Activity Reognition

Project Details

Project Lead
AJ Piergiovanni 
Project Manager
AJ Piergiovanni 
Indiana University, Computer Science  
Computer Science (401) 
11.07 Computer Science 


We are studying various neural network architectures for activity recognition. Specifically, we want to compare a model that is capable of learning a motion representation based on optical flow, while using significantly less computations time, parameters and resulting in equivalent or better performance. We also want to compare video CNN models using our temporal gaussian mixture layers, which we have found to provide better performance with significantly fewer parameters. Michael Ryoo is my advisor for these projects.

Intellectual Merit

We are proposing several new video CNN models that will lead to better performance with less computation cost.

Broader Impacts

We will release all our code and trained models upon publication of the results.

Scale of Use

We estimate we need at least 15,000 GPU hours to complete our projects.