zjsong
My research interests include predictive coding, multimodal learning, generative model, and computer vision.
School of Mathematics and Statistics, Xi’an Jiaotong UniversityXi'an, China
Pinned Repositories
SSPL
A mirror repo of SSPL: https://github.com/zjsong/SSPL
Audio-Visual-Predictive-Coding
PyTorch Implementation for "Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding"
CDNet
PyTorch code for "Toward a Controllable Disentanglement Network" (IEEE T-CYB 2020)
Fast-Inference-Predictive-Coding
Matlab implementation for "Fast Inference Predictive Coding: A Novel Model for Constructing Deep Neural Networks" (IEEE T-NNLS 2018)
SACL
PyTorch code for "Enhancing Sound Source Localization via False Negative Elimination"
SSPL
PyTorch code for "Self-Supervised Predictive Learning: A Negative-Free Method for Sound Source Localization in Visual Scenes" (CVPR, 2022)
zjsong.github.io
zjsong's Repositories
zjsong/SSPL
PyTorch code for "Self-Supervised Predictive Learning: A Negative-Free Method for Sound Source Localization in Visual Scenes" (CVPR, 2022)
zjsong/CDNet
PyTorch code for "Toward a Controllable Disentanglement Network" (IEEE T-CYB 2020)
zjsong/Fast-Inference-Predictive-Coding
Matlab implementation for "Fast Inference Predictive Coding: A Novel Model for Constructing Deep Neural Networks" (IEEE T-NNLS 2018)
zjsong/Audio-Visual-Predictive-Coding
PyTorch Implementation for "Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding"
zjsong/SACL
PyTorch code for "Enhancing Sound Source Localization via False Negative Elimination"
zjsong/zjsong.github.io