research
∙
10/24/2022
GliTr: Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction
Many online action prediction models observe complete frames to locate a...
share
research
∙
04/12/2022
Few-shot Learning with Noisy Labels
Few-shot learning (FSL) methods typically assume clean support sets with...
research
∙
04/01/2022
Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes
Most hard attention models initially observe a complete scene to locate ...
research
∙
11/15/2021
A Probabilistic Hard Attention Model For Sequentially Observed Scenes
A visual hard attention model actively selects and observes a sequence o...
research
∙
04/01/2021
Visual Attention in Imaginative Agents
We present a recurrent agent who perceives surroundings through a series...
research
∙
06/22/2018