• Publications
  • Influence
Deep Learning Face Attributes in the Wild
TLDR
We propose a novel deep learning framework for attribute prediction in the wild, which outperforms the state-of-the-art with a large margin. Expand
  • 2,785
  • 747
  • PDF
DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations
TLDR
We introduce DeepFashion, a comprehensively annotated clothes dataset that contains massive attributes, clothing landmarks, as well as cross-pose/cross-domain correspondences of clothing pairs. Expand
  • 638
  • 182
  • PDF
WIDER FACE: A Face Detection Benchmark
TLDR
We introduce a large-scale face detection dataset called WIDER FACE, which is 10 times larger than existing datasets. Expand
  • 580
  • 148
  • PDF
Facial Landmark Detection by Deep Multi-task Learning
TLDR
We propose a Tasks-Constrained Deep Convolutional Network (TCDCN) to jointly optimize facial landmark detection with a set of related tasks. Expand
  • 923
  • 103
  • PDF
A large-scale car dataset for fine-grained categorization and verification
TLDR
This paper aims to highlight vision related tasks centered around “car”, which has been largely neglected by vision community in comparison to other objects. Expand
  • 428
  • 92
  • PDF
Pedestrian Attribute Recognition At Far Distance
TLDR
The capability of recognizing pedestrian attributes, such as gender and clothing style, at far distance, is of practical interest in far-view surveillance scenarios where face and body close-shots are hardly available. Expand
  • 215
  • 69
  • PDF
From Facial Parts Responses to Face Detection: A Deep Learning Approach
TLDR
In this paper, we propose a novel deep convolutional network (DCN) that achieves outstanding performance on FDDB, PASCAL Face, and AFW. Expand
  • 403
  • 56
  • PDF
Learning Deep Representation for Face Alignment with Auxiliary Attributes
TLDR
We formulate a novel tasks-constrained deep model, which not only learns the inter-task correlation but also employs dynamic task coefficients to facilitate the optimization convergence when learning multiple complex tasks. Expand
  • 292
  • 55
  • PDF
Spatial As Deep: Spatial CNN for Traffic Scene Understanding
TLDR
We propose Spatial CNN (SCNN), which generalizes traditional deep layer-by-layer convolutions to slice-byslice convolutions within feature maps, thus enabling message passings between pixels across rows and columns in a layer. Expand
  • 144
  • 41
  • PDF
Deep Learning Strong Parts for Pedestrian Detection
TLDR
We propose DeepParts, which consists of extensive part detectors that can detect pedestrian by observing only a part of a proposal. Expand
  • 319
  • 40
  • PDF