tomoyoshki/focal
Pytorch Implementation of FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space
This tool helps researchers and engineers analyze complex real-world events captured by multiple sensors over time. It takes raw, multimodal time-series data (like acoustic and seismic signals from moving vehicles) and processes it to extract meaningful patterns, even when labeled data is scarce. The output is a highly accurate classification or detection model that can identify event types, distances, or speeds, useful for defense, smart city planning, or environmental monitoring.
No commits in the last 6 months.
Use this if you need to build robust classification models from diverse time-series sensor data, especially when you have limited labeled examples for training.
Not ideal if your data consists of single-modality signals, or if you are not working with time-series data where temporal context is crucial.
Stars
35
Forks
4
Language
Python
License
MIT
Category
Last pushed
Jan 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tomoyoshki/focal"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification