AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering.
Xiuyuan ChenYuan LinYuchen ZhangWeiran HuangPublished in: CoRR (2023)
Keyphrases
- question answering
- language model
- open ended
- passage retrieval
- information retrieval
- video data
- video content
- multimedia
- video sequences
- sentence retrieval
- language modeling
- natural language
- question classification
- speech transcripts
- named entities
- document retrieval
- key frames
- learning outcomes
- video retrieval
- speech recognition
- retrieval model
- n gram
- query expansion
- text classification
- information extraction
- bayesian networks