• Publications
  • Influence
Bit-Scalable Deep Hashing With Regularized Similarity Learning for Image Retrieval and Person Re-Identification
TLDR
We propose a supervised learning framework to generate compact and bit-scalable hashing codes directly from raw images. Expand
  • 387
  • 41
  • PDF
Cost-Effective Active Learning for Deep Image Classification
TLDR
In this paper, we propose a novel active learning (AL) framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner. Expand
  • 266
  • 32
  • PDF
DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images
TLDR
We build a large-scale fashion benchmark with comprehensive tasks and annotations, to facilitate fashion image analysis. Expand
  • 77
  • 16
  • PDF
Image-to-Video Person Re-Identification With Temporally Memorized Similarity Learning
TLDR
We propose a novel temporally memorized similarity learning neural network for image-to-video person re-id problem, in which the feature representation and distance metric learning are jointly performed and optimized. Expand
  • 31
  • 3
Geometric Scene Parsing with Hierarchical LSTM
TLDR
This paper addresses the problem of geometric scene parsing, i.e. simultaneously labeling geometric surfaces (e.g. sky, ground and vertical plane) and determining the interaction relations between them based on multi-scale super-pixel representations. Expand
  • 12
  • 3
  • PDF
Attentive Crowd Flow Machines
TLDR
We propose a unified neural network module to address this problem, called Attentive Crowd Flow Machine~(ACFM), which is able to infer the evolution of the crowd flow by learning dynamic representations of temporally-varying data with an attention mechanism. Expand
  • 22
  • 2
  • PDF
Towards Photo-Realistic Virtual Try-On by Adaptively Generating↔Preserving Image Content
TLDR
Image visual try-on aims at transferring a target clothes image onto a reference person, and has become a hot topic in recent years. Expand
  • 6
  • 2
  • PDF
SCAN: Self-and-Collaborative Attention Network for Video Person Re-Identification
TLDR
We present a novel and practical deep architecture for video person re-identification termed self-and-collaborative attention network (SCAN), which adopts the video pairs as the input and outputs their matching scores. Expand
  • 23
  • 1
  • PDF
Switchable Normalization for Learning-to-Normalize Deep Representation
TLDR
We address a learning-to-normalize problem by proposing Switchable Normalization (SN), which learns to select different normalizers for different normalization layers of a deep neural network. Expand
  • 10
  • 1
  • PDF
Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks
TLDR
We present Groupable ConvNet (GroupNet) built by using a novel dynamic grouping convolution (DGConv) operation, which learns the number of groups in an end-to-end manner. Expand
  • 9
  • 1
  • PDF