Search Results for author:
Found 4 papers, 1 papers with code
VLASE: Vehicle Localization by Aggregating Semantic Edges
In this paper, we propose VLASE, a framework to use semantic edge features from images to achieve on-road localization.
Localization-Aware Active Learning for Object Detection
Active learning - a class of algorithms that iteratively searches for the most informative samples to include in a training dataset - has been shown to be effective at annotating data for image classification.
Detecting and Grouping Identical Objects for Region Proposal and Classification
Often multiple instances of an object occur in the same scene, for example in a warehouse.
Attention-Based Multimodal Fusion for Video Description
Currently successful methods for video description are based on encoder-decoder sentence generation using recur-rent neural networks (RNNs).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
