QuerYD: A video dataset with high-quality text and audio narrations
This dataset addresses the problem of limited high-quality, detailed, and temporally aligned video annotations for researchers in video understanding, offering a resource for training and benchmarking models.
This paper introduces QuerYD, a new large-scale video dataset for retrieval and event localization. It uniquely features two audio tracks per video: original audio and high-quality spoken descriptions of visual content, derived from YouDescribe, a project providing voiced narrations for visually-impaired individuals.
We introduce QuerYD, a new large-scale dataset for retrieval and event localisation in video. A unique feature of our dataset is the availability of two audio tracks for each video: the original audio, and a high-quality spoken description of the visual content. The dataset is based on YouDescribe, a volunteer project that assists visually-impaired people by attaching voiced narrations to existing YouTube videos. This ever-growing collection of videos contains highly detailed, temporally aligned audio and text annotations. The content descriptions are more relevant than dialogue, and more detailed than previous description attempts, which can be observed to contain many superficial or uninformative descriptions. To demonstrate the utility of the QuerYD dataset, we show that it can be used to train and benchmark strong models for retrieval and event localisation. Data, code and models are made publicly available, and we hope that QuerYD inspires further research on video understanding with written and spoken natural language.