VISUAL ATTENTION SESSION
- ICIP 2009, special session: visual attention: models and applications in image and video processing.
Organizers:- Patrick Le Callet, IRCCyN France, patrick.lecallet at univ-nantes.fr
- Olivier Le Meur, University of Rennes 1, France and IRISA, France, olivier.le_meur at irisa.fr
Papers:
- O. Le Meur and P. Le Callet: What we see is most likely to be what matters: visual attention and applications, [pdf] [paper,pdf]
- N. Bruce and P. Kornprobst: On the role of context in probabilistic models of visual saliency, [pdf]
- Y. Li, Y. Zhou, L. Xu, X. Yang and J. Yang, Incremental sparse saliency detection, [pdf]
- H. Liu and I. Heynderickx, Studying the added value of visual attention in objective image quality metrics based on eye movement data, presentation not yet available
- C. Vu and D. Chandler, Main subject detection via adaptive feature selection, [pdf]
- H. Liu, X. Qiu, Q. Huang, S. Jiang and C. Xu, Advertise gently in-image advertising with low intrusiveness, [pdf]
- F. Boulos, W. Chen, B. Parrein and P. Le Callet, Region-of-interest intra prediction for H.264/AVC error resilience, [pdf]
- N. Sadaka and L. Karam, Efficient perceptual attentive super-resolution, presentation not yet available
- SPIE Photonics Europe 2012, special session: visual attention.
Organizers:- Matei Mancas, University of Mons (UMONS), Belgium, matei.mancas at umans.ac.be
- Olivier Le Meur, University of Rennes 1, France and IRISA, France, olivier.le_meur at irisa.fr
Papers:
Fred W. M. Stentiford: Visual attention: low-level and high-level viewpoints, [pdf]
Anna Belardinelli and Andrea Carbone: Motion statistics at the saccade landing point: attentional capture by spatiotemporal features in a gaze-contingent reference, [pdf]
Dubravko Culibrk, Matei Mancas, Srdjan Sladojevic and Vladimir Crnojevic, Data-driven approach to change- and motion-based visual attention modelling, [pdf]
Vincent Courboulay and Matthieu Perreira Da Silva, Real-time computational attention model for dynamic scenes, [pdf]
- WIAMIS 2013 Visual attention, a multidisciplinary topic: from behavioral studies to computer vision applications
- Zhi Liu, Shanghai University, China, liuzhi at staff.shu.edu.cn
- Olivier Le Meur, University of Rennes 1, France and IRISA, France, olivier.le_meur at irisa.fr
- Konstantinos Apostolakis* and Petros Daras, An application framework for implicit sentiment human-centered tagging using attributed affect, [Presentation]
- Zhi Liu*, Olivier Le Meur and Shuhua Luo, Superpixel-based saliency detection, [Presentation]
- Jie Sun and Congyan Lang*, Sample Specific Late Fusion for Saliency Detection
- Furkan Isikdogan* and Albert Salah, Affine invariant salient patch descriptors for image retrieval
- Antoine Coutrot* and Nathalie Guyader, Toward the introduction of auditory information in dynamic visual attention models
Organizers:
Papers:
- ICME 2014 Visual saliency: emerging models and applications in multimedia processing
Organizers:- Zhi Liu, Shanghai University, China, liuzhi at staff.shu.edu.cn
- Olivier Le Meur, University of Rennes 1, France and IRISA, France, olivier.le_meur at irisa.fr
- Xiang Zhang, University of Electronic Science and Technology of China, uestchero at uestc.edu.cn
Description: The proposed special session aims at highlighting the emerging visual saliency models and its applications in the field of multimedia processing. It will provide an interdisciplinary forum bridging across eye movements, computational saliency modeling and interesting saliency- based applications. The research on computational saliency models is originally motivated by simulating human visual attention, and a number of saliency models that exploit bottom-up information or/and top-down information have been proposed in the past decades. Except for the well-known biologically plausible center-surround scheme, a variety of well-defined theories and methods such as information theory, control theory, graph theory, frequency domain analysis, machine learning, sparse representation, etc., have been successfully introduced into saliency modeling. Besides, saliency models have been widely used in a number of applications including human fixation prediction, object detection/segmentation/recognition, image/video retargeting, image/video retrieval, image/video editing, content-based compression, visual tracking, active vision, advertising, human-centric analysis, etc. Although recent years witnessed the great development of both saliency models and the related applications, it is still difficult for the state-of-the-art saliency models to achieve a good saliency detection performance on images/videos with complex scenes. Therefore, it is worthy to further explore new information such as high-level attribute cue and specific object semantic cue, tag information of social images, the influence of audio signals in video, to effectively improve the performance of saliency models. Besides, it is also desirable to investigate new methods for interesting saliency-based applications, such as salient object detection using saliency propagation and multiple hypotheses fusion, and co-salient object detection based on low-rank matrix recovery method. We believe that the topic of the proposed session is within the scope of ICME and will be of great interest for ICME participants. Understanding how people perceive the visual environment and modeling the way we look at multimedia content are fundamental for offering the best multimedia technologies.