HSMR: A Head-Shoulder Mask Aided ResNet to Guide Focus of Re-Identification Implemented on Tour-Guide Robot
Bibliographic record
Abstract
For service robots, person re-identification (ReID) and multi-pedestrian tracking (MPT) are vital to get a person's location and link identities across frames. Though their accuracy keeps improving, most work lacks consideration of the application scenario, haunted by limited space, constrained power supply, and demands of the real-time response during human-robot interaction. Some ReID models learn trivial or unrelated features, inhibiting the downstream tasks. To solve these issues, the efficient and light-weighted Head-Shoulder Mask aided ResNet (HSMR) is proposed. This model applies multi-task learning to enhance the feature extraction performance in the training stage without extra computational load during inference. The auxiliary task fully uses head-shoulder information to guide the network and focuses on the head region, which contains the identity information. In experiments on the Tour-Guide Robot Data Base (TGRDB), HSMR earned results better than ResNet-18 on the ReID task and was superior to the recent two-stream method on the MPT task. On the mobile hardware, inference reaches an average of 15.2 FPS, three times faster than the two-stream method. The code is released at https://github.com/ZhYLin99/HSMR.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.004 |
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".