ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization

Documenti analoghi

• ViFi-ReID: A Two-Stream Vision-WiFi Multimodal Approach for Person Re-identification
  di: Mao, Chen, et al.
  Pubblicazione: (2024)
• Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval
  di: Wang, Yifan, et al.
  Pubblicazione: (2025)
• Capability-aware Prompt Reformulation Learning for Text-to-Image Generation
  di: Zhan, Jingtao, et al.
  Pubblicazione: (2024)
• Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval
  di: Xiao, Jian, et al.
  Pubblicazione: (2025)
• Offline Evaluation of Set-Based Text-to-Image Generation
  di: Arabzadeh, Negar, et al.
  Pubblicazione: (2024)