Proceedings of the 8th ACM international workshop on Multimedia information retrieval
Bibliographic record
Abstract
Welcome to the sunny and beautiful Santa Barbara, California and the ACM SIG Multimedia International Workshop on Multimedia Information Retrieval (MIR). Like in the past years, this workshop is held in conjunction with the ACM Multimedia Conference. This year is the 8th in the MIR series. Continuing the great tradition of MIR, the purpose of this year's workshop is to bring together researchers, developers, and practitioners from academia and industry to discuss important challenges, latest advances, and future possibilities in multimedia retrieval.The volume and quality of the papers submitted to the workshop confirm the steady growth of the field of multimedia information retrieval and the status of MIR as the largest dedicated ACM meeting in this research area. The MIR 2006 received about 80 abstracts, of which 70 resulted in completed submissions. The authors of these submissions are from USA, France, Japan, Germany, China, Singapore, Italy, Ireland, The Netherlands, Turkey, Denmark, Malaysia, Austria, Switzerland, Canada, S. Korea, Brazil, United Kingdom, Australia, Czech Republic, Portugal, and Pakistan. The Program Committee selected 10 (14%) contributions to include in the program as regular papers and an additional 15 as poster papers. There are also two invited special sessions on Query Systems for Data Retrieval in Large Personal Image and Video Databases and Benchmarking Image and Video Retrieval. Carole Dulong, Igor Kozintsev, Yi Wu, Stephane Marchand-Maillet, and Marcel Worring organized these sessions.We are very delighted to have two outstanding keynote speakers. Donald Geman of Johns Hopkins University, one of the most cited computer scientists, will present an interactive search engine based on information theory and statistical inference. Edward Chang of Google China and University of California at Santa Barbara will discuss a framework of integrating statistical learning approaches in multimedia information retrieval. Their talks will provide diverse perspectives to the audience. The panel this year, moderated by James Z. Wang, will focus on diversity in multimedia retrieval research. The panelists include Nozha Boujemaa, Alberto Del Bimbo, Donald Geman, Alex Hauptmann, and Jelena Tesic.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".