Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 455

The DOI matches its Crossref record.

Proceedings of the 26th ACM international conference on Multimedia

· 2018

Abstract

We are proud to present a remarkably diverse and highly interesting Technical Program for the ACM International Conference on Multimedia 2018 (ACM Multimedia 2018), which for the first time takes place in Seoul, Korea. This year, a total of 15 areas of interest were grouped into four research themes, including an Understanding Theme (covering Multimedia and Vision, Multimodal Analysis and Description, and Deep Learning for Multimedia), an Engagement Theme (covering Emotional and Social Signals in Multimedia, Multimedia Search and Recommendation, and Social Multimedia), an Experience Theme (covering Multimedia HCI and Quality of Experience, Multimedia Art, Entertainment and Culture, Multimedia for Collaboration in Education and Distributed Environments, and Music, Speech and Audio Processing in Multimedia), and a System Theme (covering Mobile Multimedia, Multimedia Scalability and Management System, Multimedia Systems and Middleware, Multimedia Telepresence and Virtual/Augmented Reality, and Multimedia Transport and Delivery). Each research theme was overseen by one of this year's Technical Program Chairs. For each area of interest, a team of Area Chairs (ACs), ranging from 2 to 19 members, was recruited to handle the paper review process. In total, 92 ACs were appointed. The sizes of the teams were defined based on the anticipated number of submissions in each area. All submissions co-authored by program chairs (in total only three submissions) were handled in a separate Conflict-of-Interest (CoI) track led by the Program Co-chair Tao Mei. The paper assignment was conducted by the combination of an automatic paper matching process (i.e., Toronto Paper Matching System) and the relevance matching between the paper and reviewer categories. The papers were handled in a double-blind fashion and for each paper a minimum of three reviews were required. We have recruited 685 program committee members to contribute their professional reviews to the submissions in a double-blind approach. On average, we received more than 3.76 reviews for each submission by the review deadline, which enabled the ACs to write meta reviews and proposed initial recommendations before the TPC meetings. ACs were instructed to administratively reject improperly formatted papers and to move papers to other tracks if they believed there was a better fit for the paper. All the submissions with the similar topics were grouped to ensure a fair calibration in the same group. Decisions on orals/posters and best papers were made at the Technical Program Committee meeting held at the Workpia Yokohama, Yokohama, Japan. Many of the ACs who were unable to attend were tele-present online for discussions. The emphasis of the TPC meeting was on borderline and controversial submissions. The discussions were detailed and intensive, taking into account all the available data, including reviews, the authors' rebuttals, the reviewers' and ACs' discussions, the initial recommendations by the ACs, and any reviews performed by ACs during the meeting.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3240508

Cites

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cited by

Metadata

Publisher
ACM
Published
2018-10-15
OpenAlex
W1516807289
Cited by
455
References
0
Type
paratext
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.