GLIPv2: Unifying Localization and Vision-Language Understanding.
Haotian ZhangPengchuan ZhangXiaowei HuYen-Chun ChenLiunian Harold LiXiyang DaiLijuan WangLu YuanJenq-Neng HwangJianfeng GaoPublished in: NeurIPS (2022)
Keyphrases
- language understanding
- natural language understanding
- dialogue management
- language processing
- vision system
- dialogue system
- semantic interpretation
- spoken dialogue systems
- contextual constraints
- natural language
- cognitive psychology
- general knowledge
- artificial intelligence
- knowledge representation
- collaborative learning