233 skills found · Page 3 of 8
abhilash1910 / ClusterTransformerTopic clustering library built on Transformer embeddings and cosine similarity metrics.Compatible with all BERT base transformers from huggingface.
GerardLiu96 / FECNetA Keras implementation of FECNet, which proposed in "A Compact Embedding for Facial Expression Similarity"
dapengchen123 / Video ReidWe plan to release our code in CVPR 2018 "Video Person Re-identification with Competitive Snippet-similarity Aggregation and Co-attentive Snippet Embedding"
Portkey-AI / MCP Tool FilterUltra-fast semantic tool filtering for MCP (Model Context Protocol) servers using embedding similarity. Reduce your tool context from 1000+ tools down to the most relevant 10-20 tools in under 10ms.
Ximilar-com / Tf Metric LearningMinimalistic TensorFlow2+ deep metric/similarity learning library with loss functions, miners, and utils as embedding projector.
zilliz-bootcamp / Image SearchThis project use VGG model to get image embeddings. Then Milvus is used to search the similarity images.
samzshi0529 / HanziNLPA NLP package for Chinese text：Preprocessing, Tokenization, Chinese Fonts, Word Embeddings, Text Similarity and Sentiment Analysis 轻量级中文自然语言处理软件包
uhh-lt / Path2vecLearning to represent shortest paths and other graph-based measures of node similarities with graph embeddings
yousef-rafat / MagnaMagna is an AI-powered embedding similarity search tool for searching within large documents.
m1nhengChen / SOPICode for ICASSP 2024 paper"Embedded Feature Similarity Optimization with Specific Parameter Initialization for 2D/3D Medical Image Registration"
handrew / Gpt MemoryUsing embeddings to create memory.
Birch-san / Imagebind Guided DiffusionGuide diffusion on ImageBind embedding similarity
zilliz-bootcamp / Audio SearchThis project use PANNs for audio tagging and sound event detection, and finally get audio embeddings. Then Milvus is used to search the similarity audio items.
adrianmfi / Git Semantic SimilaritySearch git commit messages by semantic similarity with embeddings from sentence-transformers
abhilash1910 / BERTSimilaritySentential Semantic Similarity measurement library using BERT Embeddings for spatial distance evaluation.
MahaThafar / Drug Target Interaction Prediciton MethodThis repository provides an implementation of the DTiGEMSplus tool, a network-based method for computational Drug-Target Interaction prediction using graph embedding, graph mining, and similarity-based techniques
swapnilg915 / Cosine Similarity Using EmbeddingsCode to find the distance/similarity between the 2 documents using several embeddings - 1. TF-IDF, 2. word2vec, 3. ELMO, 4. Universal Sentence Encoder, 5. Flair embeddings, 6. Spacy embeddings, 7. WMD (Word Movers Distance)
fm1320 / Song VibeAI song recommendations based on the feel of a song
GoogleCloudPlatform / PsearchAI-powered product search platform built on Google Cloud Platform (GCP). Leverages Spanner's hybrid search capabilities (vector similarity & text search), Vertex AI (Gemini & embedding APIs), and a microservices architecture (Cloud Run). Features AI-driven filter suggestions, content enrichment, and a rules engine. See README for details.
shilpar27 / Label Embeddings In Image ClassificationConvolutional Neural Networks (CNNs) are being widely used for various tasks in Computer Vision. We focus on the task of image classification particularly using CNNs with more focus on the relation or similarity between class labels. The similarity between labels is judged using label word embeddings and incorporated into the loss layer. We propose that shallower networks be learnt with more complex and structured losses, in order to gain from shorter training time and equivalent complexity. We train two variants of CNNs with multiple architectures , all limited to a maximum of ten convolution layers to obtain an accuracy of 93.27% on the Fashion-MNIST dataset and 86.40% on the CIFAR 10 dataset. We further probe the adversarial robustness of the model as well the classspecific behavior by visualizing the class confusion matrix.We also show some preliminary results towards extending a trained variant to zero-shot learning.
