datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
ProactiveVideoQA
ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models
📄 arXiv Paper |
🖥️ Github Code |
📦 Data
Introduction
ProactiveVideoQA is the first comprehensive benchmark designed to evaluate a system's ability to engage in proactive interaction in multimodal dialogue settings.
Unlike traditional turn-by-turn dialogue systems, in proactive intraction model need to determine when to repsond during… See the full description on the dataset page: https://huggingface.co/datasets/wangyueqian/ProactiveVideoQA.VisualActBenchproactive-video-eval-suite
Proactive Video Evaluation Suite
This public repository contains four proactive/streaming-video evaluation collections with their original task annotations and packaged source videos. license: other is intentional: public accessibility does not replace the source-specific terms, and the annotations and upstream videos do not share one blanket license.
Contents
Directory
Rows found in the supplied source
Description
data/table2_timing_400/
400
Frozen… See the full description on the dataset page: https://huggingface.co/datasets/LCZZZZ/proactive-video-eval-suite.proactive-hoi-san-media