6 papers
UI-LIC: A Unified Framework for Evaluating Learned Image Compression Models
Nicholas J. Nolen, Luc Trudeau, Andrew C. Freeman
The evaluation and comparison of Learned Image Compression (LIC) systems is complicated by heterogeneous software stacks, varying training conditions, and divergent evaluation meth…
Latent Planning via Embedding Arithmetic: A Contrastive Approach to Strategic Reasoning
Andrew Hamara, Greg Hamerly, Pablo Rivas +1
Planning in high-dimensional decision spaces is increasingly being studied through the lens of learned representations. Rather than training policies or value heads, we investigate…
Carousel: A High-Resolution Dataset for Multi-Target Automatic Image Cropping
Rafe Loya, Andrew Hamara, Benjamin Estell +2
Automatic image cropping is a method for maximizing the human-perceived quality of cropped regions in photographs. Although several works have proposed techniques for producing sin…
Efficient Multi-Crop Saliency Partitioning for Automatic Image Cropping
Andrew Hamara, Andrew C. Freeman
Automatic image cropping aims to extract the most visually salient regions while preserving essential composition elements. Traditional saliency-aware cropping methods optimize a s…
Learning to Plan via Supervised Contrastive Learning and Strategic Interpolation: A Chess Case Study
Andrew Hamara, Greg Hamerly, Pablo Rivas +1
Modern chess engines achieve superhuman performance through deep tree search and regressive evaluation, while human players rely on intuition to select candidate moves followed by…
Low-Latency Scalable Streaming for Event-Based Vision
Andrew Hamara, Benjamin Kilpatrick, Alex Baratta +2
Recently, we have witnessed the rise of novel ``event-based'' camera sensors for high-speed, low-power video capture. Rather than recording discrete image frames, these sensors out…