Search Results for author:
Found 4 papers, 2 papers with code
VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation
We begin with a simple premise: pose estimators often predict incoherent poses for out-of-distribution samples.
Transformer-based Flood Scene Segmentation for Developing Countries
The effects are more extensive and longer-lasting in high-population and low-resource developing countries.
Ranked #1 on
Semantic Segmentation
on Mila Simulated Floods
YouMVOS: An Actor-Centric Multi-Shot Video Object Segmentation Dataset
Many video understanding tasks require analyzing multi-shot videos, but existing datasets for video object segmentation (VOS) only consider single-shot videos.
MRSCAtt: A Spatio-Channel Attention-Guided Network for Mars Rover Image Classification
To necessitate the use of spatial and channel attention, we perform an ablation study to show the effectiveness of each of the components.
