4 papers
NovisVQ: A Streaming Convolutional Neural Network for No-Reference Opinion-Unaware Frame Quality Assessment
Kylie Cancilla, Alexander Moore, Amar Saini +1
Video quality assessment (VQA) is vital for computer vision tasks, but existing approaches face major limitations: full-reference (FR) metrics require clean reference videos, and m…
Training for X-Ray Vision: Amodal Segmentation, Amodal Content Completion, and View-Invariant Object Representation from Multi-Camera Video
Alexander Moore, Amar Saini, Kylie Cancilla +2
Amodal segmentation and amodal content completion require using object priors to estimate occluded masks and features of objects in complex scenes. Until now, no data has provided…
An Analysis of Data Transformation Effects on Segment Anything 2
Clayton Bromley, Alexander Moore, Amar Saini +2
Video object segmentation (VOS) is a critical task in the development of video perception and understanding. The Segment-Anything Model 2 (SAM 2), released by Meta AI, is the curre…
Addressing Issues with Working Memory in Video Object Segmentation
Clayton Bromley, Alexander Moore, Amar Saini +2
Contemporary state-of-the-art video object segmentation (VOS) models compare incoming unannotated images to a history of image-mask relations via affinity or cross-attention to pre…