sportsvision/soccer-qa-4b

Soccer QA 4B - Soccer Video Question Answering Model

⚠️ RESEARCH USE ONLY - NON-COMMERCIAL LICENSE

Soccer QA 4B is a unified video question-answering model specifically designed for soccer video understanding.

Model Description

This model can answer questions about soccer videos by analyzing visual content and generating natural language responses.

Example:

• Input: Video + "What unfolded during the game in the video?"
• Output: "During the game, there was a foul committed by a player from the yellow-jerseyed team, leading to a yellow card being issued..."

Architecture

• Vision Encoder: DWT-VJEPA2-based video encoder (vit_giant, 1408 dim)
• Text Model: LLaMA 3.2-3B with LoRA fine-tuning
• Vision-Text Bridge: Learned projection layer (1408 → 2048 → 3072)
• Specialization: Fine-tuned on soccer video QA data

Usage (Helper functions are in repo)

from soccer_qa_inference import SoccerQA

model = SoccerQA("/path/to/model")
answer = model.ask("video.mp4", "Was this a Foul?", max_tokens=45)
print(answer)

Model Details

• Parameters: ~4B total
• Input: Video files (16 frames, 256x256) + text questions
• Output: Natural language answers
• Domain: Soccer/football video analysis
• Context: Handles complex game situations, player actions, fouls, etc.

Training Data

• Soccer video clips with question-answer pairs
• Covers various game situations: fouls, shots, saves, player actions
• Annotated with detailed descriptions of game events

Limitations

• Research use only, no commercial applications
• Optimized specifically for soccer content
• May not generalize well to other sports or video domains
• Requires high-quality video input for best results

License

CC-BY-NC-4.0 - Research use only, no commercial applications permitted.

Citation

@misc{soccer-qa-4b-2025,
  title={Soccer QA 4B: Video Question Answering for Soccer Analysis},
  author={Varun Kodathala, Sports Vision},
  year={2025},
  note={Research model for soccer video understanding}
}