most citedBack to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness

27 citations · 30 across the 6 of their papers we have counts for

collaborators

8 papers

cs.CV2024

Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models

Matthew Kowal, Richard P. Wildes, Konstantinos G. Derpanis

Understanding what deep network models capture in their learned representations is a fundamental challenge in computer vision. We present a new methodology to understanding such vi…

cs.CV20241 cited

Understanding Video Transformers via Universal Concept Discovery

Matthew Kowal, Achal Dave, Rares Ambrus +3

This paper studies the problem of concept-based interpretability of transformer representations for videos. Concretely, we seek to explain the decision-making process of video tran…

cs.CV2023

Reconstructive Latent-Space Neural Radiance Fields for Efficient 3D Scene Representations

Tristan Aumentado-Armstrong, Ashkan Mirzaei, Marcus A. Brubaker +4

Neural Radiance Fields (NeRFs) have proven to be powerful 3D representations, capable of high quality novel view synthesis of complex scenes. While NeRFs have been applied to graph…

cs.CV2023

GePSAn: Generative Procedure Step Anticipation in Cooking Videos

Mohamed Ashraf Abdelsalam, Samrudhdhi B. Rangrej, Isma Hadji +3

We study the problem of future step anticipation in procedural videos. Given a video of an ongoing procedural activity, we predict a plausible next procedure step described in rich…

cs.CV20231 cited

Dual-Camera Joint Deblurring-Denoising

Shayan Shekarforoush, Amanpreet Walia, Marcus A. Brubaker +2

Recent image enhancement methods have shown the advantages of using a pair of long and short-exposure images for low-light photography. These image modalities offer complementary s…

cs.CV20232 cited

StepFormer: Self-supervised Step Discovery and Localization in Instructional Videos

Nikita Dvornik, Isma Hadji, Ran Zhang +4

Instructional videos are an important resource to learn procedural tasks from human demonstrations. However, the instruction steps in such videos are typically short and sparse, wi…