Contrastive Learning for Sports Video: Unsupervised Player\n Classification
Bibliographic record
Abstract
We address the problem of unsupervised classification of players in a team\nsport according to their team affiliation, when jersey colours and design are\nnot known a priori. We adopt a contrastive learning approach in which an\nembedding network learns to maximize the distance between representations of\nplayers on different teams relative to players on the same team, in a purely\nunsupervised fashion, without any labelled data. We evaluate the approach using\na new hockey dataset and find that it outperforms prior unsupervised approaches\nby a substantial margin, particularly for real-time application when only a\nsmall number of frames are available for unsupervised learning before team\nassignments must be made. Remarkably, we show that our contrastive method\nachieves 94% accuracy after unsupervised training on only a single frame, with\naccuracy rising to 97% within 500 frames (17 seconds of game time). We further\ndemonstrate how accurate team classification allows accurate team-conditional\nheat maps of player positioning to be computed.\n
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".