LVMAE-pytorch

★ 55 Open GitHub ↗

Implementation of the proposed LVMAE, from the paper, Extending Video Masked Autoencoders to 128 frames, in Pytorch

Explore Similar Repositories

OmniAgent : OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Qwen2.5-VL-72B with 73% fewer frames on LVBench.
Video-frame-prediction-by-multi-scale-GAN : Using a GAN based multi scale CNN to predict future frames of a video. Implemented in Chainer
llm-video-frames : LLM fragment plugin to turn a video into images of different frames
CanvasVideoRecorder : A little tool to record frames from the HTML5 canvas element into a video file
video_frame_remover : Remove frames and borders around videos
// repository documentation