Independent publisher
Nguyen Ngoc Minh
nguyenminh04
Models in Library0
Datasets in Library3
Models on Hugging Face3
Followers—
Compare the published evidence
This profile connects the 3 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Reported licenses: other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Datasets
This repo holds everything needed to train and run the YouCook2 event segmentation + captioning model in im-xiaoming/UniAV-fixed. The model finds the steps of an uncut cooking video and writes one caption per step. YouCook2 (Zhou et al., AAAI 2018) has 2,000 cooking videos of 89 recipes, with step segments and one English sentence per step. 1,500 of the train + validation videos are still downloadable: 1,106 are used for training and 394 for validation. Annotations and caption vectors are in the git repo (data/youcookii/), not here. Each.npz holds three float16 arrays, with row i centred on i + 0.5 s: Extracted with tools/extractinternvideo2.py; text vectors with tools/embedcaptions.py…