• Publications
  • Influence
Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro
TLDR
The main contribution of this paper is a simple semisupervised pipeline that only uses the original training data only from the training set without collecting extra data. Expand
  • 925
  • 283
  • PDF
Beyond Part Models: Person Retrieval with Refined Part Pooling
TLDR
We propose a network named Part-based Convolutional Baseline (PCB) which conducts uniform partition on the conv-layer for learning part-level features. Expand
  • 681
  • 199
  • PDF
Random Erasing Data Augmentation
TLDR
We introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN). Expand
  • 703
  • 68
  • PDF
Person Re-identification: Past, Present and Future
TLDR
Person re-identification (re-ID) has become increasingly popular in the community due to its application and research significance. Expand
  • 619
  • 67
  • PDF
Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks
TLDR
This paper proposed a Soft Filter Pruning method to accelerate the inference procedure of deep Convolutional Neural Networks (CNNs). Expand
  • 254
  • 62
  • PDF
Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning
TLDR
In this paper, we propose a new approach, namely Hierarchical Recurrent Neural Encoder (HRNE), to exploit temporal information of videos. Expand
  • 286
  • 56
  • PDF
A Discriminatively Learned CNN Embedding for Person Reidentification
TLDR
We propose a Siamese network that learns a discriminative embedding and a similarity measurement at the same time, thus taking full usage of the re-ID annotations. Expand
  • 459
  • 49
  • PDF
Infrared Patch-Image Model for Small Target Detection in a Single Image
TLDR
The robust detection of small targets is one of the key techniques in infrared search and tracking applications. Expand
  • 238
  • 49
  • PDF
A discriminative CNN video representation for event detection
TLDR
In this paper, we propose a discriminative video representation for event detection over a large scale video dataset when only limited hardware resources are available. Expand
  • 389
  • 43
  • PDF
Generalizing a Person Retrieval Model Hetero- and Homogeneously
TLDR
We introduce a Hetero-Homogeneous Learning (HHL) method to improve the generalization ability of re-ID models on the target testing set. Expand
  • 170
  • 40
  • PDF