ViFusion combines dynamic tensor fusion with hierarchical AllReduce to speed up distributed video feature indexing, but the 8-22x throughput claim is an overstatement of bandwidth gains over a self-defined baseline.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MM 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
ViFusion: In-Network Tensor Fusion for Scalable Video Feature Indexing
ViFusion combines dynamic tensor fusion with hierarchical AllReduce to speed up distributed video feature indexing, but the 8-22x throughput claim is an overstatement of bandwidth gains over a self-defined baseline.