Xuelin Zhu

multi-label classification (2) state space model (1) label correlation (1) graph propagation (1) compositional zero-shot learning (1) cross-modal interaction (1) text-guided learning (1) video denoising (1) video moment retrieval (1) co-occurrence matrix (1) visual feature aggregation (1) label-specific representation (1) fine-grained visual feature (1) state-object recognition (1) scene-aware learning (1) multimodal learning (1) label graph learning (1)