What is the Visual Cognition Gap between Humans and Multimodal LLMs?
Xu CaoBolin LaiWenqian YeYunsheng MaJoerg HeintzJintai ChenJianguo CaoJames M. RehgPublished in: CoRR (2024)
Keyphrases
- human cognition
- cognitive systems
- cross modal
- visual features
- human vision
- human intelligence
- artificial intelligence
- real time
- low level
- multi modal
- visual information
- human observers
- multimodal information
- multimodal interaction
- human behavior
- cognitive science
- information processing
- visual cues
- visual search
- visual processing
- computer vision