Derived from cvml-nus/assembly101 (Sener et al., "Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities", CVPR 2022), licensed CC BY-NC 4.0 and gated by its authors. This derivative keeps that licence: non-commercial use only, with attribution to the original dataset and paper; please also accept the original dataset's terms. Access to this repository is gated likewise. Contents: per camera view, every stride-th decoded frame (stride = ceil(fps) // 4: 15 at 60 fps, i.e. 4 fps), short side resized to 256 px (aspect kept, antialiased bilinear), JPEG quality 90, in the TAS frame-cache "jpeg" format: /.s.ss256.jpg.bin (the JPEGs back to back) +.jpg.idx.npy…
Independent publisher
Allen Peng
Moose27
Models in Library0
Datasets in Library1
Models on Hugging Face—
Followers—
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.
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.