VideoPrism: A Foundational Visual Encoder for Video Understanding
This provides a foundational model for video understanding, benefiting researchers and practitioners across domains like web video QA and scientific CV.
The paper tackles the problem of developing a general-purpose video encoder for diverse video understanding tasks by pretraining on a large heterogeneous corpus, achieving state-of-the-art performance on 31 out of 33 benchmarks.
We introduce VideoPrism, a general-purpose video encoder that tackles diverse video understanding tasks with a single frozen model. We pretrain VideoPrism on a heterogeneous corpus containing 36M high-quality video-caption pairs and 582M video clips with noisy parallel text (e.g., ASR transcripts). The pretraining approach improves upon masked autoencoding by global-local distillation of semantic video embeddings and a token shuffling scheme, enabling VideoPrism to focus primarily on the video modality while leveraging the invaluable text associated with videos. We extensively test VideoPrism on four broad groups of video understanding tasks, from web video question answering to CV for science, achieving state-of-the-art performance on 31 out of 33 video understanding benchmarks. Our models are released at https://github.com/google-deepmind/videoprism.