DenseNAS. Expand
  • 32
  • 4
  • PDF
All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting
TLDR
We propose an end-to-end trainable network for spotting arbitrary-shaped text without character-level annotations. Expand
  • 12
  • 2
  • PDF
Learning Context-Sensitive Shape Similarity
Shape similarity and shape retrieval are very important topics in computer vision. The recent progress in this domain has been mostly driven by designing smart shape descriptors for providing betterExpand
  • 4
  • 2
Con vex Shape Decomposition
In this paper, we propose a new shape decomposition method, called convex shape decomposition. We formalize the convex decomposition problem as an integer linear programming problem, and obtainExpand
  • 6
  • 2
Motion-Guided Spatial Time Attention for Video Object Segmentation
TLDR
In this paper, we propose a novel motion-guided attention module to implant the spatial and time consistency in the correlation map of the current frame with historical frames. Expand
  • 4
  • 2
  • PDF
CCNet: Criss-Cross Attention for Semantic Segmentation.
TLDR
We propose a Criss-Cross Network (CCNet) for obtaining full-image contextual information in a very effective and efficient way. Expand
  • 24
  • 1
Diversity Transfer Network for Few-Shot Learning
TLDR
We propose a novel generative framework, Diversity Transfer Network (DTN), that learns to transfer latent diversities from known categories and composite them with support features to generate diverse samples for novel categories in feature space. Expand
  • 7
  • 1
  • PDF