ICME 2004

148 papers
The 2004 edition of the IEEE International Conference on Multimedia and Expo (ICME) featured 179 papers addressing diverse challenges in multimedia processing and management. A significant portion of the research focused on information retrieval, including interactive video archive search, semantic concept learning for image retrieval, and similarity-based visualization techniques. Other prominent themes included automated content classification, such as the detection of Flash movie genres using Bayesian approaches and the temporal modeling of facial actions. Technical contributions also extended to hardware optimization, specifically SIMD loop unrolling for embedded multimedia applications, and security through sensor-based authentication systems. Prolific authors contributing to the proceedings that year included Mohan S. Kankanhalli, HongJiang Zhang, Marcel Worring, and C.-C. Jay Kuo. Collectively, the work from this year reflected an interest in bridging the gap between low-level signal processing and high-level semantic understanding in digital media.

Top Research Directions

Research directions most represented by ICME 2004 papers.

Safe Semi-Supervised Learning 1
Moving Beyond Binary Classification Frameworks 1
Joint Latent State and Parameter Estimation 1

Top Authors

AuthorPapers
Mohan Kankanhalli6
Changsheng Xu5
Wei-Ying Ma5
Alberto Del Bimbo4
Li Qing4
Marcel Worring4
Yan Lu4
Zhengguo Li4
Edward Y Chang3
Qingming Huang3
Qionghai Dai3
Shih-Fu Chang3
Siwei Ma3
Wei Tsang Ooi3
Xiaolin Wu3
Changshui Zhang2
Cha Zhang2
Chun-Shien Lu2
Ee-Chien Chang2
Kiyoharu Aizawa2

Impactful Papers

Papers from ICME 2004 that shaped research clusters.

Influential

Papers

Title
Optical flow back-projection for genuine motion vector estimation
Optimal FEC rate for media streaming in active networks
Optimizing similarity based visualization in content based image retrieval
Organizing WWW images based on the analysis of page layout and Web link structure
Overview of AVS video standard
Parameterized discriminant analysis for image classification
Perceptual cryptography on SPIHT compressed images or videos
Proactive frame-skipping decision scheme for variable frame rate video coding
Rate-distortion optimized dynamic bitstream switching for scalable video streaming
Reconstructing dense light field from a multi-focus images array
Reducing memory bank conflict for embedded multimedia systems
Reliable JPEG 2000 wireless imaging by means of error-correcting MQ coder
Repeating pattern discovery from acoustic musical signals
Representation and retrieval of paintings based on art history concepts
Resource-aware video processing techniques for ambient multimedia systems
Robust face recognition using minimax probability machine
Robust lossless image data hiding
Robust mesh-based hashing for copy detection and tracing of images
Robust soccer highlight generation with a novel dominant-speech feature extractor
Search speed and power driven integrated software and hardware optimizations for motion estimation algorithms
Semantic propagation from relevance feedbacks
Semantic video clustering across sources using bipartite spectral clustering
Shape recognition based on the medial axis approach
Shape representation by spatial partitioning for content based retrieval applications
SIMD - efficient loop unrolling design for embedded multimedia applications
Simple mathematical modeling of efficient path selection for QoS routing in load balancing
Singing voice detection using twice-iterated composite Fourier transform
Single-pass frame-level constant distortion bit allocation for smooth video quality
Sports highlight detection from keyword sequences using HMM
Sports scene analysis and visualization from multiple-view video
SSD tracking using dynamic template and log-polar transformation
Steganalysis of boundary-based steganography using autoregressive model of digital boundaries
Subjective preference of spatio-temporal rate in video adaptation using multi-dimensional scalable coding
Sub-pixel motion compensation interpolation filter in AVS
SVM-based relevance feedback using random subspace method
Temporal modeling of facial actions from face profile image sequences
Temporal scalable video transmission using multi-reference prediction chain coding
TORM: a hybrid multicast infrastructure for interactive distance learning
Toward building a robust and intelligent video surveillance system: a case study
Towards robust face recognition from multiple views
Understanding and modeling user interests in consumer videos
Unsupervised classification of music genre using hidden Markov model
Using entropy impurity for improved 3D object similarity search
Video content representation on tiny devices
Video material archive system for efficient video editing based on media identification
Video segmentation based on sequential change detection
Video summarization by video structure analysis and graph optimization
Why one example is not enough for an image query

« prev Page 3/3