A Simple LLM Framework for Long-Range Video Question-Answering.
Ce ZhangTaixi LuMd Mohaiminul IslamZiyang WangShoubin YuMohit BansalGedas BertasiusPublished in: CoRR (2023)
Keyphrases
- question answering
- long range
- short range
- natural language processing
- information retrieval
- information extraction
- question classification
- natural language
- conditional random fields
- natural language questions
- video data
- semantic roles
- passage retrieval
- long range correlations
- qa clef
- video frames
- named entities
- higher order
- video sequences
- image segmentation
- multimedia
- artificial intelligence