ICON-Pose: Toward Egocentric Action Recognition for Intelligent Construction
Bibliographic record
Abstract
The working environment of construction workers is often hazardous and dynamic, leading not only to decline in worker productivity but also fatal accidents. Monitoring of workers’ behavior has thus gained increasing attention in the construction community for hazard monitoring, ergonomic analysis, and productivity estimation. Egocentric action recognition is robust and promising in identifying, localizing, and tracking workers’ actions. However, the insufficiency of publicly available datasets designated for egocentric construction workers’ action recognition hampers the training and evaluation of existing and newly developed deep-learning models. In this regard, this paper introduces ICON-Pose, the first open dataset built specifically for estimating construction workers’ poses via egocentric view. ICON-Pose offers hundreds of egocentric images and corresponding 2D workers’ body joints in 38 actions, categorized in 10 basic construction tasks, including “connect,” “cover,” “cut,” “dig,” “finish,” “place,” “position,” “spray,” “spread,” and “others.” ICON-Pose with the proposed pose estimation model demonstrates the ability in accurately depicting diverse construction workers’ poses as well as the robustness in describing unique construction poses. The proposed dataset is expected to invigorate and support artificial intelligence research in construction workers’ behavior tracking and has the potential of serving as a benchmark dataset for subsequent analysis.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.002 | 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 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".