SgVA-CLIP: Semantic-Guided Visual Adapting of Vision-Language Models for Few-Shot Image Classification.
Fang PengXiaoshan YangLinhui XiaoYaowei WangChangsheng XuPublished in: IEEE Trans. Multim. (2024)
Keyphrases
- language model
- image classification
- visual features
- low level features
- visual information
- language modeling
- key frames
- n gram
- semantic content
- document retrieval
- visual content
- image annotation
- query expansion
- probabilistic model
- image representation
- speech recognition
- language modelling
- statistical language models
- information retrieval
- test collection
- bag of words
- feature extraction
- retrieval model
- relevance model
- video shots
- low level
- context sensitive
- smoothing methods
- ad hoc information retrieval
- vector space model
- computer vision
- image features
- visual words
- high level
- semantic information
- language model for information retrieval
- semantic similarity
- image retrieval
- language models for information retrieval
- text mining
- query specific
- natural language