emadeldeen24/TS-TCC
[IJCAI-21] "Time-Series Representation Learning via Temporal and Contextual Contrasting"
This project helps scientists and researchers in domains like human activity recognition or medical diagnosis extract meaningful features from raw, unlabeled time-series data. It takes in raw time-series measurements (e.g., sensor readings, EEG signals) and outputs learned representations, which are simplified numerical summaries of the data. Researchers can then use these representations to train more accurate classification models, even with very little labeled data.
488 stars. No commits in the last 6 months.
Use this if you need to build a classification model for time-series data but have limited labeled examples, as it excels at learning from unlabeled data.
Not ideal if your data is not time-series based or if you already have abundant labeled data for direct supervised learning.
Stars
488
Forks
121
Language
Python
License
MIT
Category
Last pushed
Mar 31, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/emadeldeen24/TS-TCC"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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