Picture for Yuhuang Hu

Yuhuang Hu

Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks

Add code
Mar 29, 2022
Figure 1 for Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks
Figure 2 for Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks
Figure 3 for Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks
Figure 4 for Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks
Viaarxiv icon

Exploiting Spatial Sparsity for Event Cameras with Visual Transformers

Add code
Feb 10, 2022
Viaarxiv icon

T-NGA: Temporal Network Grafting Algorithm for Learning to Process Spiking Audio Sensor Events

Add code
Feb 07, 2022
Figure 1 for T-NGA: Temporal Network Grafting Algorithm for Learning to Process Spiking Audio Sensor Events
Figure 2 for T-NGA: Temporal Network Grafting Algorithm for Learning to Process Spiking Audio Sensor Events
Figure 3 for T-NGA: Temporal Network Grafting Algorithm for Learning to Process Spiking Audio Sensor Events
Figure 4 for T-NGA: Temporal Network Grafting Algorithm for Learning to Process Spiking Audio Sensor Events
Viaarxiv icon

V2E: From video frames to realistic DVS event camera streams

Add code
Jun 13, 2020
Figure 1 for V2E: From video frames to realistic DVS event camera streams
Figure 2 for V2E: From video frames to realistic DVS event camera streams
Figure 3 for V2E: From video frames to realistic DVS event camera streams
Figure 4 for V2E: From video frames to realistic DVS event camera streams
Viaarxiv icon

DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction

Add code
May 18, 2020
Figure 1 for DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction
Figure 2 for DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction
Figure 3 for DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction
Figure 4 for DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction
Viaarxiv icon

Character-Level Translation with Self-attention

Add code
Apr 30, 2020
Figure 1 for Character-Level Translation with Self-attention
Figure 2 for Character-Level Translation with Self-attention
Figure 3 for Character-Level Translation with Self-attention
Figure 4 for Character-Level Translation with Self-attention
Viaarxiv icon

Exploiting Event Cameras by Using a Network Grafting Algorithm

Add code
Mar 24, 2020
Figure 1 for Exploiting Event Cameras by Using a Network Grafting Algorithm
Figure 2 for Exploiting Event Cameras by Using a Network Grafting Algorithm
Figure 3 for Exploiting Event Cameras by Using a Network Grafting Algorithm
Figure 4 for Exploiting Event Cameras by Using a Network Grafting Algorithm
Viaarxiv icon

Character-level Chinese-English Translation through ASCII Encoding

Add code
Aug 27, 2018
Figure 1 for Character-level Chinese-English Translation through ASCII Encoding
Figure 2 for Character-level Chinese-English Translation through ASCII Encoding
Figure 3 for Character-level Chinese-English Translation through ASCII Encoding
Figure 4 for Character-level Chinese-English Translation through ASCII Encoding
Viaarxiv icon

Overcoming the vanishing gradient problem in plain recurrent networks

Add code
May 25, 2018
Figure 1 for Overcoming the vanishing gradient problem in plain recurrent networks
Figure 2 for Overcoming the vanishing gradient problem in plain recurrent networks
Figure 3 for Overcoming the vanishing gradient problem in plain recurrent networks
Figure 4 for Overcoming the vanishing gradient problem in plain recurrent networks
Viaarxiv icon

Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networks

Add code
Dec 13, 2016
Figure 1 for Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networks
Figure 2 for Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networks
Viaarxiv icon