Reproduce “Key Frame Extraction with Attention Based Deep Neural Networks” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Samed Arslan, Senem Tanberk
The authors propose a video keyframe method that learns frame features with an attention-equipped autoencoder, groups them using k-means, and selects the frame nearest each cluster center. On TVSum, they evaluate keyframe detection as binary frame classification against expert-defined intervals. The keyframe class receives an F1 score of 0.77, with precision 0.78 and recall 0.75; no baseline comparison establishes an advantage.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.