MarvelOVD: Marrying Object Recognition and Vision-Language Models for Robust Open-Vocabulary Object Detection.
Kuo WangLechao ChengWeikai ChenPingping ZhangLiang LinFan ZhouGuanbin LiPublished in: CoRR (2024)
Keyphrases
- language model
- object detection
- object recognition
- computer vision
- language modeling
- document retrieval
- n gram
- probabilistic model
- spoken term detection
- speech recognition
- statistical language models
- retrieval model
- query expansion
- object categories
- information retrieval
- language modelling
- context sensitive
- vector space model
- test collection
- relevance model
- language models for information retrieval
- image understanding
- document ranking
- ad hoc information retrieval
- image features
- language model for information retrieval
- cross lingual
- translation model
- query specific
- smoothing methods
- query terms
- bag of words
- text classification