• Publications
  • Influence
Fused DNN: A Deep Neural Network Fusion Approach to Fast and Robust Pedestrian Detection
TLDR
We propose a deep neural network fusion architecture for fast and robust pedestrian detection. Expand
  • 185
  • 31
  • PDF
Towards the Limit of Network Quantization
TLDR
We analyze the quantitative relation of quantization errors to the neural network loss function and identify that Hessian-weighted distortion measure is the right objective function for the optimization of network quantization. Expand
  • 85
  • 13
  • PDF
Residual LSTM: Design of a Deep Recurrent Architecture for Distant Speech Recognition
TLDR
In this paper, a novel architecture for a deep recurrent neural network, residual LSTM is introduced. Expand
  • 105
  • 10
  • PDF
Performance Limits and Practical Decoding of Interleaved Reed-Solomon Polar Concatenated Codes
TLDR
A scheme for concatenating binary polar codes with interleaved Reed-Solomon codes captures the capacity-achieving property of polar codes, while having a significantly better error-decay rate. Expand
  • 63
  • 6
  • PDF
Design of rate-compatible structured LDPC codes for hybrid ARQ applications
TLDR
In this paper, families of rate-compatible protograph-based LDPC codes that are suitable for incrementalredundancy hybrid ARQ applications are constructed. Expand
  • 56
  • 6
  • PDF
Iterative algebraic soft-decision list decoding of Reed-Solomon codes
TLDR
We present an iterative soft-decision decoding algorithm for Reed-Solomon codes offering both complexity and performance advantages over previously known decoding algorithms. Expand
  • 81
  • 5
  • PDF
Variable Rate Deep Image Compression With a Conditional Autoencoder
TLDR
In this paper, we propose a novel variable-rate learned image compression framework with a conditional autoencoder. Expand
  • 26
  • 5
  • PDF
Relaxed Polar Codes
TLDR
Polar codes are the latest breakthrough in coding theory, as they are the first family of codes with explicit construction that provably achieve the symmetric capacity of binary-input discrete memoryless channels. Expand
  • 21
  • 5
  • PDF
Joint space-time-view error concealment algorithms for 3D multi-view video
TLDR
Efficiently compressing 3D multi-view video, while maintaining a high quality of received 3D video, is very challenging. Expand
  • 14
  • 5
Fused Deep Neural Networks for Efficient Pedestrian Detection
TLDR
In this paper, we present an efficient pedestrian detection system, designed by fusion of multiple deep neural network (DNN) systems and a fusion network which utilizes a novel soft-rejection fusion method. Expand
  • 17
  • 4
  • PDF