ABaldrati

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

CLIP-ReID

Official implementation for "CLIP-ReID: Exploiting Vision-Language Model for Image Re-identification without Concrete Text Labels" (AAAI 2023)

cores-compatibility

This repo is the official implementation of "CoReS: Compatible Representations via Stationarity" Niccolò Biondi, Federico Pernici, Matteo Bruni, and Alberto Del Bimbo, IEEE TPAMI

CompoDiff

Official Pytorch implementation of "CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion"

Personalize-SAM

Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds

ade-czsl

[CVPR 2023] Learning Attention as Disentangler for Compositional Zero-shot Learning

vision-language-models-are-bows

Experiments and data for the paper "When and why vision-language models behave like bags-of-words, and what to do about it?" Oral @ ICLR 2023

open_clip

An open source implementation of CLIP.

BlackVIP

Official implementation for CVPR'23 paper "BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning"

Vesper

WebGL + Three.js implementation of Kenny Mitchell's post-processing algorithm for volumetric light scattering rendering.

ML-Papers-of-the-Week

🔥Highlighting the top ML papers every week.

pacscore

Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation. CVPR 2023

VATr

SmartRetrievalArtDemo

ReInHerit Smart Retrieval - NoisyArt dataset demo

NEFER

[CVPR 2023] NEFER a Dataset for Neuromorphic Event-based Facial Expression Recognition

SEARLE

[ICCV 2023] - Zero-shot Composed Image Retrieval with Textual Inversion

CIRR

Official repository of ICCV 2021 - Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models

cores-compatibility

This repo is the official implementation of "CoReS: Compatible Representations via Stationarity" Niccolò Biondi, Federico Pernici, Matteo Bruni, and Alberto Del Bimbo, IEEE TPAMI

CIRCO

[ICCV 2023] - Composed Image Retrieval on Common Objects in context (CIRCO) dataset

analog-video-restoration

[ACM MM 2022 - Demo] Restoration of Analog Videos Using Swin-UNet

General-GPT

FAME-ViL

[CVPR 2023 (Highlight)] FAME-ViL: Multi-Tasking V+L Model for Heterogeneous Fashion Tasks

FICE

Text-Conditioned Fashion Image Editing

clean-fid

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

meshed-memory-transformer

Meshed-Memory Transformer for Image Captioning. CVPR 2020

composed_image_retrieval

fastdup

fastdup is a powerful free tool designed to rapidly extract valuable insights from your image & video datasets. Assisting you to increase your dataset images & labels quality and reduce your data operations costs at an unparalleled scale.

Synthetic-Social-Agents-Dataset

rps

Simple Rock-Paper-Scissors server implemented in Django

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models