Handbook of Video Databases: Design and Applications (Internet and Communications)

Chapter 2: Modeling Video using Input/Output Markov Models with Application to Multi-Modal Event Detection

Table 2.1: Comparing overall classification error.

Chapter 3: Statistical Models of Video Structure and Semantics

Table 3.1: Classification accuracy of BmoViES ( 1998 IEEE).

Chapter 4: Flavor: A Language for Media Representation

Table 4.1: Compression effectiveness (CE ) for different XML compressors. CE = Compressed XML file / Original (bitstream) file.

Chapter 5: Integrating Domain Knowledge and Visual Evidence to Support Highlight Detection in Sports Videos

Table 5.1: Results for the classification of keyframes in terms of playfield, player and audience classes.

Table 5.2: Sports type identification results. The evaluation set in the first experiment comprised also player and audience scenes. The second experiment was carried out on playfield scenes only.

Table 5.3: Highlight classification results. The Corner/Penalty kick class comprises also free kicks near the goal box zone

Table 5.4: The Other class contains actions that were not modeled. The Corner/Penalty kick class comprises also free kicks near the goal box zone.

Chapter 7: Temporal Segmentation of Video Data

Table 7.1: Output values of the MLP during the training phase

Table 7.2: Characteristics of dataset

Table 7.3: Performance using the b2b metric

Table 7.4: Performance using the chi-square metric

Table 7.5: Performance using the histogram correlation metric.

Table 7.6: Factors intervening in transition detection (technique T2)

Table 7.7: Range of parameters used for experiments

Table 7.8: Optimal result using bin-to-bin metric

Table 7.9: Optimal result using chi-squares metric

Table 7.10: Optimal result using correlation metric

Table 7.11: Performance of MLPs of different architecture

Table 7.12: Performance comparison among the described techniques

Chapter 8: A Temporal Multi-Resolution Approach to Video Shot Segmentation

Table 8.1: Transition Boundary for Echosystem.mpg

Table 8.2: Videos for Evaluation

Table 8.3: Transition Type Distribution

Table 8.4: Result Using Twin-Comparison

Table 8.5: Result on TMRA using 64-bin Histogram Without Elimination Phase

Table 8.6: Result on TMRA using DC Histogram Without Elimination Phase

Table 8.7: Result on TMRA using DC64 Without Elimination Phase

Table 8.8: Result on TMRA Integrated with Elimination Phase Using DC64 and MA64

Chapter 10: Audio and Visual Content Summarization of a Video Program

Table 10.1: Particulars of the Evaluation Database.

Table 10.2: Statistics of the Manual Summarization Results.

Table 10.3: Evaluation Results.

Table 10.4: Experimental Evaluation.

Chapter 15: Video Shot Detection using Color Anglogram and Latent Semantic Indexing: From Contents to Semantics

Table 15.1: Evaluations of Experimental Results

Chapter 22: Organizational Principles of Video Data

Table 22.1

Chapter 27: Indexing Video Archives: Analyzing, Organizing, and Searching Video Information

Table 27.1: Number of distinctive NNs.

Table 27.2: Categories of the results.

Chapter 28: Efficient Video Similarity Measurement using Video Signatures

Table 28.1: Comparison between using uniform random and Corel image SV's. The second through fifth columns are the results of using uniform random SV's and the rest are the Corel image SV's. Each row contains the results of a specific test video at IVS levels 0.8, 0.6, 0.4 and 0.2. The last two rows are the averages and standard deviations over all the test sequences.

Table 28.2: Comparison between VSS_b and VSS_r under different level of perturbation. The table follows the same format as in Table 28.1. The perturbation levels ε tested are 0.2, 0.4. 0.8, 1.2 and 1.6.

Table 28.3: Statistics of collected web video sequences

Chapter 30: Small Sample Learning Issues for Interactive Video Retrieval

Table 30.1: Averaged hit rate in top 100 for 500 rounds of testing.

Chapter 31: Cost Effective and Scalable Video Streaming Techniques

Table 31.1: Backward and forward interactions.

Chapter 32: Design and Development of a Scalable End-to-End Streaming Architecture

Table 32.1: A comparison of continuous-media servers. Note that Yima is a prototype system and does not achieve the refinement of the commercial solutions. However, we use it to demonstrate several advanced concepts.

Table 32.2: List of terms used repeatedly in this section and their respective definitions.

Chapter 34: Video Streaming: Concepts, Algorithms, and Systems

Table 34.1: Current and emerging video compression standards.

Table 34.2: Adapting error control based on differing importance of video data: unequal error protection and unequal (prioritized) retransmission based on coded frame type.

Chapter 35: Continuous Display of Video Objects using Heterogeneous Disk Subsystems

Table 35.1: Three different Seagate disk models and their zone characteristics.

Table 35.2: List of terms used repeatedly in this chapter.

Table 35.3: Three imaginary disk models and their zone characteristics.

Chapter 37: Server-Based Service Aggregation Schemes for Interactive Video-on-Demand

Table 37.1: Taxonomy of Service Aggregation Schemes in VoD

Table 37.2: Simulation Parameters

Table 37.3: Arrival and Interaction Patterns

Table 37.4: Comparison between Variants of RSMA (λ_arr = 0.1, λ_int = 0, λ_q = 0)

Table 37.5: Comparison between Variants of RSMA (λ_arr =0.1, λ_int = 0.01, λ_q = 0.001)

Chapter 38: Challenges in Distributed Video Management and Delivery

Table 38.1: Bitrate of differentially encoded streams and storage savings with respect to independent coding of the streams for the CIF sequence Football.

Table 38.2: Mapping data to data classes based on its position in the cache. The position is determined by the data's recall value.

Table 38.3: Mapping data class numbers to best allowed compression quality.

Table 38.4: Comparison of penalty in distortion for three users for MDFEC designed for the worst-case channel, and for MDFEC designed for the minimax cost.

Chapter 39: Video Compression: State of the Art and New Trends

Table 39.1: Tools supported in JVT/H.26L

Table 39.2: Average bitrate savings of JVT/H.26L

Table 39.3: Image and video coding classification

Chapter 40: Compressed-Domain Video Processing

Table 40.1: Mathematical expression of spatial vs. DCT domain algebraic operations

Table 40.2: Mathematical expression of distributiveness of DCT

Chapter 42: Video Watermarking Overview and Challenges

Table 42.1: Number of publications having the keyword watermarking as their main subject according to INSPEC database, July 2002.

Table 42.2: Video watermarking: applications and associated purpose

Table 42.3: Examples of nonhostile video processings

Table 42.4: Pros and cons of the different approaches for video watermarking.

Chapter 43: Creating Personalized Video Presentations using Multimodal Processing

Table 43.1: Parameters for different client devices.

Chapter 44: Segmenting Stories in News Video

Table 44.1: The classification results from the Decision Tree

Table 44.2: The results of HMM analysis in tests I & II

Table 44.3: Results of using combination of features used in Test II