MSRVTT-QA

The 'MSRVTT-QA' dataset is a benchmark that contains video clips paired with questions and answers, used to evaluate the performance of models in the task of video question answering (VideoQA).

Papers using MSRVTT-QA (4)

ResNetVLLM -- Multi-modal Vision LLM for the Video Understanding Task2025Zero-Shot Video Question Answering via Frozen Bidirectional Language Models2022 · 64 citesVideo Question Answering Using CLIP-Guided Visual-Text Attention2023 · 1 citesAudio-Visual LLM for Video Understanding2023 · 1 cites