Vision CAIR Research Group, KAUST

MiniGPT-4

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

ChatCaptioner

Official Repository of ChatCaptioner

MiniGPT4-video

Official code for MiniGPT4-video

VisualGPT

VisualGPT, CVPR 2022 Proceeding, GPT as a decoder for vision-language models

3DCoMPaT-v2

3DCoMPaT++: An improved large-scale 3D vision dataset for compositional recognition

LTVRR

RelTransformer

MammalNet

3DCoMPaT

Official repository for the 3DCoMPaT dataset (ECCV2022 Oral)

artemis-v2

Code for the paper: It is Okay to Not Be Okay: Overcoming Emotional Bias in Affective Image Captioning by Contrastive Data Collection

AF-Guide

Official repository of Action-Free Guide

saai-factory-tutorial-creative-ai

Creative AI for Visual Art and Music slides and demos.

CWAN

Creative Walk Adversarial Networks: Novel Art Generation with Probabilistic Random Walk Deviation from Style Norms

HalentNet

affectiveVisDial

CIZSLv2

CIZSL++: Creativity Inspired Generative Zero-Shot Learning. T-PAMI under review.

WAGA

Code for Wölfflin Affective Generative Analysis paper published in ICCC 2021

cs326-few-shot-classification

CS326 Practical assignment #2: few-shot classification

artelingo

GRaWD

Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation. CVPR 2022 Workshop, ICCC 2022.

UnlikelihoodMotionForecasting

Affective-and-Creative-AI

VisionCAIR Affective and Creative AI Research

affective-vision-language

CIZSL

Creativity Inspired Zero-Shot Learning

feelings

GDPP

Generator loss to reduce mode-collapse and to improve the generated samples quality.

lifelong_fact_learning

Zero-Shot-Learning

VisionCAIR Zero-Shot Learning Research