Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

We propose a fully automatic and computationally efficient framework for analysis and summarization of soccer videos using cinematic and object-based features. The proposed framework includes some novel low-level processing algorithms, such as dominant color region detection, robust shot boundary detection, and shot classification, as well as some higher-level algorithms for goal detection, referee detection, and penalty-box detection. The system can output three types of summaries: i) all slow-motion segments in a game; ii) all goals in a game; iii) slow-motion segments classified according to object-based features. The first two types of summaries are based on cinematic features only for speedy processing, while the summaries of the last type contain higher-level semantics. The proposed framework is efficient, effective, and robust. It is efficient in the sense that there is no need to compute object-based features when cinematic features are sufficient for the detection of certain events, e.g., goals in soccer. It is effective in the sense that the framework can also employ object-based features when needed to increase accuracy (at the expense of more computation). The efficiency, effectiveness, and robustness of the proposed framework are demonstrated over a large data set, consisting of more than 13 hours of soccer video, captured in different countries and under different conditions.

Automatic soccer video analysis and summarization

Video indexing and retrieval have a wide spectrum of promising applications, motivating the interest of researchers worldwide. This paper offers a tutorial and an overview of the landscape of general strategies in visual content-based video indexing and retrieval, focusing on methods for video structure analysis, including shot boundary detection, key frame extraction and scene segmentation, extraction of features including static key frame features, object features and motion features, video data mining, video annotation, video retrieval including query interfaces, similarity measure and relevance feedback, and video browsing. Finally, we analyze future research directions.

A Survey on Visual Content-Based Video Indexing and Retrieval

Efficient and effective handling of video documents depends on the availability of indexes. Manual indexing is unfeasible for large video collections. In this paper we survey several methods aiming at automating this time and resource consuming process. Good reviews on single modality based video indexing have appeared in literature. Effective indexing, however, requires a multimodal approach in which either the most appropriate modality is selected or the different modalities are used in collaborative fashion. Therefore, instead of separately treating the different information sources involved, and their specific algorithms, we focus on the similarities and differences between the modalities. To that end we put forward a unifying and multimodal framework, which views a video document from the perspective of its author. This framework forms the guiding principle for identifying index types, for which automatic methods are found in literature. It furthermore forms the basis for categorizing these different methods.

/pdf/multimodal-video-indexing-a-review-of-the-state-of-the-art-2vyybm3bil.pdf

Multimodal Video Indexing: A Review of the State-of-the-art

Current information and communication technologies provide the infrastructure to send bits anywhere, but do not presume to handle information at the semantic level. This paper investigates the use of video content analysis and feature extraction and clustering techniques for further video semantic classifications and a supervised rule based video classification system is proposed. This system can be applied to the applications such as on-line video indexing, filtering and video summaries, etc. As an experiment, basketball video structure will be examined and categorized into different classes according to distinct visual and motional characteristics features by rule-based classifier. The semantics classes, the visual/motional feature descriptors and their statistical relationship are then studied in detail and experiment results based on basketball video will be provided and analyzed.

Rule-based video classification system for basketball video indexing

http://mcl.usc.edu/wp-content/uploads/2014/01/200212-On-line-knowledge-based-and-rule-based-video-classification-system-for-video-indexing-and-dissemination.pdf

On-line knowledge- and rule-based video classification system for video indexing and dissemination

Many multimedia applications, such as multimedia data management systems and communication systems, require efficient representation of multimedia content. Thus semantic interpretation of video content has been a popular research area. Currently, most content-based video representation involves the segmentation of video based on key frames which are generated using scene change detection techniques as well as camera/object motion. Then, video features can be extracted from key frames. However most of such research performs off-line video processing in which the whole video scope is known as a priori which allows multiple scans of the stored video files during video processing. In comparison, relatively not much research has been done in the area of on-line video processing, which is crucial in video communication applications such as on-line collaboration, news broadcasts and so on. Our research investigates on-line real-time scene change detection of multicast video over the Internet. Our on-line processing system are designed to meet the requirements of real-time video multicasting over the Internet and to utilize the successful video parsing techniques available today. The proposed algorithms extract key frames from video bitstreams sent through the MBone network, and the extracted key frames are multicasted as annotations or metadata over a separate channel to assist in content filtering such as those anticipated to be in use by on-line filtering proxies in the Internet. The performance of the proposed algorithms are demonstrated and discussed in this paper.

Online scene change detection of multicast (MBone) video

http://mcl.usc.edu/wp-content/uploads/2014/01/200103-On-line-scene-change-detection-of-multicast-video.pdf

On-line Scene Change Detection of Multicast Video

Events include simple events and complex events. The causative SVN1N2 structure can be considered as a demonstration of complex events. In this essay, the causative SVN1N2 structure will be analyzed from three aspects: causing events, causative relationships and causative events. This structure has three subordinate structures: ①gain and loss causing structure, ②consequence causing structure, and ③beneficial causing structure. Among the causing events, the first two structures(① and ②) can be only initiated by entitive causer, and the third structure obtains both entitive causer and eventive causer.BR From the semantical dimension, since the SVN1N2 structure contains causative expressions, these expressions can be represented by syntactic causations and lexical causations. The causative events of three subordinate structures mentioned above are represented differently in the syntactic manners. That is, the gain and lost causing structure only can be represented in the form of number+quantifier+noun, meanwhile the consequence causing structure and the beneficial causing structure have three different representations respectively. 

Wensheng Zhou

Papers

Rule-based video classification system for basketball video indexing

On-line knowledge- and rule-based video classification system for video indexing and dissemination

Online scene change detection of multicast (MBone) video

On-line Scene Change Detection of Multicast Video

The Analysis of Event Structure of the SVN1N2 Construction in Modern Chinese