iVQA
Emerging5papers using it
2022first seen
The 'iVQA' dataset/benchmark contains video clips paired with questions and answers, and it is used to evaluate models' performance in understanding and linking video content with corresponding textual queries.
Papers using iVQA (5)
- Viqagent: Zero-shot Video Question Answering Via Agent With Open-vocabulary Grounding ValidationLooking Beyond Visible Cues: Implicit Video Question Answering Via Dual-clue ReasoningBridging Vision Language Models and Symbolic Grounding for Video Question AnsweringZero-Shot Video Question Answering via Frozen Bidirectional Language
ModelsTowards Fast Adaptation of Pretrained Contrastive Models for
Multi-channel Video-Language Retrieval