ViSiL learns video-to-video similarity by feeding a regional frame-to-frame similarity matrix into a convolutional network, improving state-of-the-art mAP on four video retrieval tasks.
Pattern- based near-duplicate video retrieval and localization on web- scale videos
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ViSiL: Fine-grained Spatio-Temporal Video Similarity Learning
ViSiL learns video-to-video similarity by feeding a regional frame-to-frame similarity matrix into a convolutional network, improving state-of-the-art mAP on four video retrieval tasks.