ICME 2007

235 papers
The 2007 IEEE International Conference on Multimedia and Expo (ICME) featured 296 papers covering a broad spectrum of multimedia research. Key themes included advancements in video coding, specifically multi-view and panoramic video structures, and image processing techniques such as annotation models and multi-focus fusion. Research also addressed computer vision applications, including facial animation synthesis and foreground segmentation for surveillance. Network-related studies explored scalable reliable multicast and overlay path diversity. Prolific contributors to this edition included Xian-Sheng Hua, Wen Gao, and Thomas S. Huang. Notable research topics represented in the proceedings involved the development of delayless architectures for adaptive filters and performance modeling for multi-view video coding. The technical program reflected a focus on improving efficiency in video bandwidth and enhancing the realism of synthetic facial expressions through flexible expression ratio images. These contributions highlighted a focus on optimizing both the transmission and the visual quality of multimedia content.

Top Research Directions

Research directions most represented by ICME 2007 papers.

The Breakdown of Local Estimators under Data Sparsity 1
Multimodal Feature Fusion for Video Semantic Understanding 1
Gated Fusion for Adaptive Feature Integration 1
Bridging the Semantic Gap in Video Text Alignment 1
Temporal Consistency in Generative Video Synthesis 1

Top Authors

AuthorPapers
Xian-Sheng Hua8
Qingming Huang6
Shuqiang Jiang6
Changsheng Xu4
Guo-Jun Qi4
Kiyoharu Aizawa4
Marcel Worring4
Meng Wang4
Nenghai Yu4
Toshihiko Yamasaki4
Yun Fu4
Cees G. M. Snoek3
Debin Zhao3
Hanqing Lu3
Hari Sundaram3
Jinhui Tang3
Joo Hwee Lim3
Li Song3
Mohan Kankanhalli3
Mubarak Shah3

Impactful Papers

Papers from ICME 2007 that shaped research clusters.

Influential

Papers

Title
Exploiting Overlay Path-Diversity for Scalable Reliable Multicast
Exploiting Personal And Social Network Context For Event Annotation
Exploiting Users' Personal and Public Information for Personal Photo Annotation
Exploring Contextual Information in a Layered Framework for Group Action Recognition
Exploring Discriminative Learning for Text-Independent Speaker Recognition
Extracting Barcodes from a Camera-Shaken Image on Camera Phones
Face Recognition for Smart Interactions
Fast and Robust Motion Tracking for Time-Varying Mesh Featuring Reeb-Graph-Based Skeleton Fitting and its Application to Motion Retrieval
Fast Mode Decision for Coarse Granular Scalability via Switched Candidate Mode Set
Featured Wand for 3D Interaction
Foreground Segmentation in Surveillance Scenes Containing a Door
Gait History Image: A Novel Temporal Template for Gait Recognition
Gaussian Representation for 3D Point Based Head Model Classification Based on Generalized Minimax Algorithm
Generating High-Resolution Textures for 3D Virtual Environments using View-Independent Texture Mapping
Generating Video Sequence from Photo Image for Mobile Screens by Content Analysis
Generic and Robust Video Coding with Texture Analysis and Synthesis
Geodesic Distances for 3D-3D and 2D-3D Face Recognition
Ghost Shadow Removal in Multi-Layered Video Inpaintinga
GOP-Level Transmission Distortion Modeling for Unequal Importance Judgement
Graph-Based Perceptual Quality Model for Audiovisual Contents
Hidden Maximum Entropy Approach for Visual Concept Modeling
High Capacity Data Hiding for Binary Images in Morphological Wavelet Transform Domain
Highlight Ranking for Racquet Sports Video in User Attention Subspaces Based on Relevance Feedback
Hole Filling on Three-Dimensional Surface Texture
Human Action Recognition Using 2-D Spatio-Temporal Templates
i.Boosting for Image Classification
ICP with Bounded Scale for Registration of M-D Point Sets
Identifying Source Cell Phone using Chromatic Aberration
Image Annotation in a Progressive Way
Image Annotation Refinement using NSC-Based Word Correlation
Image-Based Quizzes from News Video Archives
Image Search Result Clustering and Re-Ranking via Partial Grouping
Image Splicing Detection using Camera Response Function Consistency and Automatic Segmentation
Image Steganography Based on Quantization-Embedders Combination
Image Super-Resolution Framework with Multi-Channel Constraints
Improvements on Sensor Noise Based Source Camera Identification
Improving Semantic Concept Detection and Retrieval using Contextual Estimates
Integrated Image Enhancement and Artifacts Reduction Based on Frequency Bands Manipulation
Interactive Search of Adipocytes in Large Collections of Digital Cellular Images
Interactive Spatio-Temporal Visual Map Model for Web Video Retrieval
Interoperability Issues in DRM and DMP Solutions
Joint Decoding of Multiple Video Streams
Joint Fingerprint Embedding and Decryption for Video Distribution
Joint Multimedia Fingerprinting and Encryption: Security Issues and Some Solutions
Joint Network and Rate Allocation for Simultaneous Wireless Applications
Joint Source Coding and Data Rate Adaptation for Multi-User Wireless Video Transmission
Knowledge-Assisted Medical Image Retrieval
Lazy Learning Based Efficient Video Annotation
Learning-Based Perceptual Image Quality Improvement for Video Conferencing
Learning Semantic Concepts for Image Retrieval using the Max-Min Posterior Pseudo-Probabilities

« prev Page 3/5 next »