2025
Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval
NeurIPS 2025poster
Recent progress in text–video retrieval has been largely driven by contrastive learning. However, existing methods often overlook the effect of the modality gap, which causes anchor representations to undergo in-place optimization (i.e., optimization tension) that limits their alignment capacity. Mo…