PHA-Net inserts shared prototype tokens into a three-level text-video alignment model and reports higher aggregate retrieval scores than the HBI baseline on four benchmarks, though several gains are small and unverified.
4100–4110
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PHA-Net: Prototype-based Hierarchical Alignment Network for Text-Video Retrieval
PHA-Net inserts shared prototype tokens into a three-level text-video alignment model and reports higher aggregate retrieval scores than the HBI baseline on four benchmarks, though several gains are small and unverified.