4 papers
SAM 3: Segment Anything with Concepts
Nicolas Carion, Laura Gustafson, Yuan-Ting Hu +35
We present Segment Anything Model (SAM) 3, a unified model that detects, segments, and tracks objects in images and videos based on concept prompts, which we define as either short…
SAVeD: Learning to Denoise Low-SNR Video for Improved Downstream Performance
Suzanne Stathatos, Michael Hobley, Pietro Perona +1
Low signal-to-noise ratio videos -- such as those from underwater sonar, ultrasound, and microscopy -- pose significant challenges for computer vision models, particularly when pai…
Diffusion-Based Action Recognition Generalizes to Untrained Domains
Rogerio Guimaraes, Frank Xiao, Pietro Perona +1
Humans can recognize the same actions despite large context and viewpoint variations, such as differences between species (walking in spiders vs. horses), viewpoints (egocentric vs…
Probing the Mid-level Vision Capabilities of Self-Supervised Learning
Xuweiyi Chen, Markus Marks, Zezhou Cheng
Mid-level vision capabilities - such as generic object localization and 3D geometric understanding - are not only fundamental to human vision but are also crucial for many real-wor…