AV1 motion vectors filtered by cosine consistency yield dense sub-pixel correspondences that support structure-from-motion on short video clips with lower CPU cost and higher match density than sequential SIFT.
Efficient feature extraction, encoding, and classification for action recognition,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2verdicts
UNVERDICTED 2representative citing papers
AV1 motion vectors serve as a high-fidelity warm-start for the RAFT optical flow network, delivering a four-fold speedup in convergence with only minor end-point error increase compared to standard initialization.
citing papers explorer
-
Leveraging AV1 motion vectors for Fast and Dense Feature Matching
AV1 motion vectors filtered by cosine consistency yield dense sub-pixel correspondences that support structure-from-motion on short video clips with lower CPU cost and higher match density than sequential SIFT.
-
AV1 Motion Vector Fidelity and Application for Efficient Optical Flow
AV1 motion vectors serve as a high-fidelity warm-start for the RAFT optical flow network, delivering a four-fold speedup in convergence with only minor end-point error increase compared to standard initialization.