GLIPv2: Unifying Localization and Vision-Language Understanding.
Haotian ZhangPengchuan ZhangXiaowei HuYen-Chun ChenLiunian Harold LiXiyang DaiLijuan WangLu YuanJenq-Neng HwangJianfeng GaoPublished in: CoRR (2022)
Keyphrases
- language understanding
- natural language understanding
- dialogue management
- language processing
- vision system
- natural language
- semantic interpretation
- dialogue system
- spoken dialogue systems
- general knowledge
- contextual constraints
- cognitive psychology
- information retrieval
- speech acts
- semantic analysis
- human computer interaction
- computer science
- metadata
- artificial intelligence