Event detection in coarsely annotated sports videos via parallel multi\n receptive field 1D convolutions
Bibliographic record
Abstract
In problems such as sports video analytics, it is difficult to obtain\naccurate frame level annotations and exact event duration because of the\nlengthy videos and sheer volume of video data. This issue is even more\npronounced in fast-paced sports such as ice hockey. Obtaining annotations on a\ncoarse scale can be much more practical and time efficient. We propose the task\nof event detection in coarsely annotated videos. We introduce a multi-tower\ntemporal convolutional network architecture for the proposed task. The network,\nwith the help of multiple receptive fields, processes information at various\ntemporal scales to account for the uncertainty with regard to the exact event\nlocation and duration. We demonstrate the effectiveness of the multi-receptive\nfield architecture through appropriate ablation studies. The method is\nevaluated on two tasks - event detection in coarsely annotated hockey videos in\nthe NHL dataset and event spotting in soccer on the SoccerNet dataset. The two\ndatasets lack frame-level annotations and have very distinct event frequencies.\nExperimental results demonstrate the effectiveness of the network by obtaining\na 55% average F1 score on the NHL dataset and by achieving competitive\nperformance compared to the state of the art on the SoccerNet dataset. We\nbelieve our approach will help develop more practical pipelines for event\ndetection in sports video.\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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".