Automatically extracting highlights for TV Baseball programs

Rui, Yong; Gupta, Anoop; Acero, Alex

doi:10.1145/354384.354443

Cited by 339 publications

(192 citation statements)

References 12 publications

(14 reference statements)

Supporting

Mentioning

190

Contrasting

Unclassified

Order By: Relevance

“…Under many conditions, visual segmentation cues are accompanied by correlated inputs from other senses, notably audition (Roskies, 1999;Shimojo & Shams, 2001). Contentbased, automated image recognition systems can improve their segmentation of events by exploiting correlated multisensory information (Rui, Gupta, & Acero, 2000), but can humans do the same? And if they can, by what rules are multiple segmentation cues integrated?…”

Section: Introductionmentioning

confidence: 99%

Multi-sensory integration of spatio-temporal segmentation cues: one plus one does not always equal two

2007

View full text Add to dashboard Cite

How are multiple, multi-sensory stimuli combined for use in segmenting spatio-temporal events? For an answer, we measured the effect of various auditory or visual stimuli, in isolation or in combination, on a bistable percept of visual motion ("bouncing" vs. "streaming"). To minimize individual differences, the physical properties of stimuli were adjusted to reflect individual subjects' sensitivity to each cue in isolation. When put into combination, perceptual influences that had been equipotent in isolation were substantially altered. Specifically, auditory cues that had been strong when presented alone, were greatly reduced in combination. Evaluation of alternative models of sensory integration showed that the state of the visual bistable percept could not be accounted for by probability summation among cues, as might occur at the level of decision processes. Instead, the state of the bistable percept was well predicted from a weighted sum of cues, with visual cues strongly dominating auditory cues. Finally, when cue weights were compared for individual subjects, it was found that subjects differ somewhat in the strategy they use for integrating multi-sensory information.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-sensory integration of spatio-temporal segmentation cues: one plus one does not always equal two

2007

View full text Add to dashboard Cite

show abstract

“…A similar work, for tennis video, is done by Sudhir et al [7], they used court line detection and player tracking to extract tennis play events. However, Rui et al [8] presented a system for baseball-video highlight detection. In addition to visual contents, these systems based on audio contents to detect the excited speech and pitch hit detection.…”

Section: Event Detection In Videosmentioning

confidence: 99%

Action boundaries detection in a video

Wehbe

Haidar

Joly

2015

Multimed Tools Appl

View full text Add to dashboard Cite

OATAO is an open access repository that collects the work of Toulouse researchers and makes it freely available over the web where possible. AbstractIn the video analysis domain, automatic detection of actions performed in a recorded video represents an important scientific and industrial challenge. This paper presents a new method to approximate the boundaries of actions performed by a person while interacting with his environment (such as moving objects). This method relies on a Codebook quantization method to analyze the rough evolution of each pixel and then decide whether this evolution corresponds to an action or not; this decision is taken by an automated system. Statistics are then produced -at the scale of the whole frame -to estimate the start and the end of an action. According to our proposed evaluation protocol, this method produces interesting results on both real and simulated videos. This statistic-based protocol is discussed at the end of this paper. The interpretation of this evaluation protocol nominates this method to be a solid base to localize the exact boundaries of actions or -in the framework of this research activity -to associate prescriptive text with a visual content.

show abstract

“…Therefore, many play detection algorithms [13], [41], [79], [147] use color, motion, court layout, and tracking features followed by either rule-based or statistical models such as Bayesian network or HMM. Spontaneous events in sports are intuitively characterized by distinct audio cues such as audience cheering and excited commentator speech, particular view angles such as the soccer goal post and penalty area, behavior of salient objects such as players and balls, as well as mid-level detectors such as whistle and goal posts [39], [44], [117], [153], [158]. Models for inferring sporadic events include rules and distances [153], SVMs [39], [117], [158].…”

Section: ) Detecting Production Eventsmentioning

confidence: 99%

Event Mining in Multimedia Streams

2008

View full text Add to dashboard Cite

| Events are real-world occurrences that unfold over space and time. Event mining from multimedia streams improves the access and reuse of large media collections, and it has been an active area of research with notable recent progress. This paper contains a survey on the problems and solutions in event mining, approached from three aspects: event description, event-modeling components, and current event mining systems. We present a general characterization of multimedia events, motivated by the maxim of five BW[s and one BH[ for reporting real-world events in journalism: when, where, who, what, why, and how. We discuss the causes for semantic variability in real-world descriptions, including multilevel event semantics, implicit semantics facets, and the influence of context. We discuss five main aspects of an event detection system. These aspects are: the variants of tasks and event definitions that constrain system design, the media capture setup that collectively define the available data and necessary domain assumptions, the feature extraction step that converts the captured data into perceptually significant numeric or symbolic forms, statistical models that map the feature representations to richer semantic descriptions, and applications that use event metadata to help in different information-seeking tasks. We review current event-mining systems in detail, grouping them by the problem formulations and approaches. The review includes detection of events and actions in one or more continuous sequences, events in edited video streams, unsupervised event discovery, events in a collection of media objects, and a discussion on ongoing benchmark activities. These problems span a wide range of multimedia domains such as surveillance, meetings, broadcast news, sports, documentary, and films, as well as personal and online media collections. We conclude this survey with a brief outlook on open research directions.

show abstract

Automatically extracting highlights for TV Baseball programs

Cited by 339 publications

References 12 publications

Multi-sensory integration of spatio-temporal segmentation cues: one plus one does not always equal two

Multi-sensory integration of spatio-temporal segmentation cues: one plus one does not always equal two

Action boundaries detection in a video

Event Mining in Multimedia Streams

Contact Info

Product

Resources

About