1 citations · 2 across the 7 of their papers we have counts for
5 papers · 1 filter
SkipSR: Faster Super Resolution with Token Skipping
Rohan Choudhury, Shanchuan Lin, Jianyi Wang +6
Diffusion-based super-resolution (SR) is a key component in video generation and video restoration, but is slow and expensive, limiting scalability to higher resolutions and longer…
Accelerating Vision Transformers with Adaptive Patch Sizes
Rohan Choudhury, JungEun Kim, Jinhyung Park +3
Vision Transformers (ViTs) partition input images into uniformly sized patches regardless of their content, resulting in long input sequence lengths for high-resolution images. We…
Don't Look Twice: Faster Video Transformers with Run-Length Tokenization
Rohan Choudhury, Guanglei Zhu, Sihan Liu +3
Transformers are slow to train on videos due to extremely large numbers of input tokens, even though many video tokens are repeated over time. Existing methods to remove such uninf…
Zero-Shot Video Question Answering with Procedural Programs
Rohan Choudhury, Koichiro Niinuma, Kris M. Kitani +1
We propose to answer zero-shot questions about videos by generating short procedural programs that derive a final answer from solving a sequence of visual subtasks. We present Proc…
TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecasting
Rohan Choudhury, Kris Kitani, Laszlo A. Jeni
Existing volumetric methods for predicting 3D human pose estimation are accurate, but computationally expensive and optimized for single time-step prediction. We present TEMPO, an…