A deep learning-based action recognition and confrontation analysis system for sparring players
Bibliographic record
Abstract
There is an increasing demand for assisted training techniques in the sport of sparring.In this paper, a sparring multiple recognition and analysis system is designed and fabricated for the movements of sparring sports and used to recognize and analyze the players' technical movements using the collected data and the model built using deep neural networks.The CNN-LSTM network is applied to extract the feature classification of the preprocessed sparring inertia data, and then the DTW algorithm is combined with the spatial distance classification method to realize the matching and recognition of sparring behaviors by stretching and compressing transformations of the time axis, effectively eliminating the distortion error in the time domain and obtaining the similar path with the shortest cumulative distance of the effective matches between different sequences.Experiments on the application of this paper's system were conducted in two groups of sparring players, and after 12 weeks of training intervention, the average confrontation striking speed of the experimental group progressed from 0.36 seconds before the experiment to 0.32 seconds after the experiment, and the average performance of the control group progressed from 0.38 seconds before the experiment to 0.36 seconds after the experiment, which indicates that although the traditional resistance training also has a positive impact on the training effect of sparring training, the training effect of this paper's system is more obvious The systematic training effect of this paper is more obvious.This paper makes an innovative exploration for the combination of sports programs such as sparring and cutting-edge information technology.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 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".