Search Results for author:
Found 2 papers, 0 papers with code
Attention-based fusion of semantic boundary and non-boundary information to improve semantic segmentation
To the best of our knowledge, ours is the first work to show that boundary detection can improve semantic segmentation when fused through a semantic fusion gate (attention model).
On estimating gaze by self-attention augmented convolutions
In our experiments, results showed a decrease of the average angular error by 2. 38% when compared to state-of-the-art methods on the MPIIFaceGaze data set, and a second-place on the EyeDiap data set.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
