<div align="center">

🦑 OctoNet Toolbox 🦑

The Ultimate Multi-Modal Human Activity Understanding Toolkit

---

🎯 Revolutionary Multi-Modal Dataset for Human Activity Understanding

Comprehensive sensor fusion • State-of-the-art benchmarks • Ready-to-use visualization tools

---

</div> <div align="center"> <img src="figs/octonet_overview.png" alt="OctoNet Dataset Overview - Multi-modal sensor data visualization" style="width: 100%; height: auto; border-radius: 10px; box-shadow: 0 4px 8px rgba(0,0,0,0.1);"> </div>

🚀 What's Inside This Toolbox

<div align="center">

✨ Comprehensive OctoNet Toolkit ✨

</div>

This powerful toolbox provides everything you need to work with the OctoNet dataset:

<table> <tr> <td align="center" width="50%">

🎨 Visualization Suite

• Interactive dataset exploration tools
• Multi-modal data visualization capabilities

</td> <td align="center" width="50%">

⚡ Benchmark Framework

• Reproducible benchmark implementations
• Benchmark results recordings

</td> </tr> </table> <div align="center">

🎯 Ready to dive into multi-modal human activity recognition? Let's get started!

</div>

---

---

<div align="center">

🎨 Part 1: Dataset Visualization & Exploration 🎨

Interactive Multi-Modal Data Analysis Suite

</div> <div align="center">

💡 💻 Recommended Environment: Run the code in Python Jupyter Notebook demo.ipynb for the best interactive experience!

</div>

---

📁 Dataset Structure Overview

<div align="center">

🗂️ Complete Directory Layout:

</div>

./dataset
├── mocap_csv_final          # Data: Final motion capture data in CSV format.
├── mocap_pose               # Data: Final motion capture data in npy format.
├── node_1                   # Data: Data related to multi-modal sensor node 1.
├── node_2                   # Data: Data related to multi-modal sensor node 2.
├── node_3                   # Data: Data related to multi-modal sensor node 3.
├── node_4                   # Data: Data related to multi-modal sensor node 4.
├── node_5                   # Data: Data related to multi-modal sensor node 5.
├── imu                      # Data: Inertial measurement unit data.
├── vayyar_pickle            # Data: vayyar mmWave radar data.
└── cut_manual.csv           # Manually curated data cuts.

<div align="center">

📊 Dataset Metadata & Statistics

</div> <details> <summary>🔍 **📋 Click to View Complete OctoNet Dataset Metadata**</summary> <div align="center">

📝 Key Information:

</div>

📌 Important Notes:

• 👥 Gender Classification: Male (M) and Female (F) participants
• 🏃 Activity Types: PA&F indicates subjects performed both Programmed Aerobics and Freestyle activities
• ⭐ Special Marking: Asterisk (*) denotes subjects who performed only Programmed Aerobics (no Freestyle)
• 🏠 Scene Mapping: Scene 1: IDs 1-99, Scene 2: IDs 101-199, Scene 3: IDs 201-299

</details>

| User (Gender) | Exp ID | Scene 1: Activity IDs | Scene 1: PA&F | Scene 2: Activity IDs | Scene 2: PA&F | Scene 3: Activity IDs | Scene 3: PA&F | |---------------|--------------------------|:---------------------:|:-------------:|:---------------------:|:-------------:|:-----------------------:|:-------------:| | 1 (M) | 1, 11, 101, 201 | all 62 | ✓ | 1–23 | | 1–23, 57–62 | ✓* | | 2 (M) | 2, 12, 102, 112, 202 | all 62 | ✓ | 9–29 | ✓ | 9–29 | | | 3 (M) | 3, 13, 113, 213 | all 62 | ✓ | | ✓ | | ✓ | | 4 (F) | 4, 14, 104, 114, 204 | all 62 | ✓ | 30–56 | ✓ | 30–56 | | | 5 (M) | 5, 15, 115, 215 | all 62 | ✓ | | ✓ | | ✓ | | 6 (F) | 6, 16 | all 62 | ✓ | | | | | | 7 (M) | 7, 17, 117, 217 | all 62 | ✓ | | ✓ | | ✓ | | 8 (M) | 8, 18, 108, 118 | all 62 | ✓ | 24–62 | ✓ | 24–62 | | | 9 (M) | 9 | all 62 | | | | | | | 10 (M) | 10, 20, 120, 220 | all 62 | ✓ | | ✓ | | ✓ | | 11 (F) | 21 | | ✓ | | | | | | 12 (M) | 22 | | ✓ | | | | | | 13 (F) | 23 | | ✓ | | | | | | 14 (M) | 24 | | ✓ | | | | | | 15 (F) | 25 | | ✓ | | | | | | 16 (F) | 26 | | ✓ | | | | | | 17 (F) | 27 | | ✓ | | | | | | 18 (F) | 28 | | ✓ | | | | | | 19 (F) | 29 | | ✓ | | | | | | 20 (F) | 30, 230 | | ✓ | | | | ✓ | | 21 (M) | 31 | | ✓ | | | | | | 22 (M) | 32 | | ✓ | | | | | | 23 (F) | 33 | | ✓ | | | | | | 24 (M) | 34 | | ✓ | | | | | | 25 (M) | 35 | | ✓ | | | | | | 26 (M) | 36 | | ✓ | | | | | | 27 (M) | 37 | | ✓ | | | | | | 28 (F) | 38 | | ✓ | | | | | | 29 (F) | 39 | | ✓ | | | | | | 30 (M) | 40 | | ✓ | | | | | | 31 (M) | 41 | | ✓ | | | | | | 32 (F) | 42 | | ✓ | | | | | | 33 (F) | 43 | | ✓ | | | | | | 34 (F) | 44 | | ✓ | | | | | | 35 (M) | 45 | | ✓ | | | | | | 36 (M) | 46 | | ✓ | | | | | | 37 (M) | 47 | | ✓ | | | |