Current position: Home >> Scientific Research >> Paper Publications

MarvelOVD: Marrying Object Recognition and Vision-Language Models for Robust Open-Vocabulary Object Detection

Release Time:2024-12-25  Hits:

Indexed by: Conference Paper

Document Code: 471270

Date of Publication: 2025-01-01

Journal: COMPUTER VISION - ECCV 2024, PT XVII

Volume: 15075

Page Number: 106-122

ISSN: 0302-9743

Key Words: Open Vocabulary Object Detection; Pseudo Labeling

Prev One:Complementary and Contrastive Learning for Audio-Visual Segmentation

Next One:Multi-Modal Understanding and Generation for Object Tracking