🏆 #6,005 overall#1297 of 1,507 in Search & Retrieval

DRSY /MoTIS

[NAACL 2022]Mobile Text-to-Image search powered by multimodal semantic representation models(e.g., OpenAI's CLIP)

$ git clone https://github.com/DRSY/MoTIS.git
GitHub social preview for DRSY/MoTIS
Stars
127
127
This week
0 ★
0 this month
Forks
10
10
Language
Swift
License
None
Created
Aug 7, 2021
5.3 years old
Last push
May 11, 2023

Stars, last 30 days

Oct 15, 2026 → Nov 16, 2026
★ 127▲ +0★ 127

Categories

GitHub topics

More in Search & Retrieval

Search & Retrieval

rom1504/clip-retrieval

▲ +3 ★ this week

Easily compute clip embeddings and build a clip retrieval system with them

Jupyter NotebookMITupdated Mar 28, 2026
GitHub ↗★ 2.8K⑂ 234
Search & Retrieval

unum-cloud/UForm🔥 active

Distributed training & inference for multimodal perception: shared embeddings across text, images, video, audio, code & graphs from 64 to 1024 dimensions 🖼️

🧠 Natural Language Processing
CudaApache-2.0updated Nov 16, 2026
GitHub ↗★ 1.3K⑂ 76
Search & Retrieval

slavabarkov/tidy

▲ +2 ★ this week

Offline semantic Text-to-Image and Image-to-Image search on Android powered by quantized state-of-the-art vision-language pretrained CLIP model and ONNX Runtime inference engine

🧠 Natural Language Processing
KotlinGPL-3.0updated Mar 28, 2024
GitHub ↗★ 611⑂ 47
Search & Retrieval

liangjianshu/multimodal-image-retrieval

多模态检索实战:意图识别、Prompt 工程、Qwen LoRA、EmbeddingGemma 2 与 InfoNCE 对比学习。含真实演示、自有数据接入、训练评测及 RAG 检索组件学习指南。

PythonMITupdated Nov 5, 2026
GitHub ↗★ 128⑂ 0
Search & Retrieval

Egoist-Machines/LodeDB

▲ +4 ★ this week

World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated

PythonApache-2.0updated Oct 18, 2026
GitHub ↗★ 108⑂ 13

Data from GitHub · snapshot Nov 16, 2026