Pix2seq: A Language Modeling Framework for Object Detection.
Ting ChenSaurabh SaxenaLala LiDavid J. FleetGeoffrey E. HintonPublished in: ICLR (2022)
Keyphrases
- object detection
- language modeling framework
- document retrieval
- query expansion
- language model
- language modeling
- web search
- retrieval model
- relevance model
- computer vision
- topic modeling
- information retrieval
- topic models
- object recognition
- cross lingual
- xml retrieval
- smoothing methods
- retrieval effectiveness
- image understanding
- natural language
- relevance feedback
- active learning