1 citations · 1 across the 3 of their papers we have counts for
5 papers
What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models
Sharon S. Musa, Fereshteh Forghani, Harrish Thasarathan +3
Self-supervised video foundation models learn rich spatiotemporal representations, yet it remains unclear what visual concepts these representations encode, where they emerge acros…
Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment
Harrish Thasarathan, Julian Forsyth, Thomas Fel +2
We present Universal Sparse Autoencoders (USAEs), a framework for uncovering and aligning interpretable concepts spanning multiple pretrained deep neural networks. Unlike existing…
Artist-Guided Semiautomatic Animation Colorization
Harrish Thasarathan, Mehran Ebrahimi
There is a delicate balance between automating repetitive work in creative domains while staying true to an artist's vision. The animation industry regularly outsources large anima…
Edge-Informed Single Image Super-Resolution
Kamyar Nazeri, Harrish Thasarathan, Mehran Ebrahimi
The recent increase in the extensive use of digital imaging technologies has brought with it a simultaneous demand for higher-resolution images. We develop a novel edge-informed ap…
Automatic Temporally Coherent Video Colorization
Harrish Thasarathan, Kamyar Nazeri, Mehran Ebrahimi
Greyscale image colorization for applications in image restoration has seen significant improvements in recent years. Many of these techniques that use learning-based methods strug…