Reconnaissance des actions humaines à partir d'une séquence vidéo
Bibliographic record
Abstract
The work done in this master's thesis, presents a new system for the\n recognition of human actions from a video sequence. The system uses,\n as input, a video sequence taken by a static camera. A binary\n segmentation method of the the video sequence is first achieved, by a\n learning algorithm, in order to detect and extract the different people\n from the background. To recognize an action, the system then exploits\n a set of prototypes generated from an MDS-based dimensionality\n reduction technique, from two different points of view in the video\n sequence. This dimensionality reduction technique, according to two\n different viewpoints, allows us to model each human action of the\n training base with a set of prototypes (supposed to be similar for\n each class) represented in a low dimensional non-linear space. The\n prototypes, extracted according to the two viewpoints, are fed to a\n $K$-NN classifier which allows us to identify the human action that\n takes place in the video sequence. The experiments of our model\n conducted on the Weizmann dataset of human actions provide interesting\n results compared to the other state-of-the art (and often more\n complicated) methods. These experiments show first the\n sensitivity of our model for each viewpoint and its effectiveness to\n recognize the different actions, with a variable but satisfactory\n recognition rate and also the results obtained by the fusion of these\n two points of view, which allows us to achieve a high performance \n recognition rate.
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 | 0.001 |
| 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 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.003 |
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".