Coherence Progress: A Measure of Interestingness Based on Fixed Compressors

Schaul, Tom; Pape, Leo; Glasmachers, Tobias; Graziano, Vincent; Schmidhuber, Jürgen

doi:10.1007/978-3-642-22887-2_3

Cited by 10 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This was already noticed in the beginnings of cognitive psychology [1,30] and calls for a direct modeling of visual concepts which attract human attention. For example, Itti and Baldi came up with a theory of Bayesian surprise [11] or Schmidhuber and co-workers [21,20] define interestingness as allowing for learning new things: "Neither the arbitrary nor the fully predictable is truly surprising or interesting -only data with still unknown but learnable statistical regularities are".…”

Section: Computational Perspectivementioning

confidence: 99%

See 1 more Smart Citation

Visual interestingness in image sequences

Gräbner

Nater

Druey

et al. 2013

Proceedings of the 21st ACM International Conference on Multimedia

View full text Add to dashboard Cite

Interestingness is said to be the power of attracting or holding one's attention (because something is unusual or exciting, etc.). We, as humans, have the great capacity to direct our visual attention and judge the interestingness of a scene. Consider for example the image sequence in the figure on the right. The spider in front of the camera or the snow on the lens are examples of events that deviate from the context since they violate the expectations, and therefore are considered interesting. On the other hand, weather changes or a camera shift, do not raise human attention considerably, even though large regions of the image are influenced. In this work we firstly investigate what humans consider as "interesting" in image sequences. Secondly we propose a computer vision algorithm to automatically spot these interesting events. To this end, we integrate multiple cues inspired by cognitive concepts and discuss why and to what extent the automatic discovery of visual interestingness is possible. ABSTRACTInterestingness is said to be the power of attracting or holding one's attention (because something is unusual or exciting, etc.). 1 We, as humans, have the great capacity to direct our visual attention and judge the interestingness of a scene. Consider for example the image sequence in the figure on the right. The spider in front of the camera or the snow on the lens are examples of events that deviate from the context since they violate the expectations, and therefore are considered interesting. On the other hand, weather changes or a camera shift, do not raise human attention considerably, even though large regions of the image are influenced. In this work we firstly investigate what humans consider as "interesting" in image sequences. Secondly we propose a computer vision algorithm to automatically spot these interesting events. To this end, we integrate multiple cues inspired by cognitive concepts and discuss why and to what extent the automatic discovery of visual interestingness is possible. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org. Categories and Subject Descriptors

show abstract

Section: Computational Perspectivementioning

confidence: 99%

“…To show the benefit of our method, we compare it to other related works. First, we have implemented a technique based on [20], where the interestingness scoreŝt = − ∂ 2 ∂t 2 lC ([I1, . .…”

Section: Individual Cuesmentioning

confidence: 99%

Visual interestingness in image sequences

Gräbner

Nater

Druey

et al. 2013

Proceedings of the 21st ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…The intuitive notion of interestingness [16] can be summarized as the 'potential for the discovery of novel patterns.' A sound quantitative measure of interestingness must assign low values to patterns the observer already knows, and patterns the observer cannot learn; and high values to patterns the observer does not yet know, but can still discover.…”

Section: B Methods For Explorationmentioning

confidence: 99%

Artificial curiosity with planning for autonomous perceptual and cognitive development

Luciw

Graziano

Ring

et al. 2011

2011 IEEE International Conference on Development and Learning (ICDL)

Self Cite

View full text Add to dashboard Cite

Abstract-Autonomous agents that learn from reward on highdimensional visual observations must learn to simplify the raw observations in both space (i.e., dimensionality reduction) and time (i.e., prediction), so that reinforcement learning becomes tractable and effective. Training the spatial and temporal models requires an appropriate sampling scheme, which cannot be hardcoded if the algorithm is to be general. Intrinsic rewards are associated with samples that best improve the agent's model of the world. Yet the dynamic nature of an intrinsic reward signal presents a major obstacle to successfully realizing an efficient curiosity-drive. TD-based incremental reinforcement learning approaches fail to adapt quickly enough to effectively exploit the curiosity signal. In this paper, a novel artificial curiosity system with planning is implemented, based on developmental or continual learning principles. Least-squares policy iteration is used with an agent's internal forward model, to efficiently assign values for maximizing combined external and intrinsic reward. The properties of this system are illustrated in a highdimensional, noisy, visual environment that requires the agent to explore. With no useful external value information early on, the self-generated intrinsic values lead to actions that improve both its spatial (perceptual) and temporal (cognitive) models. Curiosity also leads it to learn how it could act to maximize external reward.

show abstract

“…Unlike the closely related concept of aesthetic beauty of images [6,19], the computational prediction of interestingness has not been studied extensively. Based on above psychological findings, several recent attempts were made to directly predict interestingness [7,22]. One of the most recent works by [10] considers three factors: unusualness (novelty), aesthetics, and general preferences for certain scene types (e.g., outdoor vs. indoor).…”

Section: Introductionmentioning

confidence: 99%

Sentiment Flow for Video Interestingness Prediction

Yoon

Pavlović

2014

Proceedings of the 1st ACM International Workshop on Human Centered Event Understanding From Multimedia

View full text Add to dashboard Cite

Computational analysis and prediction of digital media interestingness is a challenging task, largely driven by subjective nature of interestingness. Several attempts were made to construct a reliable measure and obtain a better understanding of interestingness based on various psychological study results. However, most current works focus on interestingness prediction for images. While the video affective analysis has been studied for quite some time, there are few works that explictly try to predict interestingness of videos. In this work, we extend a recent pilot study on the video interestingness prediction by using a mid-level representation of sentiment (emotion) sequence. We evaluate our proposed framework on three datasets including the datasets proposed by the pilot study and show that the result effectively verifies a promising utility of the approach.

show abstract

Coherence Progress: A Measure of Interestingness Based on Fixed Compressors

Cited by 10 publications

References 7 publications

Visual interestingness in image sequences

Visual interestingness in image sequences

Artificial curiosity with planning for autonomous perceptual and cognitive development

Sentiment Flow for Video Interestingness Prediction

Contact Info

Product

Resources

About