MELODY
MOU PEIJING
Artist:
Dr. Hector Rodriguez
Programming:
Mou Peijing, Dr. Hector Rodriguez
Visualization:
Mou Peijing
Reseach Assistant
Machine Learning Projects
Machine Learning and Computer Vision research project led by Dr. Hector Rodrigez at ACIM Lab, School of Creative Media.
The selected demos are visualization created for research progress, which explores the unique possibilities of machine learning to reconfigure and analyze moving images through experimenting with AI models. The research particularly focuses on the analysis of the rhythm of old films and new clip generation.
The video on the left shows a neural network trained to predict future frames of an old B&W movie. This clip shows the original movie on the left and the predictions on the right. The other images are visualizations for latent features embedded in Cross Transformer and image reconstruction using AdaBins Model.
Publication 2024 CVPR AI Art:
The selected demos are visualization created for research progress, which explores the unique possibilities of machine learning to reconfigure and analyze moving images through experimenting with AI models. The research particularly focuses on the analysis of the rhythm of old films and new clip generation.
The video on the left shows a neural network trained to predict future frames of an old B&W movie. This clip shows the original movie on the left and the predictions on the right. The other images are visualizations for latent features embedded in Cross Transformer and image reconstruction using AdaBins Model.
"Movie Map" using embeddings from X-Transformer
3D visualization for features from X-Transformer
Visualization for Attention in Cross Transformer