35 citations · 72 across the 10 of their papers we have counts for
10 papers
Synaptic Dynamics Realize First-order Adaptive Learning and Weight Symmetry
Yukun Yang, Peng Li
Gradient-based first-order adaptive optimization methods such as the Adam optimizer are prevalent in training artificial networks, achieving the state-of-the-art results. This work…
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation
Peng Li, Jiayin Zhao, Jingyao Wu +3
Light field disparity estimation is an essential task in computer vision with various applications. Although supervised learning-based methods have achieved both higher accuracy an…
Binary Neural Networks as a general-propose compute paradigm for on-device computer vision
Guhong Nie, Lirui Xiao, Menglong Zhu +6
For binary neural networks (BNNs) to become the mainstream on-device computer vision algorithm, they must achieve a superior speed-vs-accuracy tradeoff than 8-bit quantization and…
FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks
Jiabin Zhang, Zheng Zhu, Wei Zou +4
Both accuracy and efficiency are significant for pose estimation and tracking in videos. State-of-the-art performance is dominated by two-stages top-down methods. Despite the leadi…
State-aware Re-identification Feature for Multi-target Multi-camera Tracking
Peng Li, Jiabin Zhang, Zheng Zhu +3
Multi-target Multi-camera Tracking (MTMCT) aims to extract the trajectories from videos captured by a set of cameras. Recently, the tracking performance of MTMCT is significantly e…
Exploiting Offset-guided Network for Pose Estimation and Tracking
Rui Zhang, Zheng Zhu, Peng Li +4
Human pose estimation has witnessed a significant advance thanks to the development of deep learning. Recent human pose estimation approaches tend to directly predict the location…
Robust Deep Multi-Modal Sensor Fusion using Fusion Weight Regularization and Target Learning
Myung Seok Shim, Chenye Zhao, Yang Li +3
Sensor fusion has wide applications in many domains including health care and autonomous systems. While the advent of deep learning has enabled promising multi-modal fusion of high…
Optimized Gated Deep Learning Architectures for Sensor Fusion
Myung Seok Shim, Peng Li
Sensor fusion is a key technology that integrates various sensory inputs to allow for robust decision making in many applications such as autonomous driving and robot control. Deep…
Efficient Two-Step Adversarial Defense for Deep Neural Networks
Ting-Jui Chang, Yukun He, Peng Li
In recent years, deep neural networks have demonstrated outstanding performance in many machine learning tasks. However, researchers have discovered that these state-of-the-art mod…
Image Captioning based on Deep Reinforcement Learning
Haichao Shi, Peng Li, Bo Wang +1
Recently it has shown that the policy-gradient methods for reinforcement learning have been utilized to train deep end-to-end systems on natural language processing tasks. What's m…