The DOI matches its Crossref record.
Proceedings of the 22nd ACM international conference on Multimedia
Abstract
It is our pleasure to introduce to you the Technical Program of the ACM International Conference on Multimedia 2014. While we built this year's program upon the best practices from previous editions of the conference, we also introduced several adjustments with the goal to define the set of submission areas to reflect the current and emerging research directions in the multimedia field and to improve the quality of the review process and the feedback provided to the authors. Papers were submitted to 14 areas: Big and Broad Multimedia, Deep Learning for Multimedia, Emotional and Social Signals in Multimedia, Media Transport and Delivery, Multimedia and Society, Multimedia and the Crowd, Multimedia Art, Entertainment and Culture, Multimedia HCI and QoE, Multimedia Search and Recommendation, Multimedia Security, Privacy and Forensics, Multimedia Systems and Middleware, Multimodal Analysis and Description, Music, Speech and Audio Processing in Multimedia, and Social Media and Collective Online Presence. This set of areas resulted from revising and expanding the areas from previous years, and based on the discussion within the Technical Program Committee (TPC) that aimed at highlighting new and emerging research directions (e.g., big and broad multimedia, multimedia and society, QoE), promising new technical approaches not traditionally covered at ACM Multimedia (e.g., deep learning), and reaching out to related communities with complementary expertise (e.g., emotional and social signals). At the same time, some areas were discontinued, either due to the sub-standard number of submissions over the past several years (e.g. multimedia authoring and collaboration) or due to the fact that some technologies and platforms have become mainstream and need no special emphasis any more (e.g. mobile and multi-device). For each area, a team of Area Chairs (ACs) was appointed to handle the paper review process. In total, 38 ACs were appointed. The sizes of the teams were defined based on the anticipated number of submissions per area. Consequently, the teams ranged from two to seven ACs. The TPC consisted of both experienced and junior ACs. Also, some ACs were new to the ACM Multimedia venue, with the intention to broaden the ACM Multimedia community and open it up to related communities. ACs were given autonomy to define the Call for Papers (CfP) for their areas, select reviewers, assign papers to them (either manually or through a bidding process), assess papers based on their reviews, and provide initial acceptance recommendation as input for the TPC meeting. The activities of the ACs were steered at the meta level by the following guidelines defined by the TPC Chairs to maximize the program quality: The conference must preserve its unique multimedia character in order to stand out among related scientific venues and attract highest-quality submissions.The papers were handled in a double-blind fashion and for each paper a minimum of three reviews were required.The CfPs for different areas were defined so as to minimize overlap among areas, optimally highlight the focus of individual areas, and maximize the overall topic coverage of the conference program. For this purpose, ACs were requested to share their CfPs with other ACs, and to collaboratively resolve any overlap or ambiguity issues. This resulted in several area-CfP adjustments.ACs were also requested to share their lists of reviewers so as to maximize the level of expertise per area and to make the lists non-overlapping in order to control the review load per reviewer (a reviewer was allowed to participate in multiple areas only with the explicit agreement of the reviewer and the corresponding ACs).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. This required the agreement of ACs from both the outgoing and the receiving area.Conflict of Interest (CoI) handling: ACs were allowed to submit at most one full paper and one short paper to their own area. Since the submission system (EasyChair) only allowed the ACs to have access to papers and reviews in their own track, any submission by ACs were moved to a separate meta track, which included only papers with conflicts of interest. All of these papers were handled by another qualified AC, either from the same area or from another area. If the papers co-authored by ACs passed the threshold for discussion during the TPC meeting, the discussion was led by the handling AC and the author-AC was asked to leave the room. An elaborate EasyChair Paper Management Guidelines document was written containing instructions for the ACs on how to implement the TPC Chair's guidelines and how to navigate the submission management system (EasyChair). This Guidelines document will be made available to the SIGMM Director of Conferences to share with future TPCs of the ACM Multimedia conference. As an aside, we would strongly s
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
A systematic study of the class imbalance problem in convolutional neural networks
Buda, M., Maki, A., & Mazurowski, M. A. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.07.011 · Cited by 3,088
A survey on deep learning techniques for image and video semantic segmentation
Garcia-Garcia, A., Orts-Escolano, S., Oprea, S., Villena-Martinez, V., Martinez-Gonzalez, P., & Garcia-Rodriguez, J. (2018) · Applied Soft Computing · doi:10.1016/j.asoc.2018.05.018 · Cited by 1,490
Medical image analysis using convolutional neural networks: a review
Anwar, S. M., Majid, M., Qayyum, A., Awais, M., Alnowami, M., & Khan, M. K. (2018) · Journal of Medical Systems · doi:10.1007/s10916-018-1088-1 · Cited by 1,431
CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images
Khan, A. I., Shah, J. L., & Bhat, M. M. (2020) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2020.105581 · Cited by 1,312
DeepCrack: A deep hierarchical feature learning architecture for crack segmentation
Liu, Y., Yao, J., Lu, X., Xie, R., & Li, L. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.036 · Cited by 1,158
Metadata
- Publisher
- ACM
- Published
- 2014-11-03
- OpenAlex
- W2914695977
- Cited by
- 725
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Proceedings of the 22nd ACM international conference on Multimedia. https://app.cochat.ai/papers/10.1145/2647868
- The paper
- Proceedings of the 22nd ACM international conference on Multimedia. (2014). https://doi.org/10.1145/2647868
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.