vivit
Datasets
All datasets matching “vivit”vivit-b16x2-k400-postblock5-bf16-activations
ViViT-B/16x2 K400 post-block-5 bf16 activations
This data-only repository contains the frozen 10,400-clip activation cache used by NeonByte L5: 3,200 train, 800 dev, and 6,400 eval activations. Each .safetensors file stores the 3,137 × 768 bfloat16 hidden state after ViViT block 5 in CLS|tubelet(t,y,x)-row-major order.
The repository contains derived activations and provenance metadata only. It contains no raw video, frames, audio, model weights, executable scripts, or NeonByte… See the full description on the dataset page: https://huggingface.co/datasets/LieUr/vivit-b16x2-k400-postblock5-bf16-activations.violence-detection-vivit
Violence Detection Video Dataset (ViViT-ready)
This dataset contains preprocessed video clips (224x224) for violence detection, prepared for training ViViT transformer models with 10-frame clips.
🧾 Labels
0: Non Violence
1: Violence
📄 Source
The original dataset is the Real Life Violence Situations Dataset
by M. Elesawy, M. Hussein, and M. A. El Massih.
🧠 Features
Frame size: 224x224
Clips: 10 frames sampled every 2 frames
Train/Test split… See the full description on the dataset page: https://huggingface.co/datasets/MatteoGinesi/violence-detection-vivit.vivit-test