ACM Multimedia 2014

160 papers
ACM Multimedia 2014 featured 241 papers focusing on bridging the semantic gap in human activity recognition and decomposing appearance and motion within video models. Research directions included lifting 2D visual priors into 3D representations, exemplified by work on 3D fingertip detection and tracking. Another prominent theme involved integrating exogenous signals into social media dynamics, including the use of deep neural networks for psychological stress detection. The edition also emphasized passive and unobtrusive sensing for continuous health and physiological monitoring. Practical applications presented included mobile video mashup systems, clothing retrieval based on local similarity, and interactive sketch recognition tools. Prolific contributors included Roger Zimmermann, Yang Yang, Nicu Sebe, and Shuicheng Yan. The conference also addressed automated video summarization and hosted the third workshop on geotagging and its applications. These works collectively reflected a trend toward combining social media analysis with longitudinal health data and improving 3D spatial understanding from 2D inputs.

Top Research Directions

Research directions most represented by ACM Multimedia 2014 papers.

Leveraging Background Context for Visual Representation Learning 1
Modeling Exogenous Influence in Social and Information Networks 1
Mitigating Finite Sample Bias in Information Estimation 1
Automated Diagnostic Classification from Respiratory Acoustic Datasets 1
Constant Time Spatial Aggregation with Integral Images 1
Designing Annotation Interfaces for Non-Expert Data Labeling 1
Mapping Semantic Descriptors to Audio Processing Parameters 1
Rotation Invariance via Canonical Orientation Alignment 1
Mapping Perceptual Spaces with Multidimensional Scaling 1
The Static Camera Assumption in Computer Vision 1
Geometric Verification for Robust Feature Matching 1
Modeling Subjective Ambiguity in Audio and Music AI 1
Pose Invariant Representation via Canonical UV Mapping 1
Biometric Recognition under Severe Resolution Degradation 1
Fragility of Landmark Localization in Facial Analysis Pipelines 1

Top Authors

AuthorPapers
Roger Zimmermann6
Shuicheng YAN5
Fei Wu4
Nicu Sebe4
Shih-Fu Chang4
Tat-Seng Chua4
Xiaochun Cao4
Yang Yang4
Bruno Lepri3
Jinhui Tang3
Kien A. Hua3
Liangliang Cao3
Xi Li3
Yu-Gang Jiang3
Abdulmotaleb El Saddik2
Alexander G Hauptmann2
Asako Kanezaki2
Axel Carlier2
Bo Yan2
Changsheng Xu2

Impactful Papers

Papers from ACM Multimedia 2014 that shaped research clusters.

Foundational

Influential

Papers

Title
VideoStory: A New Multimedia Embedding for Few-Example Recognition and Translation of Events
Weakly-Supervised Image Parsing via Constructing Semantic Graphs and Hypergraphs
We are not All Equal: Personalizing Models for Facial Expression Analysis with Transductive Parameter Transfer
WeMash: An Online System for Web Video Mashup
What Can We Learn about Motion Videos from Still Images?
What's Making that Sound?
What Strikes the Strings of Your Heart?: Multi-Label Dimensionality Reduction for Music Emotion Analysis
What Videos Are Similar with You?: Learning a Common Attributed Representation for Video Recommendation
WISMM'14 - First ACM International Workshop on Internet-Scale Multimedia Management
You Talkin' to Me?: Recognizing Complex Human Interactions in Unconstrained Videos

« prev Page 4/4