Dépôts

Dépôts de m-bain

31 dépôts pris en charge

m-bain/CLIPJupyter Notebook

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Dernier commit 25 juil. 2023

 (1 star) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

Story-Based Retrieval with Contextual Embeddings. Largest freely available movie video dataset. [ACCV'20]

Dernier commit 21 sept. 2022

 (206 stars) (32 forks) (0 issues indexées) (0 good first issues ouvertes)

Condensed Movies Challenge 2021

Dernier commit 21 sept. 2022

 (24 stars) (2 forks) (0 issues indexées) (0 good first issues ouvertes)
m-bain/LAVISJupyter Notebook

LAVIS - A One-stop Library for Language-Vision Intelligence

Dernier commit 17 août 2023

 (3 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

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)

Dernier commit 7 nov. 2023

 (2 stars) (1 fork) (0 issues indexées) (0 good first issues ouvertes)

Simple Diarization model

Dernier commit 16 avr. 2023

 (2 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

Mapping a variable-length sentence to a fixed-length vector using BERT model

Dernier commit 20 mars 2019

 (0 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

Dernier commit 9 juin 2021

 (2 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

A Clip-Hitchiker's Guide to Long Video Retrieval [Arxiv 2022]

Dernier commit 30 janv. 2024

 (10 stars) (1 fork) (0 issues indexées) (0 good first issues ouvertes)

Video embeddings for retrieval - code for the paper "Use What You Have: Video retrieval using representations from collaborative experts"

Dernier commit 16 févr. 2020

 (1 star) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

Conceptual 12M is a dataset containing (image-URL, caption) pairs collected for vision-and-language pre-training.

Dernier commit 21 avr. 2021

 (1 star) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [ICCV'21]

Dernier commit 19 mai 2022

 (376 stars) (46 forks) (0 issues indexées) (0 good first issues ouvertes)

An open-source AI agent that brings the power of Gemini directly into your terminal.

Dernier commit 6 juil. 2025

 (1 star) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

Hydra is a framework for elegantly configuring complex applications

Dernier commit 18 nov. 2021

 (0 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

Dernier commit 21 juil. 2023

 (0 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

Automated Audiovisual Behaviour Recognition in Wild Primates

Dernier commit 22 sept. 2021

 (1 star) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Dernier commit 30 janv. 2023

 (1 star) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2, MNASNet, Single-Path NAS, FBNet, and more

Dernier commit 17 mars 2021

 (1 star) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

A pytorch implemented classifier for Multiple-Label classification

Dernier commit 25 mai 2018

 (3 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

Multimodal language model benchmark, featuring challenging examples

Dernier commit 11 déc. 2024

 (1 star) (0 forks) (0 issues indexées) (0 good first issues ouvertes)