Egocentric-video-based construction quality supervision (EgoConQS): Application of automatic key activity queries
Bibliographic record
Abstract
Construction quality supervision is essential for project success and safety. Traditional methods relying on manual inspections and paper records are time-consuming, error-prone, and difficult to verify. In-process construction quality supervision offers a more direct and effective approach. Recent advancements in computer vision and egocentric video analysis present opportunities to enhance these processes. This paper introduces the use of key activity queries on egocentric video data for construction quality supervision. A framework, Egocentric Video-Based Construction Quality Supervision (EgoConQS), is developed using a video self-stitching graph network to identify key activities in egocentric videos. EgoConQS facilitates efficient monitoring and quick review of key activity frames. Empirical evaluation with real-world data demonstrates an average recall of 35.85 % and a mAP score of 6.07 %, highlighting the potential of key activity queries for reliable and convenient quality supervision. • Proposed key activity queries on egocentric video data for construction quality supervision. • Introduced a video self-stitching graph network approach to obtain key activities. • Proposed activity taxonomy and annotation for construction quality supervision. • Experimentally confirmed the efficacy of the framework on real-world construction data.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.000 |
| 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".