Proceedings of the 1st ACM workshop on Vision networks for behavior analysis
Bibliographic record
Abstract
It is our great pleasure to welcome you to the 1st ACM Workshop on Vision Networks for Behaviour Analysis -- VNBA'08. This workshop marks a new era of the successful series of the Video Surveillance and Sensor Networks (VSSN) workshops, pioneered by J.K. Aggarwal and Rita Cucchiara, and held until 2006 in conjunction with the ACM Multimedia conference (Berkeley, CA, 2003; New York, NY, 2004; Singapore, 2005; and Santa Barbara, CA, 2006). By shifting the focus to cover higher level topics and applications under the common framework of "behaviour analysis," the new workshop aims to adapt to the evolved directions of interest in the field, and reach out to other research communities with overlapping interests. Rapidly increasing interest on the topics of behaviour analysis has been reflected in a high number of recent events (workshops and conferences) and publications (books and special issues) in both fields of behaviour or action analysis and multi-camera or multi-sensor systems. However, there has not been a joint event/publication on the use of multiple vision sensors for enhancing existing approaches to behaviour analysis, an area targeted by the workshop. The VNBA 2008 serves as an initial attempt to bring together communities working on these two different topics with the scope of evaluating whether the technologies and techniques are mature enough to allow the use of vision networks for behaviour analysis. In addition, VNBA aims to serve as a forum for presenting novel behaviour analysis application areas such as immersive human-computer interfaces for virtual reality, gaming and gesture-based control, occupancy sensing and event detection for smart environments, and human-centric applications such as fall detection in elderly care. Despite the ambitious objective and the fact it was the first edition, the workshop attracted a good number of quality submissions (16) fairly distributed among different countries (USA, UK, Italy, Japan, Germany, Belgium, Korea, UK, Canada) and among the different topics of the workshop. The VNBA Technical Program Committee includes the most experienced researchers in the VNBA-related research fields, and thanks to their indispensable effort we were able to select 9 papers for oral presentation and 5 papers for poster presentation. The workshop schedules three oral sessions, named "Smart Environments: Pose, Gesture, HCI", "Surveillance Systems: Detection, Tracking" and "Selected Topics," each containing 3 oral presentations. The 5 poster presentations will be organized in a single, non-overlapped session. In addition, the program will include a keynote address from a distinguished lecturer (to be announced in due time).
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.005 | 0.005 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.030 | 0.010 |
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".