MamFusion adds a Mamba module and two temporal cross-attention modules to GMMFormer, achieving slight SumR improvements on three partially relevant video retrieval benchmarks.
Hierarchical cross-modal graph consistency learn- ing for video-text retrieval,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
MamFusion: Multi-Mamba with Temporal Fusion for Partially Relevant Video Retrieval
MamFusion adds a Mamba module and two temporal cross-attention modules to GMMFormer, achieving slight SumR improvements on three partially relevant video retrieval benchmarks.