Search Results for author:
Found 2 papers, 0 papers with code
Attention cannot be an Explanation
Motivated by this, we ask a follow-up question: "Assuming that we only consider the tasks where attention weights correlate well with feature importance, how effective are these attention based explanations in increasing human trust and reliance in the underlying models?".
Discourse Analysis for Evaluating Coherence in Video Paragraph Captions
We also introduce DisNet, a novel dataset containing the proposed visual discourse annotations of 3000 videos and their paragraphs.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
