CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
仓库
m-bain 的仓库
Story-Based Retrieval with Contextual Embeddings. Largest freely available movie video dataset. [ACCV'20]
Condensed Movies Challenge 2021
LAVIS - A One-stop Library for Language-Vision Intelligence
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
Simple Diarization model
Mapping a variable-length sentence to a fixed-length vector using BERT model
A Clip-Hitchiker's Guide to Long Video Retrieval [Arxiv 2022]
Video embeddings for retrieval - code for the paper "Use What You Have: Video retrieval using representations from collaborative experts"
Conceptual 12M is a dataset containing (image-URL, caption) pairs collected for vision-and-language pre-training.
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [ICCV'21]
An open-source AI agent that brings the power of Gemini directly into your terminal.
Hydra is a framework for elegantly configuring complex applications
Automated Audiovisual Behaviour Recognition in Wild Primates
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2, MNASNet, Single-Path NAS, FBNet, and more
A pytorch implemented classifier for Multiple-Label classification
Multimodal language model benchmark, featuring challenging examples