• Publications
  • Influence
SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks
This work proves the core reason Siamese trackers still have accuracy gap comes from the lack of strict translation invariance, and proposes a new model architecture to perform depth-wise and layer-wise aggregations, which not only improves the accuracy but also reduces the model size.
The Visual Object Tracking VOT2016 Challenge Results
The Visual Object Tracking challenge VOT2016 goes beyond its predecessors by introducing a new semi-automatic ground truth bounding box annotation methodology and extending the evaluation system with the no-reset experiment.
Transfer Learning Based Visual Tracking with Gaussian Processes Regression
This paper directly analyze this probability of target appearance as exponentially related to the confidence of a classifier output using Gaussian Processes Regression (GPR), and introduces a latent variable to assist the tracking decision.
The Visual Object Tracking VOT2017 Challenge Results
The Visual Object Tracking challenge VOT2017 is the fifth annual tracker benchmarking activity organized by the VOT initiative. Results of 51 trackers are presented; many are state-of-the-art
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
This work proposes an end-to-end spatial and temporal attention model for human action recognition from skeleton data on top of the Recurrent Neural Networks with Long Short-Term Memory (LSTM), which learns to selectively focus on discriminative joints of skeleton within each frame of the inputs and pays different levels of attention to the outputs of different frames.
DCFNet: Discriminant Correlation Filters Network for Visual Tracking
This work presents an end-to-end lightweight network architecture, namely DCFNet, to learn the convolutional features and perform the correlation tracking process simultaneously, and treats DCF as a special correlation filter layer added in a Siamese network.
Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks
This work takes the skeleton as the input at each time slot and introduces a novel regularization scheme to learn the co-occurrence features of skeleton joints, and proposes a new dropout algorithm which simultaneously operates on the gates, cells, and output responses of the LSTM neurons.
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data
A novel view adaptation scheme to automatically regulate observation viewpoints during the occurrence of an action by design a view adaptive recurrent neural network with LSTM architecture, which enables the network itself to adapt to the most suitable observation viewpoints from end to end.
Pose-Driven Deep Convolutional Model for Person Re-identification
A Pose-driven Deep Convolutional (PDC) model is proposed to learn improved feature extraction and matching models from end to end and explicitly leverages the human part cues to alleviate the pose variations and learn robust feature representations from both the global image and different local parts.
A Deep Regression Architecture with Two-Stage Re-initialization for High Performance Facial Landmark Detection
This paper presents a deep regression architecture with two-stage re-initialization to explicitly deal with the initialization problem and obtains promising results using different kinds of unstable initialization.