Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval

Documenti analoghi

• Object-Aware Query Perturbation for Cross-Modal Image-Text Retrieval
  di: Sogi, Naoya, et al.
  Pubblicazione: (2024)
• Generalized Contrastive Learning for Multi-Modal Retrieval and Ranking
  di: Zhu, Tianyu, et al.
  Pubblicazione: (2024)
• Multimedia-Aware Question Answering: A Review of Retrieval and Cross-Modal Reasoning Architectures
  di: Raja, Rahul, et al.
  Pubblicazione: (2025)
• Dual Pose-invariant Embeddings: Learning Category and Object-specific Discriminative Representations for Recognition and Retrieval
  di: Sarkar, Rohan, et al.
  Pubblicazione: (2024)
• SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models
  di: Sivakumar, Anushka, et al.
  Pubblicazione: (2025)