• Publications
  • Influence
Large Margin Object Tracking with Circulant Feature Maps
TLDR
A novel large margin object tracking method which absorbs the strong discriminative ability from structured output SVM and speeds up by the correlation filter algorithm significantly and a multimodal target detection technique is proposed to improve the target localization precision and prevent model drift introduced by similar objects or background noise.
Improved Recurrent Neural Networks for Session-based Recommendations
TLDR
This work proposes the application of two techniques to improve RNN-based models for session-based recommendations performance, namely, data augmentation, and a method to account for shifts in the input data distribution.
Stochastic Network Calculus
TLDR
A stochastic network calculus is proposed to systematically analyze the end-to-end Stochastic QoS performance of a system with stochastically bounded input traffic over a series of deterministic and stochastics servers.
Blind Image Quality Assessment Based on High Order Statistics Aggregation
TLDR
A novel general purpose BIQA method based on high order statistics aggregation (HOSA), requiring only a small codebook, which has been extensively evaluated on ten image databases with both simulated and realistic image distortions, and shows highly competitive performance to the state-of-the-art BIZA methods.
A 45nm CMOS neuromorphic chip with a scalable architecture for learning in networks of spiking neurons
TLDR
A new architecture is proposed to overcome scalable learning algorithms for networks of spiking neurons in silicon by combining innovations in computation, memory, and communication to leverage robust digital neuron circuits and novel transposable SRAM arrays.
Opposition-based particle swarm algorithm with cauchy mutation
TLDR
An Opposition-based PSO (OPSO) to accelerate the convergence of PSO and avoid premature convergence is presented, which employs opposition-based learning for each particle and applies a dynamic Cauchy mutation on the best particle.
Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships
TLDR
This work presents a so-called Structure Inference Network (SIN), a detector that incorporates into a typical detection framework with a graphical model which aims to infer object state and comprehensive experiments indicate that scene context and object relationships truly improve the performance of object detection with more desirable and reasonable outputs.
A survey on peer-to-peer video streaming systems
TLDR
The challenges and solutions of providing live and on-demand video streaming in P2P environment are described and tree, multi-tree and mesh based systems are introduced.
...
1
2
3
4
5
...