Throwing Down the Visual Intelligence Gauntlet

Tan, Cheston; Leibo, Joel Z.; Poggio, Tomaso

doi:10.1007/978-3-642-28661-2_1

Cited by 7 publications

(8 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although outperformed by machines in some recognition tasks in recent years (O'Toole et al, 2007; Tan et al, 2013), our visual system appears particularly adept at discriminating, categorizing and identifying faces. On one level, this is perhaps understandable.…”

Section: Introductionmentioning

confidence: 96%

Toward a unified model of face and object recognition in the human visual system

Wallis¹

2013

Front. Psychol.

View full text Add to dashboard Cite

Our understanding of the mechanisms and neural substrates underlying visual recognition has made considerable progress over the past 30 years. During this period, accumulating evidence has led many scientists to conclude that objects and faces are recognised in fundamentally distinct ways, and in fundamentally distinct cortical areas. In the psychological literature, in particular, this dissociation has led to a palpable disconnect between theories of how we process and represent the two classes of object. This paper follows a trend in part of the recognition literature to try to reconcile what we know about these two forms of recognition by considering the effects of learning. Taking a widely accepted, self-organizing model of object recognition, this paper explains how such a system is affected by repeated exposure to specific stimulus classes. In so doing, it explains how many aspects of recognition generally regarded as unusual to faces (holistic processing, configural processing, sensitivity to inversion, the other-race effect, the prototype effect, etc.) are emergent properties of category-specific learning within such a system. Overall, the paper describes how a single model of recognition learning can and does produce the seemingly very different types of representation associated with faces and objects.

show abstract

Section: Introductionmentioning

confidence: 96%

Toward a unified model of face and object recognition in the human visual system

Wallis¹

2013

Front. Psychol.

View full text Add to dashboard Cite

show abstract

“…This is an innovative crowdsourcing-based performance evaluation scheme which allows people all over the world, from the layman to the researcher, to actively take part in the evaluation process of a set of evolving visual agents using a simple user-friendly interface. This is also close in spirit to the "visual Turing test" recently advocated by Tomaso Poggio (Tan et al, 2013) and, independently, by Donald Geman 5 . Interestingly, the central role of social aspects in the evaluation process has long been recognized in other subfields of computer science such as computer security, where people do not think that a science of security equal to traditional physical sciences can be ever developed (Evans and Stolfo, 2011).…”

Section: Discussionmentioning

confidence: 69%

Pattern recognition between science and engineering: A red herring?

Pelillo

Scantamburlo

Schiaffonati

2015

Pattern Recognition Letters

View full text Add to dashboard Cite

“…Especially for dark background in visible image, adaptive adjustment in image brightness is performed to increase its contrast. Compared with results in literature [6], [8] and [9], in the same decomposition layer, the method in this paper can get the biggest information entropy, standard deviation, mutual information and spatial frequency, which means this algorithm has significant advantages in performance and is superior than other algorithms.…”

Section: Evaluation and Analysis Of Fusion Experimentsmentioning

confidence: 59%

“…Low-level feature extraction method has quickness, simplicity, economy and other advantages, but the two methods from the geometry and statistical significance express the image, does not have biological visual significance, lack of invariance on the changing goal, and the generalization ability is poor. 2) Depth features, said: hierarchical network structure based on the extracted features inspired by biological visual representation, such as HMAX features [8], ST feature [9], Gist characteristics [10] and NSCT features [11]. Depth features, said: hierarchical network structure based on the extracted features inspired by biological visual.…”

Section: Introductionmentioning

confidence: 99%

Image Fusion Technology Based on Bio-inspired Features

Xing¹,

Li²,

Chen³

et al. 2013

2013 Ninth International Conference on Intelligent Information Hiding and Multimedia Signal Processing

View full text Add to dashboard Cite

Infrared and visible image fusion, as a powerful tool for the object detection and recognition, has developed with the advent of various imaging modalities. However, resulting images of traditional methods are always difficult to compromise between multimodalities. This paper has solved this problem by a variable-weight fusion rule based on the non-subsampled contourlet transform (NSCT). The original images are combined in the multiscaled space and the fused image is obtained in the bio-inspired feature frame. Validation experiments on infrared and visible images are for two purposes: the comparison among different fusion rules and the impact of the multiscaled analysis in infrared and visible image fusion. In order to evaluate the proposed method, information entropy (IE), standard deviation (STD), spatial frequency (SF) and mutual information (MI) are adopted to compare with Laplace, wavelet, and NSCT et al. Results are shown that all evaluation value of the proposed method is higher than that of other methods, and it is a better image fusion method.

show abstract

Throwing Down the Visual Intelligence Gauntlet

Cited by 7 publications

References 31 publications

Toward a unified model of face and object recognition in the human visual system

Toward a unified model of face and object recognition in the human visual system

Pattern recognition between science and engineering: A red herring?

Image Fusion Technology Based on Bio-inspired Features

Contact Info

Product

Resources

About