SynthDa is a framework designed to make synthetic data generation for human actions more usable and accessible. This is a pose-level augmentation framework that generates synthetic training videos by interpolating real and AI-generated poses. It increases minority-class coverage, helping to mitigate data scarcity for rare actions.
☆41Feb 25, 2026Updated last week
Alternatives and similar repositories for synthda
Users that are interested in synthda are comparing it to the libraries listed below
Sorting:
- A Python package for amino acid sequence analysis. Proforma 2.1 complicant.☆14Feb 6, 2026Updated last month
- 一个基于大模型MCP的智能旅行规划助手☆23May 31, 2025Updated 9 months ago
- (Unofficial) Implementation of the paper "Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS" Chen et al.☆13Dec 25, 2024Updated last year
- ☆13Dec 18, 2024Updated last year
- Implementation for "StyleGAN-Canvas: Augmenting StyleGAN3 for Real-Time Human-AI Co-Creation"☆12May 24, 2023Updated 2 years ago
- HemoPI2: Prediction of hemolytic activity of peptides against mammalian RBCs☆13Feb 10, 2025Updated last year
- TensorRT In Docker☆11Dec 7, 2024Updated last year
- Implementation of UniSpec, a deep learning model for predicting full fragment ion peptide spectra.☆12Feb 11, 2025Updated last year
- Project containing examples on how to use AiFi's Public Dataset on People Shopping☆11May 22, 2023Updated 2 years ago
- Implementation of SoundtStream from the paper: "SoundStream: An End-to-End Neural Audio Codec"☆13Jan 27, 2025Updated last year
- PGx supports proteogenomic intregration of mass spectrometry (MS) proteomics data with next generation sequencing (NGS) by mapping identi…☆10Jul 9, 2024Updated last year
- Web app for makeup transfer using Stable Diffusion☆10Sep 11, 2023Updated 2 years ago
- AMPDeep: Hemolytic Activity Prediction of Antimicrobial Peptides using Transfer Learning☆13Aug 15, 2022Updated 3 years ago
- ☆12Oct 14, 2024Updated last year
- Official implementation for “SafeMVDrive: Multi-view Safety-Critical Driving Video Synthesis in the Real World Domain”☆21Dec 11, 2025Updated 2 months ago
- ☆13Oct 6, 2022Updated 3 years ago
- Run Llama (LLM) on a Raspberry Pi.☆11Sep 4, 2023Updated 2 years ago
- ☆20Feb 13, 2026Updated 3 weeks ago
- [WACV 2026] PyTorch code for 4D-Animal.☆27Nov 18, 2025Updated 3 months ago
- Post-processing peptide de novo sequences to improve their accuracy☆10Nov 29, 2022Updated 3 years ago
- Virtual character locomotion system. See article“Motion Graphs”, Lucas Kovar, 2002☆12Mar 1, 2012Updated 14 years ago
- Official repository of "TDSD: Text-Driven Scene-Decoupled Weakly Supervised Video Anomaly Detection"☆11May 25, 2025Updated 9 months ago
- Peptide Correlation analysis☆11Oct 3, 2024Updated last year
- ☆14Nov 20, 2024Updated last year
- An open-source prediction framework for peptide ion collision cross section (CCS) values with python.☆15Oct 6, 2023Updated 2 years ago
- モリカトロン株式会社のテックブログで公開する（ちょっとした）ソースコードをシェアするリポジトリです。☆11Aug 1, 2024Updated last year
- Minimalist Vision with Freeform Pixels (ECCV 24)☆12Dec 30, 2024Updated last year
- A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling☆15Dec 5, 2023Updated 2 years ago
- A cage-based deformation for meshes in 2D.☆14Sep 8, 2018Updated 7 years ago
- We introduce EfficientRAG, an efficient retriever for multi-hop question answering. EfficientRAG iteratively generates new queries withou…☆17Mar 4, 2025Updated last year
- The Rust SDK library supports the call of Hikvision network cameras and MVS industrial cameras☆14Dec 21, 2024Updated last year
- Deep Steganalysis training script☆13May 1, 2025Updated 10 months ago
- Code to reproduce 'MOCCA: Multi-Layer One-Class Classification for Anomaly Detection'☆10Dec 12, 2021Updated 4 years ago
- [CVPR 2025] OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts☆17Apr 2, 2025Updated 11 months ago
- ☆18Jun 25, 2023Updated 2 years ago
- Explainable deep hypergraph learning modeling the peptide secondary structure prediction☆13Feb 27, 2023Updated 3 years ago
- [ACL 2023] VSTAR is a multimodal dialogue dataset with scene and topic transition information☆15Oct 27, 2024Updated last year
- C++/OpenGL tool for cage-based deformation, including functionality for cage generation. Originally developed as a fall 2019 term project…☆12Sep 10, 2020Updated 5 years ago
- Independent evaluation set construction for trustworthy ML models in biochemistry☆16Feb 18, 2026Updated 2 weeks ago