An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D projection. These features share similar properties with neurons in inferior temporal cortex that are used for object recognition in primate vision. Features are efficiently detected through a staged filtering approach that identifies stable points in scale space. Image keys are created that allow for local geometric deformations by representing blurred image gradients in multiple orientation planes and at multiple scales. The keys are used as input to a nearest-neighbor indexing method that identifies candidate object matches. Final verification of each match is achieved by finding a low-residual least-squares solution for the unknown model parameters. Experimental results show that robust object recognition can be achieved in cluttered partially-occluded images with a computation time of under 2 seconds.

Spatial attention: Visual selection and deployment over space The attentional spotlight and spatial cueing Attentional shifts, splits, and resolution Object-based Selection The visual search paradigm Top-down and bottom-up control of attention Inhibitory mechanisms of attention Invalid cueing Negative priming Inhibition of return Temporal attention: Visual selection and deployment over time Single target search Attentional blink and attentional dwell time Repetition blindness NEURAL MECHANISMS OF SELECTION Single-cell physiological method Event-related potentials Functional imaging: PET and fMRI

& The processing required to decide whether a briefly flashed natural scene contains an animal can be achieved in 150 msec (Thorpe, Fize, & Marlot, 1996). Here we report that extensive training with a subset of photographs over a 3-week period failed to increase the speed of the processing underlying such rapid visual categorizations: Completely novel scenes could be categorized just as fast as highly familiar ones. Such data imply that the visual system processes new stimuli at a speed and with a number of stages that cannot be compressed. This rapid processing mode was seen with a wide range of visual complex images challenging the idea that short reaction times can only be seen with simple visual stimuli and implying that highly automatic feed-forward mechanisms underlie a far greater proportion of the sophisticated image analysis needed for everyday vision than is generally assumed. & Both humans and monkeys are able to categorize natural images accurately and very rapidly (Fabre-Thorpe, Richard, & Thorpe, 1998; Thorpe, Fize, & Marlot, 1996). The nature of the underlying mechanisms is currently

There is considerable evidence that object recognition in primates is based on the detection of local image features of intermediate complexity that are largely invariant to imaging transformations. A computer vision system has been developed that performs object recognition using features with similar properties. Invariance to image translation, scale and rotation is achieved by first selecting stable key points in scale space and performing feature detection only at these locations. The features measure local image gradients in a manner modeled on the response of complex cells in primary visual cortex, and thereby obtain partial invariance to illumination, affine change, and other local distortions. The features are used as input to a nearest-neighbor indexing method and Hough transform that identify candidate object matches. Final verification of each match is achieved by finding a best-fit solution for the unknown model parameters and integrating the features consistent with these parameter values. This verification procedure provides a model for the serial process of attention in human vision that integrates features belonging to a single object. Experimental results show that this approach can achieve rapid and robust object recognition in cluttered partially-occluded images.

The problem of representing the spatial structure of images, which arises in visual object processing, is commonly described using terminology borrowed from propositional theories of cognition, notably, the concept of compositionality. The classical propositional stance mandates representations composed of symbols, which stand for atomic or composite entities and enter into arbitrarily nested relationships.

visual structure

This paper explores a psychological attention approach for sports highlight detection. A multiresolution autoregressive algorithm is proposed to fuse misaligned audio-visual time sequences and estimate an unified attention curve. Game highlights are found by ranking attention intensity; contentbased events are filtered out by allocating local attention peaks. The test bed includes six complete football games from World Cup 2002, 2006 and Champion League 2006, and two content suppliers, BBC and ITV. Two evaluations are presented, the comparison on average attention and event attention, and the ranking of goal events. Experiments show this fusion framework is robust on different data collections. 1.

Consider the problem of removing a subset of images or other visually complex objects from a crowded visualization in order to increase intelligibility. Occlusion severely reduces image intelligibility, and empty space conveys no image information, so optimal choices will tend toward constant density displays. However, previous constant density algorithms are based on global density, which leads to occlusion and empty space if the density is not uniform. This paper introduces an algorithm that considers the layout of individual objects and avoids occlusion altogether. Efficiency concerns are important for dynamic summaries of the Informedia Digital Video Library, which has hundreds of thousands of shots from news stories. Posting multiple queries that take into account parameters of the visualization as well as the original query reduces the amount of work required.

Abstract. Attention is a psychological measurement of human reflection against stimulus. We propose a general framework of highlight detection by comparing attention intensity during the watching of sports videos. Three steps are involved: adaptive selection on salient features, unified attention estimation and highlight identification. Adaptive selection computes feature correlation to decide an optimal set of salient features. Unified estimation combines these features by the technique of multi-resolution auto-regressive (MAR) and thus creates a temporal curve of attention intensity. We rank the intensity of attention to discriminate boundaries of highlights. Such a framework alleviates semantic uncertainty around sport highlights and leads to an efficient and effective highlight detection. The advantages are as follows: (1) the capability of using data at coarse temporal resolutions; (2) the robustness against noise caused by modality asynchronism, perception uncertainty and feature mismatch; (3) the employment of Markovian constrains on content presentation, and (4) multi-resolution estimation on attention intensity, which enables the precise allocation of event boundaries. Key words:highlight detection, attention computation, sports video analysis 1

What are the brain mechanisms allowing a stimulus to enter our awareness? Some theories suggest that this process engages resources overlapping with those required for action control, but experimental support for these ideas is still required. Here, we investigated whether the human frontal eye ®eld (FEF), an area known to control eye movements, is involved in visual awareness. Volunteers participated in a backward masking task in which they were able to detect a target in a small proportion of trials. We observed that a single pulse of transcranial magnetic stimulation applied over the FEF shortly before the target's onset facilitated visual sensitivity; subjects were able to detect an otherwise subliminal object. These results show that modulating the neuronal activity of the FEF can enhance visual detection, thereby yielding new insights into the neural basis of visual awareness.