Research on Human Action Detection and Recognition Methods Based on Interpretable Artificial Intelligence
Bibliographic record
Abstract
Deep learning-based methods can be combined with skeleton data, but they only consider the feature vectors formed by joint coordinates and do not extract the spatio-temporal dependencies between skeletons. In order to provide a more comprehensive detection and recognition of spatio-temporal relationships in human action sequences, this paper proposes a graph neural network-based human action detection and recognition method by combining YOLOv5, AlphaPose, and spatio-temporal graph convolutional network (ST-GCN) algorithms under the interpretable artificial intelligence (XAI) perspective. Firstly, the improved YOLOv5s target detection algorithm is used to get the human body detection frame and obtain the human body position information, then the AlphaPose pose estimation algorithm is used to obtain the coordinate information of the joint points of the human skeleton, and finally the improved ST-GCN algorithm is used to construct the spatio-temporal graph and extract the spatio-temporal dependencies between the joints to complete the human body action recognition. Through experimental verification, the method can accurately recognize human fall, running, kicking, and squatting actions on the dataset, with a recognition accuracy of 92.04%, and compared with the five baseline models, the method has higher recognition accuracy, with the values of each index greater than 91%, which can provide technical support for human behavior recognition.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".