A cross-game intent-forecasting benchmark: from tournament commentary (+ video frames), predict the next-stage gameplay intention of professional players, across repo's root corresponds to the local data/ directory. To use with the code, clone this repo into your code checkout as data/ (or symlink it there): - 31 / 47 matches annotated (intents/.intent.json); 4 games complete at 5 (dota, lol, pubg, wc3). - 16 matches pending ASR+intent — their VODs are already in raw/; pipeline rerun on a GPU machine. - See DATASETSTATUS.md for the per-game done/missing breakdown + migration checklist. Each match → {game}/{stem}/: - match.json — metadata (vodurl, vodmatchstart, duration, recordstatus…
Organization
Game Intention
GameIntention
Models in Library0
Datasets in Library1
Models on Hugging Face—
Followers3
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Text classification.
Reported licenses: cc-by-nc-4.0. 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.