Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection

Documenti analoghi

• V3Det Challenge 2024 on Vast Vocabulary and Open Vocabulary Object Detection: Methods and Results
  di: Wang, Jiaqi, et al.
  Pubblicazione: (2024)
• CoMP: Continual Multimodal Pre-training for Vision Foundation Models
  di: Chen, Yitong, et al.
  Pubblicazione: (2025)
• DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs
  di: Meng, Lingchen, et al.
  Pubblicazione: (2024)
• CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection
  di: Sun, Zhichao, et al.
  Pubblicazione: (2025)
• Enhanced Object Detection: A Study on Vast Vocabulary Object Detection Track for V3Det Challenge 2024
  di: Wu, Peixi, et al.
  Pubblicazione: (2024)