Object-based visual attention for computer vision

By Yaoru Sun, Robert B. Fisher. Artificial Intelligence, 2003

346 citations recorded by the source corpus.

In this paper, a novel model of object-based visual attention extending Duncan's Integrated Competition Hypothesis [Phil. Trans. R. Soc. London B 353 (1998) 1307-1317] is presented. In contrast to the attention mechanisms used in most previous machine vision systems which drive attention based on the spatial location hypothesis, the mechanisms which direct visual attention in our system are object-driven as well as feature-driven. The competition to gain visual attention occurs not only within an object but also between objects. For this purpose, two new mechanisms in the proposed model are described and analyzed in detail. The first mechanism computes the visual salience of objects and groupings; the second one implements the hierarchical selectivity of attentional shifts. The results of the new approach on synthetic and natural images are reported.

View Paper: https://www.semanticscholar.org/paper/43ca5c713727611febc01c5b709fc0b857f5454a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

State-of-the-Art in Visual Attention Modeling (2013, methodology): “, [14], [117]) and processed by center-surround processes inspired by neural responses in lateral geniculate nucleus (LGN) [10] and V1 cortex.”
A Novel Multiresolution Spatiotemporal Saliency Detection Model and Its Applications in Image and Video Compression (2010, methodology): “According to Scholl’s theory, Sun et al. proposed the ﬁrst HS implementation which shifts attention from one grouping to another one or from a parent grouping to its sub-grouping as well as implemented a model that can focus its attention from far to near or from coarse to ﬁne [36].”
Controllable Multi-Interest Framework for Recommendation (2020, background): “Attention The originality of attention mechanism can be traced back to decades ago in fields of computer vision [5, 50].”
Computational visual attention systems and their cognitive foundations: A survey (2010, methodology): “Examples of linear filter systems of visual attention are presented for instance in [Milanese 1993; Itti et al. 1998; Backer et al. 2001; Sun and Fisher 2003; Heidemann et al. 2004; Hamker 2005; Frintrop 2005].”
Modeling attention to salient proto-objects (2006, unknown): “Closely following and extending Duncan's Integrated Competition Hypothesis (Duncan, 1997), Sun and Fisher (2003) developed and implemented a common framework for object-based and location-based visual attention using " groupings " .”