Search Results for author: Farrukh Rahman

Found 2 papers, 0 papers with code

Weak Supervision for Label Efficient Visual Bug Detection

no code implementations20 Sep 2023 Farrukh Rahman

As video games evolve into expansive, detailed worlds, visual quality becomes essential, yet increasingly challenging.

On the Surprising Effectiveness of Transformers in Low-Labeled Video Recognition

no code implementations15 Sep 2022 Farrukh Rahman, Ömer Mubarek, Zsolt Kira

Our work empirically explores the low data regime for video classification and discovers that, surprisingly, transformers perform extremely well in the low-labeled video setting compared to CNNs.

Image Classification Inductive Bias +2

Cannot find the paper you are looking for? You can Submit a new open access paper.