• Publications
  • Influence
Diversified Visual Attention Networks for Fine-Grained Object Classification
TLDR
We propose a diversified visual attention network for fine-grained object classification, which explicitly pursues the diversity of attention and is able to gather discriminative information to the maximal extent. Expand
  • 199
  • 18
  • PDF
Neural Person Search Machines
  • H. Liu, Jiashi Feng, +5 authors S. Yan
  • Computer Science
  • IEEE International Conference on Computer Vision…
  • 21 July 2017
TLDR
We develop the Neural Person Search Machines (NPSM) to implement such recursive localization for person search. Expand
  • 72
  • 14
  • PDF
Image Generation From Layout
TLDR
We propose a novel approach for layout-based image generation; we call it Layout2Im. Expand
  • 57
  • 13
  • PDF
Nonlinear Robust Adaptive Tracking Control of a Quadrotor UAV Via Immersion and Invariance Methodology
TLDR
This paper presents a novel asymptotic tracking controller for an underactuated quadrotor unmanned aerial vehicle using the robust integral of the signum of the error (RISE) method and an immersion and invariance (I&I)-based adaptive control methodology. Expand
  • 264
  • 9
AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding
TLDR
This paper proposed a large-scale dataset named AIC (AI Challenger) with three sub-datasets, human keypoint detection (HKD), large- scale attribute dataset (LAD) and image Chinese captioning (ICC). Expand
  • 45
  • 9
  • PDF
Memory-Augmented Attribute Manipulation Networks for Interactive Fashion Search
TLDR
We introduce a novel memory-augmented Attribute Manipulation Network (AMNet) which can manipulate image representation at the attribute level. Expand
  • 66
  • 8
  • PDF
Left-Right Comparative Recurrent Model for Stereo Matching
  • Zequn Jie, Pengfei Wang, +4 authors W. Liu
  • Computer Science
  • IEEE/CVF Conference on Computer Vision and…
  • 3 April 2018
TLDR
This paper proposes a novel left-right comparative recurrent model to performleft-right consistency checking jointly with disparity estimation. Expand
  • 42
  • 6
  • PDF
Modular Generative Adversarial Networks
TLDR
This paper proposes ModularGAN for multi-domain image generation and image-to-image translation. Expand
  • 46
  • 6
  • PDF
Sketch Recognition with Deep Visual-Sequential Fusion Model
TLDR
A deep end-to-end network for sketch recognition, named Deep Visual-Sequential Fusion model (DVSF) is proposed to model the visual and sequential patterns of the strokes. Expand
  • 17
  • 6
  • PDF
A Large-Scale Attribute Dataset for Zero-Shot Learning
TLDR
We propose a Large-scale Attribute Dataset (LAD) with 78,017 images of 230 classes. Expand
  • 17
  • 5
  • PDF