conftrace_

visual feature enrichment

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

clip visual representation (1) multimodal compensation (1) language decoder contextualization (1) feature ablation (1) text-driven augmentation (1) manifold augmentation (1) language decoder (1) semantic perturbation (1) vision-language model (1) cross-modal transfer (1)

Papers

LLMs Can Compensate for Deficiencies in Visual Representations EMNLP 2025 TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation ICCV 2023