Characterization of 3D organelle motion using curve fitting and clustering by unsupervised machine learning

Project Information

bioinformatics
Project Status: Reviewing Applicants
Project Region: CAREERS
Submitted By: Anita Schwartz
Project Email: chandrak@udel.edu
Project Institution: University of Delaware
Anchor Institution: CR-University of Delaware
Project Address: Newark, Delaware. 19716

Mentors: Jeffrey Caplan
Students: Huining Liang

Project Description

Our current work is based on a transformer based pipeline, more specifically, TransUNet to leverage the power of CNNs and transformers for the image segmentation task. TransUNet involves CNN-Transformer Hybrid Encoder, Patch Embedding and Cascaded Upsampler. For tracking, we are using the tracking-by-attention paradigm which not only applies attention for data association but jointly performs tracking and detection, using TrackFormer, an end-to-end trainable MOT (multi-object tracking) approach based on an encoder-decoder Transformer architecture.

Project Information

bioinformatics
Project Status: Reviewing Applicants
Project Region: CAREERS
Submitted By: Anita Schwartz
Project Email: chandrak@udel.edu
Project Institution: University of Delaware
Anchor Institution: CR-University of Delaware
Project Address: Newark, Delaware. 19716

Mentors: Jeffrey Caplan
Students: Huining Liang

Project Description

Our current work is based on a transformer based pipeline, more specifically, TransUNet to leverage the power of CNNs and transformers for the image segmentation task. TransUNet involves CNN-Transformer Hybrid Encoder, Patch Embedding and Cascaded Upsampler. For tracking, we are using the tracking-by-attention paradigm which not only applies attention for data association but jointly performs tracking and detection, using TrackFormer, an end-to-end trainable MOT (multi-object tracking) approach based on an encoder-decoder Transformer architecture.