Towards Causal Physical Error Discovery in Video Analytics Systems

no code implementations • 27 May 2024 • Jinjin Zhao, Ted Shaowang, Stavos Sintos, Sanjay Krishnan

Video analytics systems based on deep learning models are often opaque and brittle and require explanation systems to help users debug.

vONTSS: vMF based semi-supervised neural topic modeling with optimal transport

1 code implementation • 3 Jul 2023 • Weijie Xu, Xiaoyu Jiang, Srinivasan H. Sengamedu, Francis Iannacci, Jinjin Zhao

Recently, Neural Topic Models (NTM), inspired by variational autoencoders, have attracted a lot of research interest; however, these methods have limited applications in the real world due to the challenge of incorporating human knowledge.

text-classification Topic Classification +1

FFPDG: Fast, Fair and Private Data Generation

no code implementations • 30 Jun 2023 • Weijie Xu, Jinjin Zhao, Francis Iannacci, Bo wang

Generative modeling has been used frequently in synthetic data generation.

Fairness Synthetic Data Generation

Deep Transfer Learning with Graph Neural Network for Sensor-Based Human Activity Recognition

no code implementations • 14 Mar 2022 • Yan Yan, Tianzheng Liao, Jinjin Zhao, Jiahong Wang, Liang Ma, Wei Lv, Jing Xiong, Lei Wang

Given this observation, we devised a graph-inspired deep learning approach toward the sensor-based HAR tasks, which was further used to build a deep transfer learning model toward giving a tentative solution for these two challenging problems.

Few-Shot Learning Graph Neural Network +2

Knowledge Graph semantic enhancement of input data for improving AI

no code implementations • 10 May 2020 • Shreyansh Bhatt, Amit Sheth, Valerie Shalin, Jinjin Zhao

Intelligent systems designed using machine learning algorithms require a large number of labeled data.

BIG-bench Machine Learning Community Detection