OVD: Fine-grained Visual-Text Prompt-Driven Self-Training for Open-Vocabulary Object Detection.
Yanxin LongJianhua HanRunhui HuangXu HangYi ZhuChunjing XuXiaodan LiangPublished in: CoRR (2022)
Keyphrases
- fine grained
- object detection
- coarse grained
- access control
- keywords
- text documents
- visual features
- visual information
- tightly coupled
- computer vision
- text mining
- massively parallel
- information retrieval
- co occurrence
- semantic information
- training set
- text processing
- data provenance
- database
- text categorization
- semi supervised learning
- text classification
- machine learning
- databases