Biosketch

Georgios Evangelopoulos holds the Diploma degree (2001) in Electrical and Computer Engineering and Ph.D. degree (2007) from National Technical University of Athens (NTUA). His thesis, on image analysis and computer vision, involved texture modeling for image decomposition, feature extraction and low-level vision. As a graduate research assistant, he participated in diverse National and EU research projects involving audio, visual and multimodal information processing. Holding a Postdoctoral research associate position at CVSP, he worked on audiovisual saliency and computational attention models for video summarization and was appointed lecturer P.D 407/80 for the undergraduate "Signals & Systems" course, School of ECE. His research interests lie in the areas of nonlinear signal and audio processing, visual texture analysis, saliency/abstraction/selection of multimodal sensory information and generalized event detection in audiovisual streams with applications related to image and audio analysis, computer vision and multimedia processing. He is currently a postdoctoral fellow with University of Houston, Dept. of Computer Science, on the areas of Biometrics and Face Recognition. [CV, web]

Research

Audiovisual Saliency and Movie Summarization

Developing saliency models for the audio and visual streams of video data based on local signal modulations. Detecting attentionaly important events based on saliency measures integrated from various modalities, e.g., audio, video, text. Multimodal saliency curves are the basis of a bottom-up, content-intepented video summarization algorithm. [Research page]

Temporal, Spatial & Spatiotemporal Event Detection

Formulating  energy-based region detectors for the detection of salient regions, feature extraction/description and event (i.e. a changes in low-level signal characteristics) detection/modeling in audio (1D), images (2D) or video streams (3D). Applications include classification/recognition of audio sources, visual scenes or human actions.

Image Saliency through Spatial Surprise

Using an information-theoretic approach to study bottom-up spatial saliency, we show how Bayesian surprise can be interpreted to explain spatial saliency. Applications include attention modeling and fixation-prediction, image region detector and image quality assesement. [Research page]

Image Texture Analysis

Texture modeling and analysis methods are based on the multicomponent spatial AM-FM image models. The framework includes multiband models of narrowband components and spatial modulations and energy methods for texture description. We pursue a general treatment of texture in natural images invlolving detection, feature extraction, classification and segmentation. [Research page]

Image Decomposition

We have developed a variational image decomposition scheme of the u+v (cartoon + texture) family of models using explicit texture reconstruction constraints. Texture information is reconstructed from the outputs of linear filters using component selection and the image modulation modeling framework. This general formulation is a u + Kv model, with K texture subcomponents.

Speech and Audio Analysis and Detection

Based on non-linear speech modeling techniques we have developed energy and spectral content signal features. Dominant modulation features are derived through mutliband filtering and Teager-Kaiser energy tracking of narrowband AM-FM components. The features are applied for speech detection and, in the case of generic audio signals, for saliency modeling, event detection and classification.

Preprints/Submissions

• G. Evangelopoulos, A. Zlatintsi, A. Potamianos, P. Maragos, K. Rapantzikos, G. Skoumas and Y. Avrithis,
  Multimodal Saliency and Fusion for Movie Summarization based on Aural, Visual, Textual Attention,
  IEEE Trans. Multimedia, (submitted), 2012.
  
• P. Maragos and G. Evangelopoulos,
  Leveling Cartoons, Texture Markers and Multiscale Image Decomposition,
  (in preparation), 2012.
  

Journal Publications

• I. Kokkinos, G. Evangelopoulos and P. Maragos,
  Texture Analysis and Segmentation using Modulation Features, Generative Models and Weighted Curve Evolution,
  IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 31, no. 1, pp. 142-157, Jan. 2009.
  [pdf] [bib]
• M. Kotti, D. Ververidis, G. Evangelopoulos, I. Panagakis, C.Kotropoulos, P. Maragos and I. Pitas,
  Audio-assisted Movie Dialogue Detection,
  IEEE Transactions on Circuits and Systems for Video Technology, special issue on Event Analysis in Videos, vol. 18, no. 11, pp. 1618-1627, Nov. 2008.
  [pdf] [bib]
• G. Evangelopoulos and P. Maragos,
  Multiband Modulation Energy Tracking for Noisy Speech Detection,
  IEEE Transactions on Audio, Speech and Language Processing, vol. 14, no. 6, pp. 2024-2038, Nov. 2006.
  [pdf] [bib]
• N. Sofou, G. Evangelopoulos and P. Maragos,
  Soil Image Segmentation and Texture Analysis: a Computer Vision Approach,
  IEEE Geoscience and Remote Sensing Letters, vol. 2, no. 4, pp. 394-398, Oct. 2005.
  [pdf] [bib]

Book Chapters

• G. Evangelopoulos, K. Rapantzikos, P. Maragos, Y. Avrithis and A. Potamianos,
  Audiovisual Attention Modeling and Salient Event Detection,
  Multimodal Processing and Interaction: Audio, Video, Text, edited by P. Maragos, A. Potamianos and P. Gros, Springer-Verlag, 2008.
  [springer] [chapter doi] [book doi] [bib]

Conference Publications

• C. Georgakis, P. Maragos, G. Evangelopoulos and D. Dimitriadis,
  Dominant spatio-temporal modulations and energy tracking in videos: Application to interest point detection for action recognition,
  Proc. IEEE Int'l Conf. on Image Processing (ICIP), Orlando, FL, Oct. 2012.
• A. Zlatintsi, P. Maragos, A. Potamianos and G. Evangelopoulos,
  A Saliency-Based Approach to Audio Event Detection and Summarization,
  Proc. 20th European Signal Processing Conf. (EUSIPCO), Bucharest, Romania, Aug. 2012.
  [pdf]
• N. Malandrakis, A. Potamianos, G. Evangelopoulos, and A. Zlatintsi,
  A supervised approach to movie emotion tracking,
  Proc. IEEE Int'l Conf. on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, May. 22-27, 2011.
• I. Gkioulekas, G. Evangelopoulos, P. Maragos,
  Spatial Bayesian Surprise for Image Saliency & Quality Assessment,
  Proc. IEEE Int'l Conf. on Image Processing (ICIP-10), Hong-Kong, Sep. 26-29, 2010.
  [pdf]
• G. Evangelopoulos, A. Zlatintsi, G. Skoumas, K. Rapantzikos, A. Potamianos, P. Maragos, Y. Avrithis,
  Video Event Detection and Summarization Using Audio, Visual and Text Saliency,
  Proc. IEEE Int'l Conf. on Acoustics, Speech and Signal Processing (ICASSP-09), Taipei, Taiwan, Apr. 19-24, 2009.
  [pdf] [bib]
• G. Evangelopoulos and P. Maragos,
  Texture Modulation-constrained Image Decomposition,
  Proc. IEEE Int'l Conf. on Image Processing (ICIP-08), San Diego, CA, U.S.A., Oct. 12-15, 2008, pp. 793-796.
  [pdf] [bib]
• G. Evangelopoulos, K. Rapantzikos, A. Potamianos, P. Maragos, A. Zlatintsi, Y. Avrithis,
  Movie Summarization based on Audiovisual Saliency Detection,
  Proc. IEEE Int'l Conf. on Image Processing (ICIP-08), San Diego, CA, U.S.A., Oct. 12-15, 2008, pp. 2528-2531.
  [pdf] [bib]
• G. Evangelopoulos and P. Maragos,
  Image Decomposition into Structure and Texture Subcomponents with Multifrequency Modulation Constraints,
  Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR-08), Anchorage, AK, June 2008.
  [pdf] [bib]
• P. Maragos and G. Evangelopoulos
  Leveling Cartoons, Texture Energy Markers and Image Decomposition,
  Proc. 8th Int'l Symp. Mathematical Morphology (ISMM-07), Rio de Janeiro, Brazil, MCT/INPE, pp. 125-138, 10-13 Oct. 2007.
  [pdf] [bib]
• K. Rapantzikos, G. Evangelopoulos, P. Maragos and Y. Avrithis
  An Audio-Visual Saliency Model for Movie Summarization,
  Proc. IEEE Int' l Workshop on Multimedia Signal Processing (MMSP-07), Chania, Greece, Oct. 2007.
  [pdf] [bib]
• G. Evangelopoulos, I. Kokkinos and P. Maragos,
  Advances in Variational Image Segmentation using AM-FM Models: Regularized Demodulation and Probabilistic Cue Integration,
  Proc. Int' l Workshop on Variational and Level Set Methods (VLSM-05), Beijing, China, Oct. 2005, Springer LNCS, vol. 3275, pp. 121-136.
  [pdf] [bib]
• A. Sofou, G. Evangelopoulos and P. Maragos,
  Coupled Geometric and Texture PDE-based Segmentation,
  Proc. IEEE Int' l Conf. on Image Processing (ICIP-05), Genova, Italy, Sep. 2005.
  [pdf] [bib]
• G. Evangelopoulos and P. Maragos,
  Speech Event Detection Using Multiband Modulation Energy,
  Proc. Interspeech 2005 - Eurospeech, Lisbon, Portugal, 4-8 Sep. 2005, pp. 685-688.
  [pdf] [bib]
• I. Kokkinos, G. Evangelopoulos and P. Maragos,
  Advances in Texture Analysis: Energy Dominant Component and Multiple Hypothesis Testing,
  Proc. IEEE Int' l Conf. on Image Processing (ICIP-04), Singapore, Oct. 2004, vol. 3, pp. 1509-1512.
  [pdf] [bib]
• I. Kokkinos, G. Evangelopoulos and P. Maragos,
  Modulation-Feature Based Textured Image Segmentation Using Curve Evolution,
  Proc. IEEE Int' l Conf. on Image Processing (ICIP-04), Singapore, Oct. 2004, vol. 2, pp. 1204-1207.
  [pdf] [bib]

Theses

• G. Evangelopoulos,
  Texture and Image Microstructure Analysis with Modulation Models, Energy and Variational Techniques: Detection & Separation  (in greek),
  Ph.D. Thesis, School of ECE, NTUA, May 2007. Thesis supervisor: P. Maragos.
  [pdf] [ps.rar] [bib] [abstract greek, english] [artemis ntua]
• G. Evangelopoulos,
  Detection and Analysis of Visual Texture and Signal Microstructures  (in greek),
  Ph.D. Progress Report, School of ECE, NTUA, Oct. 2005.
  [zip] [bib]
• G. Evangelopoulos,
  Advanced Signal Analysis Methods for Speech-Silence-Noise Detection  (in greek),
  Diploma Thesis, School of ECE, NTUA, Oct. 2001. Thesis supervisor: P. Maragos.
  [zip] [bib]

Software

• AVSal: MATLAB toolbox for audiovisual saliency curve extraction and audiovisual event detection. See here.
• movieSUM: MATLAB-based toolbox for audiovisual saliency-based automatic movie summarization. See here.