Proceedings ArticleDOI
Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification
Zhongdao Wang,Luming Tang,Xihui Liu,Zhuliang Yao,Shuai Yi,Jing Shao,Junjie Yan,Shengjin Wang,Hongsheng Li,Xiaogang Wang +9 more
- pp 379-387
Reads0
Chats0
TLDR
Both the orientation invariant feature embedding and the spatio-temporal regularization achieve considerable improvements in the vehicle Re-identification problem.Abstract:
In this paper, we tackle the vehicle Re-identification (ReID) problem which is of great importance in urban surveillance and can be used for multiple applications. In our vehicle ReID framework, an orientation invariant feature embedding module and a spatial-temporal regularization module are proposed. With orientation invariant feature embedding, local region features of different orientations can be extracted based on 20 key point locations and can be well aligned and combined. With spatial-temporal regularization, the log-normal distribution is adopted to model the spatial-temporal constraints and the retrieval results can be refined. Experiments are conducted on public vehicle ReID datasets and our proposed method achieves state-of-the-art performance. Investigations of the proposed framework is conducted, including the landmark regressor and comparisons with attention mechanism. Both the orientation invariant feature embedding and the spatio-temporal regularization achieve considerable improvements.read more
Citations
More filters
Journal Article
Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond
TL;DR: In this paper , an attribute descent approach is proposed to optimize engine attributes to enable synthetic data to approximate real-world data, which can be used in three scenarios: training with synthetic data only, training data augmentation and numerically understanding dataset content.
Journal ArticleDOI
Vehicle re-identification in tunnel scenes via synergistically cascade forests
TL;DR: A synergistically cascade forests (SCF) model is proposed which aims to gradually construct the linking relation between vehicle samples with an increasing of alternative layers of random forest and extremely randomized forest and can outperform current state-of-the-art methods.
Journal ArticleDOI
Transformer-Based Attention Network for Vehicle Re-Identification
TL;DR: The experimental results demonstrated that the proposed TAN is effective in improving the performance of both the vehicle and person ReID tasks, and the proposed method achieves state-of-the-art (SOTA) perfomance.
Journal ArticleDOI
Cold Start Problem of Vehicle Model Recognition under Cross-Scenario Based on Transfer Learning
TL;DR: Transfer the vehicle model recognition from the network image dataset (source domain) to the surveillance-nature dataset (target domain), both Top-1 and Top-5 accuracy have been improved by at least 20%.
Posted Content
Multi-Domain Learning and Identity Mining for Vehicle Re-Identification.
TL;DR: Zhang et al. as mentioned in this paper proposed a multi-domain learning method to joint the real-world and synthetic data to train the model and then proposed the identity mining method to automatically generate pseudo labels for a part of the testing data, which was better than the k-means clustering.
References
More filters
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Journal Article
Visualizing Data using t-SNE
TL;DR: A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
Proceedings ArticleDOI
FaceNet: A unified embedding for face recognition and clustering
TL;DR: A system that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity, and achieves state-of-the-art face recognition performance using only 128-bytes perface.
Book ChapterDOI
Stacked Hourglass Networks for Human Pose Estimation
TL;DR: This work introduces a novel convolutional network architecture for the task of human pose estimation that is described as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions.
Proceedings ArticleDOI
Scalable Person Re-identification: A Benchmark
TL;DR: A minor contribution, inspired by recent advances in large-scale image search, an unsupervised Bag-of-Words descriptor is proposed that yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large- scale 500k dataset.