Search Results for author:
Found 3 papers, 1 papers with code
Occlusion-Aware Deep Convolutional Neural Network via Homogeneous Tanh-transforms for Face Parsing
Based on homogeneous tanh-transforms, we propose an occlusion-aware convolutional neural network for occluded face parsing.
GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolution
GEAR achieves better efficiency by delegating tool grounding and execution to small language models (SLM) and LLM, respectively; while leveraging semantic and pattern-based evaluation at both question and answer levels for generalizable tool grounding.
A Robust Regression Approach for Background/Foreground Segmentation
Background/foreground segmentation has a lot of applications in image and video processing.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
