ACM Multimedia 2013

145 papers
The 2013 edition of ACM Multimedia featured 216 papers, with a prominent focus on affective computing and high-dimensional data analysis. Research directions included bridging the affective gap in computer vision and exploring continuous dimensional models to analyze the asymmetry of valence and arousal. Methodological trends centered on supervised dimensionality reduction for feature extraction and modeling structured relationships within label spaces to improve inference. Notable work during this year addressed diverse applications such as multimedia event detection through fine-grained labeling and visual business recognition using multimodal approaches. Other contributions explored location recognition via geo-informative attributes and non-linear media access in peer-to-peer networks. Research also examined image representation in sub-semantic spaces, moving beyond traditional bag-of-words models. Prolific contributors included researchers such as Qi Tian, Shuicheng Yan, and Shih-Fu Chang, whose work spanned areas from superpixel segmentation for scene recognition to non-reference audio quality assessment for live recordings.

Top Research Directions

Research directions most represented by ACM Multimedia 2013 papers.

Latent Label Space Compression for Extreme Classification 1
Preserving Motion Boundaries in Dense Flow Estimation 1
Supervised Dimensionality Reduction 1
Grounding Textual Semantics in User Behavior Logs 1
Spatio-Temporal Representation Mapping for Action Recognition 1
3D Body Geometry for Invariant Person Re-Identification 1
Navigating Complex Datasets Through Multi-Scale Abstraction 1
The Limitations of Monochromatic Visual Features 1
Integrating Heterogeneous Data Streams for Grounded Context 1
Horizontal Spatial Partitioning for Robust Person Identification 1
Aggregating Local Features via Fisher Vectors 1
Translating Complex Data into Intuitive Visual Interfaces 1
The Vulnerability of Predictive Models to Exogenous Shocks 1
Scale Invariant Local Feature Extraction and Matching 1
The Information Loss of Visual Feature Quantization 1

Top Authors

AuthorPapers
Shuicheng YAN8
Rongrong Ji4
Shih-Fu Chang4
Alberto Del Bimbo3
Cees G. M. Snoek3
Damian Borth3
Fei Wu3
Jingdong Wang3
Kiyoharu Aizawa3
Liangliang Cao3
Marco Bertini3
Nicu Sebe3
Qingming Huang3
Xian-Sheng Hua3
Amir Habibian2
Ansgar Scherp2
Brendan Jou2
Changsheng Xu2
Chao Liang2
Chunjie Zhang2

Impactful Papers

Papers from ACM Multimedia 2013 that shaped research clusters.

Foundational

Influential

Papers

Title
Scale based region growing for scene text detection
Second ACM multimedia workshop on geotagging and its applications in multimedia (GeoMM 2013)
Segmental multi-way local pooling for video recognition
Semantic pooling for complex event detection
Semantic technologies for multimedia content: foundations and applications
SentiBank: large-scale ontology and classifiers for detecting sentiment and emotions in visual content
Sim-min-hash: an efficient matching technique for linking large image collections
Social interactions over geographic-aware multimedia systems
Spatialized audio multiparty teleconferencing with commodity miniature microphone array
Spatio-temporal fisher vector coding for surveillance event detection
Spot the differences: from a photograph burst to the single best picture
Static saliency vs. dynamic saliency: a comparative study
Stereotime: a wireless 2D and 3D switchable video communication system
Strong geometrical consistency in large scale partial-duplicate image search
Structured exploration of who, what, when, and where in heterogeneous multimedia news sources
Summary abstract for the 1st ACM international workshop on personal data meets distributed multimedia
Superpixel segmentation based structural scene recognition
TEEVE endpoint: towards the ease of 3D tele-immersive application development
Tele echo tube: beyond cultural and imaginable boundaries
Tell me what happened here in history
Temporal encoded F-formation system for social interaction detection
The space between the images
The third ACM international workshop on interactive multimedia on mobile and portable devices (IMMPD'13)
Time matters!: capturing variation in time in video using fisher kernels
Topology preserving hashing for similarity search
Towards a comprehensive computational model foraesthetic assessment of videos
Towards cover group thumbnailing
Towards efficient sparse coding for scalable image annotation
Towards next generation multimedia recommendation systems
Understanding and classifying image tweets
Undo the codebook bias by linear transformation for visual applications
User interest and social influence based emotion prediction for individuals
Using emotional context from article for contextual music recommendation
Video2Sentence and vice versa
Visual business recognition: a multimodal approach
Visual interestingness in image sequences
Weakly-supervised multi-class object detection using multi-type 3D features
We are not equally negative: fine-grained labeling for multimedia event detection
WeCard: a multimodal solution for making personalized electronic greeting cards
What are the distance metrics for local features?
Why not, WINE?: towards answering why-not questions in social image search
With one look: robust face recognition using single sample per person
Workshop summary for the 5th international workshop on multimedia for cooking and eating activities (CEA'13)
"Wow! you are so beautiful today!"
πLDA: document clustering with selective structural constraints

« prev Page 3/3