Search Results for author:
Found 4 papers, 3 papers with code
360-Indoor: Towards Learning Real-World Objects in 360° Indoor Equirectangular Images
In this paper, our goal is to provide a standard dataset to facilitate the vision and machine learning communities in 360{\deg} domain.
Efficient Uncertainty Estimation for Semantic Segmentation in Videos
Uncertainty estimation in deep learning becomes more important recently.
Ranked #16 on
Semantic Segmentation
on CamVid
A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss
On the one hand, a simple extractive model can obtain sentence-level attention with high ROUGE scores but less readable.
Ranked #39 on
Abstractive Text Summarization
on CNN / Daily Mail
Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner
The domain critic assesses whether the generated sentences are indistinguishable from sentences in the target domain.
