# dvanderhaar/uj-aqa-cricketvision architecture

> Architecture diagram of the GitHub repository dvanderhaar/uj-aqa-cricketvision, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-04). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/dvanderhaar/uj-aqa-cricketvision
- Repository: https://github.com/dvanderhaar/uj-aqa-cricketvision

## Overview

This repository releases the CricketVision cricket-stroke dataset alongside research code for action-quality assessment. The documented workflow combines video-frame and pose-keypoint inputs, learns representations with a two-stream I3D-AE-LSTM autoencoder, and regresses body-part quality scores. Dataset clips include phase annotations. The source excerpts were unavailable, so the model stages and their links below reflect README-level documentation, not inspected notebook internals.

Main entry points: [`I3D_AE_LSTM _Code_Release/ViT_I3D.ipynb`](https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/I3D_AE_LSTM%20_Code_Release/ViT_I3D.ipynb) (Two-Stream Autoencoder), [`CricketVision_dataset_release/Videos.zip`](https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/CricketVision_dataset_release/Videos.zip) (Stroke Clips), [`CricketVision_dataset_release/JSON.zip`](https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/CricketVision_dataset_release/JSON.zip) (Phase Annotations), [`README.md`](https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/README.md) (AQA Benchmark)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["CricketVision Dataset"]
  node_clips[("Stroke Clips<br/>[Videos.zip]")]
  node_phases[("Phase Annotations<br/>[JSON.zip]")]
  node_annotation_spec["Annotation Structure"]
  node_dataset_attributes["Dataset Attributes"]
end

subgraph group_model["Assessment Model"]
  node_frames["Video Frames<br/>[ViT_I3D.ipynb]"]
  node_pose["Pose Keypoints<br/>[ViT_I3D.ipynb]"]
  node_autoencoder["Two-Stream Autoencoder<br/>[ViT_I3D.ipynb]"]
  node_regression["MLP Regressor<br/>[ViT_I3D.ipynb]"]
end

subgraph group_outcomes["Evaluation"]
  node_body_scores["Body-Part Scores<br/>[ViT_I3D.ipynb]"]
  node_benchmark["AQA Benchmark<br/>[README.md]"]
end

node_clips -->|"annotated with"| node_phases
node_clips -->|"provides video"| node_frames
node_frames -->|"input to"| node_autoencoder
node_pose -->|"input to"| node_autoencoder
node_autoencoder -->|"features to"| node_regression
node_regression -->|"predicts"| node_body_scores
node_body_scores -->|"evaluated by"| node_benchmark

click node_clips "https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/CricketVision_dataset_release/Videos.zip"
click node_phases "https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/CricketVision_dataset_release/JSON.zip"
click node_annotation_spec "https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/CricketVision_dataset_release/Annotation%20Structure.txt"
click node_dataset_attributes "https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/Dataset%20Attributes.md"
click node_frames "https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/I3D_AE_LSTM%20_Code_Release/ViT_I3D.ipynb"
click node_pose "https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/I3D_AE_LSTM%20_Code_Release/ViT_I3D.ipynb"
click node_autoencoder "https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/I3D_AE_LSTM%20_Code_Release/ViT_I3D.ipynb"
click node_regression "https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/I3D_AE_LSTM%20_Code_Release/ViT_I3D.ipynb"
click node_body_scores "https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/I3D_AE_LSTM%20_Code_Release/ViT_I3D.ipynb"
click node_benchmark "https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/README.md"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_clips,node_phases,node_annotation_spec,node_dataset_attributes toneBlue
class node_frames,node_pose,node_autoencoder,node_regression toneAmber
class node_body_scores,node_benchmark toneMint
```

## Components

### CricketVision Dataset

- [Stroke Clips](https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/CricketVision_dataset_release/Videos.zip): `CricketVision_dataset_release/Videos.zip`
- [Phase Annotations](https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/CricketVision_dataset_release/JSON.zip): `CricketVision_dataset_release/JSON.zip`
- [Annotation Structure](https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/CricketVision_dataset_release/Annotation%20Structure.txt): `CricketVision_dataset_release/Annotation Structure.txt`
- [Dataset Attributes](https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/Dataset%20Attributes.md): `Dataset Attributes.md`

### Assessment Model

- [Video Frames](https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/I3D_AE_LSTM%20_Code_Release/ViT_I3D.ipynb): `I3D_AE_LSTM _Code_Release/ViT_I3D.ipynb`
- [Pose Keypoints](https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/I3D_AE_LSTM%20_Code_Release/ViT_I3D.ipynb): `I3D_AE_LSTM _Code_Release/ViT_I3D.ipynb`
- [Two-Stream Autoencoder](https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/I3D_AE_LSTM%20_Code_Release/ViT_I3D.ipynb): `I3D_AE_LSTM _Code_Release/ViT_I3D.ipynb`
- [MLP Regressor](https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/I3D_AE_LSTM%20_Code_Release/ViT_I3D.ipynb): `I3D_AE_LSTM _Code_Release/ViT_I3D.ipynb`

### Evaluation

- [Body-Part Scores](https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/I3D_AE_LSTM%20_Code_Release/ViT_I3D.ipynb): `I3D_AE_LSTM _Code_Release/ViT_I3D.ipynb`
- [AQA Benchmark](https://github.com/dvanderhaar/uj-aqa-cricketvision/blob/main/README.md): `README.md`

## Connections

- Stroke Clips → Phase Annotations: annotated with (evidence: `README.md`)
- Stroke Clips → Video Frames: provides video (evidence: `README.md`)
- Video Frames → Two-Stream Autoencoder: input to (evidence: `README.md`)
- Pose Keypoints → Two-Stream Autoencoder: input to (evidence: `README.md`)
- Two-Stream Autoencoder → MLP Regressor: features to (evidence: `README.md`)
- MLP Regressor → Body-Part Scores: predicts (evidence: `README.md`)
- Body-Part Scores → AQA Benchmark: evaluated by (evidence: `README.md`)
