ABaldrati/CLIP4Cir
[ACM TOMM 2023] - Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features
This tool helps fashion professionals, marketers, or anyone curating image collections to find specific images based on both a reference image and a text description of desired modifications. You input an existing image and a caption describing how you want to change it (e.g., "make it more formal," "change to stripes"), and it outputs a set of visually similar images from your catalog that match the specified edits. This is ideal for e-commerce, content creation, or visual asset management.
192 stars. No commits in the last 6 months.
Use this if you need to precisely retrieve images from a large collection by combining visual cues from a reference image with textual descriptions of desired alterations.
Not ideal if you only need to search for images using text keywords or if your image collection is very small and manually browsable.
Stars
192
Forks
16
Language
Python
License
MIT
Category
Last pushed
Sep 05, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ABaldrati/CLIP4Cir"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OBA-Research/VAAS
VAAS is an inference-first, research-driven library for image integrity analysis. It integrates...
deepmancer/clip-object-detection
Zero-shot object detection with CLIP, utilizing Faster R-CNN for region proposals.
kyegomez/CLIPQ
A simple implementation of a CLIP that splits up an image into quandrants and then gets the...
IvanAer/G-Universal-CLIP
4th place solution for the Google Universal Image Embedding Kaggle Challenge. Instance-Level...
joanrod/ocr-vqgan
OCR-VQGAN, a discrete image encoder (tokenizer and detokenizer) for figure images in...