Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

High-level event recognition in unconstrained videos

High-level event recognition in unconstrained videos The goal of high-level event recognition is to automatically detect complex high-level events in a given video sequence. This is a difficult task especially when videos are captured under unconstrained conditions by non-professionals. Such videos depicting complex events have limited quality control, and therefore, may include severe camera motion, poor lighting, heavy background clutter, and occlusion. However, due to the fast growing popularity of such videos, especially on the Web, solutions to this problem are in high demands and have attracted great interest from researchers. In this paper, we review current technologies for complex event recognition in unconstrained videos. While the existing solutions vary, we identify common key modules and provide detailed descriptions along with some insights for each of them, including extraction and representation of low-level features across different modalities, classification strategies, fusion techniques, etc. Publicly available benchmark datasets, performance metrics, and related research forums are also described. Finally, we discuss promising directions for future research. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Multimedia Information Retrieval Springer Journals

High-level event recognition in unconstrained videos

Download PDF
29 pages

Loading next page...
 
/lp/springer-journals/high-level-event-recognition-in-unconstrained-videos-rOz0o2rFXx
Publisher
Springer Journals
Copyright
Copyright © 2012 by Springer-Verlag London
Subject
Computer Science; Multimedia Information Systems; Information Storage and Retrieval; Information Systems Applications (incl. Internet); Data Mining and Knowledge Discovery; Image Processing and Computer Vision; Computer Science, general
ISSN
2192-6611
eISSN
2192-662X
DOI
10.1007/s13735-012-0024-2
Publisher site
See Article on Publisher Site

Abstract

The goal of high-level event recognition is to automatically detect complex high-level events in a given video sequence. This is a difficult task especially when videos are captured under unconstrained conditions by non-professionals. Such videos depicting complex events have limited quality control, and therefore, may include severe camera motion, poor lighting, heavy background clutter, and occlusion. However, due to the fast growing popularity of such videos, especially on the Web, solutions to this problem are in high demands and have attracted great interest from researchers. In this paper, we review current technologies for complex event recognition in unconstrained videos. While the existing solutions vary, we identify common key modules and provide detailed descriptions along with some insights for each of them, including extraction and representation of low-level features across different modalities, classification strategies, fusion techniques, etc. Publicly available benchmark datasets, performance metrics, and related research forums are also described. Finally, we discuss promising directions for future research.

Journal

International Journal of Multimedia Information Retrieval – Springer Journals

Published: Nov 13, 2012

References

  • Human activity analysis: a review
    Aggarwal, JK; Ryoo, MS
  • Human action recognition in videos using kinematic features and multiple instance learning
    Ali, S; Shah, M
  • Maintaining knowledge about temporal intervals
    Allen, JF
  • Kinematic features of unrestrained vertical arm movements
    Atkeson, CG; Hollerbach, JM
  • The bag-of-frames approach to audio pattern recognition: a sufficient model for urban soundscapes but not for polyphonic music
    Aucouturier, JJ; Defreville, B; Pachet, F
  • Event detection and recognition for semantic annotation of video
    Ballan, L; Bertini, M; Bimbo, AD; Seidenari, L; Serra, G
  • SURF: speeded up robust features
    Bay, H; Ess, A; Tuytelaars, T; Gool, L
  • A graphical model for audiovisual object tracking
    Beal, MJ; Jojic, N; Attias, H
  • Movement, activity, and action: the role of knowledge in the perception of motion
    Bobick, AF
  • Automatic video classification: a survey of the literature
    Brezeale, D; Cook, D
  • Efficient structure learning of bayesian networks using constraints
    Campos, C; Ji, Q
  • Audio-based context recognition
    Eronen, A; Peltonen, V; Tuomi, J; Klapuri, A; Fagerlund, S; Sorsa, T; Lorho, G; Huopaniemi, J
  • Object detection with discriminatively trained part based models
    Felzenszwalb, P; Girshick, R; McAllester, D; Ramanan, D
  • Verl: an ontology framework for representing and annotating video events
    Francois, ARJ; Nevatia, R; Hobbs, J; Bolles, RC
  • A comparison of algorithms for inference and learning in probabilistic graphical models
    Frey, BJ; Jojic, N
  • Visual word ambiguity
    Gemert, JC; Veenman, CJ; Smeulders, AWM; Geusebroek, JM
  • Investigating causal relations by econometric models and cross-spectral methods
    Granger, C
  • Learning Kernel classifiers: theory and algorithms
    Herbrich, R
  • Semantic analysis of soccer video using dynamic bayesian network
    Huang, CL; Shih, HC; Chao, CY
  • Recognizing planned, multiperson action
    Intille, SS; Bobick, AF
  • Recognition of visual activities and interactions by stochastic parsing
    Ivanov, YA; Bobick, AF
  • Representations of keypoint-based semantic concept detection: a comprehensive study
    Jiang, YG; Yang, J; Ngo, CW; Hauptmann, AG
  • Natural language description of human activities from video images based on concept hierarchy of actions
    Kojima, A; Tamura, T; Fukunaga, K
  • On space-time interest points
    Laptev, I
  • Understanding video events: a survey of methods for automatic interpretation of semantic occurrences in videos
    Lavee, G; Rivlin, E; Rudzsky, M
  • Audio-based semantic concept classification for consumer video
    Lee, K; Ellis, DPW
  • Expandable data-driven graphical modeling of human actions based on salient postures
    Li, W; Zhang, Z; Liu, Z
  • Feature detection with automatic scale selection
    Lindeberg, T
  • Distinctive image features from scale-invariant keypoints
    Lowe, D
  • Audio keywords discovery for text-like audio content analysis and retrieval
    Lu, L; Hanjalic, A
  • Sound retrieval and ranking using sparse auditory representations
    Lyon, RF; Rehn, M; Bengio, S; Walters, TC; Chechik, G
  • Texture features for browsing and retrieval of image data
    Manjunath, BS; Ma, WY
  • Scale and affine invariant interest point detectors
    Mikolajczyk, K; Schmid, C
  • A performance evaluation of local descriptors
    Mikolajczyk, K; Schmid, C
  • A comparison of affine region detectors
    Mikolajczyk, K; Tuytelaars, T; Schmid, C; Zisserman, A; Matas, J
  • Video handling with music and speech detection
    Minami, K; Akutsu, A; Hamada, H; Tonomura, Y
  • Randomized clustering forests for image classification
    Moosmann, F; Nowak, E; Jurie, F
  • Large-scale concept ontology for multimedia
    Naphade, M; Smith, J; Tesic, J; Chang, SF; Hsu, W; Kennedy, L; Hauptmann, A; Curtis, J
  • Spatiotemporal localization and categorization of human actions in unsegmented image sequences
    Oikonomopoulos, A; Patras, I; Pantic, M
  • Multiresolution gray-scale and rotation invariant texture classification with local binary patterns
    Ojala, T; Pietikainen, M; Maenpaa, T
  • Modeling the shape of the scene: a holistic representation of the spatial envelope
    Oliva, A; Torralba, A
  • Head-driven phrase structure grammar
    Pollard, C; Sag, I
  • Survey on vision-based human action recognition
    Poppe, R
  • The earth mover’s distance as a metric for image retrieval
    Rubner, Y; Tomasi, C; Guibas, LJ
  • LabelMe: a database and web-based tool for image annotation
    Russell, B; Torralba, A; Murphy, K; Freeman, WT
  • Event detection in field sports video using audio-visual features and a support vector machine
    Sadlier, DA; O’Connor, NE
  • Evaluating color descriptors for object and scene recognition
    Sande, KEA; Gevers, T; Snoek, CGM
  • Content based image retrieval at the end of the early years
    Smeulders, AWM; Worring, M; Santini, S; Gupta, A; Jain, R
  • Concept-based video retrieval
    Snoek, CGM; Worring, M
  • Content-based video parsing and indexing based on audio-visual interaction
    Tsekeridou, S; Pitas, I
  • Machine recognition of human activities: a survey
    Turaga, P; Chellappa, R; Subrahmanian, VS; Udrea, O
  • Real-time visual concept classification
    Uijlings, JRR; Smeulders, AWM; Scha, RJH
  • Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion
    Vincent, P; Larochelle, H; Lajoie, I; Bengio, Y; Manzagol, PA
  • Free viewpoint action recognition using motion history volumes
    Weinland, D; Ronfard, R; Boyer, E
  • Structure analysis of soccer video with domain knowledge and hidden markov models
    Xie, L; Xu, P; Chang, SF; Divakaran, A; Sun, H
  • A novel framework for semantic annotation and personalized retrieval of sports video
    Xu, C; Wang, J; Lu, H; Zhang, Y
  • Video event recognition using Kernel methods with multilevel temporal alignment
    Xu, D; Chang, SF
  • Brief descriptions of visual features for baseline trecvid concept detectors
    Yanagawa, A; Hsu, W; Chang, SF
  • I2T: Image parsing to text description
    Yao, B; Yang, X; Lin, L; Lee, M; Zhu, S
  • Local features and kernels for classification of texture and object categories: a comprehensive study
    Zhang, J; Marszalek, M; Lazebnik, S; Schmid, C