2021-2022

F2-T DeepSLAM: Object Detection, Re-identification and Prediction wih Implicit Mapping

The project goals and objectives are

1.Communication privacy and security of multi-agent systems:

Develop a privacy-enhanced multi-agent system that uses shared knowledge for both (i) Vision and (ii) Communication tasks.

2.Ego-motion prediction under Intermittent Feedback:

This goal removes the assumption that the GPS signal is always given and considers a GPS denied area. We design a hybrid system to help a traditional error-based control method maintain an error bound, of its state information using a CNN-based localization method.

F12-A Explainable Commonsense Question Answering

Current question answering systems is incapable of providing human-interpretable explanations or proof to support the decision. In this project, we propose general methods to answer common sense questions, offering natural language explanations or supporting facts. In particular, we propose Copy-explainer that generate natural language explanation that later help answer commonsense questions by leveraging structured and unstructured commonsense knowledge from external knowledge graph and pre-trained language models. Furthermore, we propose Encyclopedia Net, a fact-level causal knowledge graph, facilitating commonsense reasoning for question answering.

M1-V Deep Learning in Video Compression

We are proposing end-to-end video compression with motion field prediction. In video-based point cloud compression (V-PCC), a dynamic point cloud is projected onto geometry and attribute videos patch by patch for compression. We propose a CNN-based occupancy map recovery method to improve the quality of the reconstructed occupancy map video. To the best of our knowledge, this is the first deep learning based accurate occupancy map work for improving V-PCC coding efficiency.

O1-H Semantic Deep Learning for Electronic Health Records

We propose a novel “Semantic Deep Learning” method to analyze the electronic health records of real patients. Our previous work as successfully used a hypergraph- based approach in the clinical text notes from Stanford Hospital’s Clinical Data Warehouse (STRIDE). Previous experiments based on ontology (i.e., domain knowledge) annotated electronic health records show that hypergraph mining is successful in finding semantic (i.e., indirect) associations. This proposed method will take the success to the next level by adding the deep learning-based embedding in place of the basic hypergraphs of the previous approaches.