379 citations
- Stanford UniversityUS4 papers
- Tencent (China)CN4 papers
- University of Science and Technology of ChinaCN4 papers
- Boston UniversityUS3 papers
- California Institute of TechnologyUS3 papers
- Center for Astrophysics Harvard & SmithsonianUS3 papers
- SLAC National Accelerator LaboratoryUS3 papers
- University of ArizonaUS3 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Georgia Institute of TechnologyUS2 papers
- Harvard UniversityUS2 papers
- Technical University of MunichDE2 papers
6 papers · 1 filter
Referenceless Rate-Distortion Modeling with Learning from Bitstream and Pixel Features
Yangfan Sun, Li Li, Zhu Li +1
Generally, adaptive bitrates for variable Internet bandwidths can be obtained through multi-pass coding. Referenceless prediction-based methods show practical benefits compared wit…
Deep Spatial Transformation for Pose-Guided Person Image Generation and Animation
Yurui Ren, Ge Li, Shan Liu +1
Pose-guided person image generation and animation aim to transform a source person image to target poses. These tasks require spatial manipulation of source data. However, Convolut…
A Neural-Network Variational Quantum Algorithm for Many-Body Dynamics
Chee-Kong Lee, Pranay Patil, Shengyu Zhang +1
We propose a neural-network variational quantum algorithm to simulate the time evolution of quantum many-body systems. Based on a modified restricted Boltzmann machine (RBM) wavefu…
ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction
Zhongkai Hao, Chengqiang Lu, Zheyuan Hu +5
Molecular property prediction (e.g., energy) is an essential problem in chemistry and biology. Unfortunately, many supervised learning methods usually suffer from the problem of sc…
Decay studies of the long-lived states in Tl
M. Stryjczyk, B. Andel, A. N. Andreyev +45
Decay spectroscopy of the long-lived states in Tl has been performed at the ISOLDE Decay Station at ISOLDE, CERN. The decay from the low-spin state in T…
Self-supervised learning for audio-visual speaker diarization
Yifan Ding, Yong Xu, Shi-Xiong Zhang +2
Speaker diarization, which is to find the speech segments of specific speakers, has been widely used in human-centered applications such as video conferences or human-computer inte…