AI RESEARCH
StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrieval
arXiv CS.CV
•
ArXi:2601.20597v2 Announce Type: replace Continual Text-to-Video Retrieval (CTVR) is a challenging multimodal continual learning setting, where models must incrementally learn new semantic categories while maintaining accurate text-video alignment for previously learned ones, thus making it particularly prone to catastrophic forgetting. A key challenge in CTVR is feature drift, which manifests in two forms: intra-modal feature drift caused by continual learning within each modality, and non-cooperative feature drift across modalities that leads to modality misalignment.