Is bottom-up attention useful for object recognition?

By Ueli Rutishauser, Dirk B. Walther, Christof Koch, Pietro Perona. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., 2004

663 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/6addf8bddf2fd2e194a662a8a7f0ea001f2a29a7

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

An Integrated Model of Top-Down and Bottom-Up Attention for Optimizing Detection Speed (2006, background): “This area has received much interest recently, with several systems using attention as a front-end to accelerate detection speed [10], to reduce complexity of automated multi-target detection and tracking [31], and to enable automated learning and recognition of objects in cluttered scenes [21].”
Graph-Based Visual Saliency (2006, background): “Besides the purely scientiic goal of understanding this remarkable behavior of humans, and animals in general, to consistently xate on "important" information, there is tremendous engineering application, e.g. in compression and recognition [13].”
Global contrast based salient region detection (2011, background): “Extracted saliency maps are widely used in many computer vision applications including objectof-interest image segmentation [13, 18], object recognition [25], adaptive compression of images [6], contentaware image editing [28, 33, 30, 9], and image retrieval [4].”
Global Contrast Based Salient Region Detection (2015, unknown): “F”
Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection (2020, background): “Therefore, it often serves as the first step in many researches, like object tracking [20], object recognition [28], action categorization [1] and so on.”
Saliency filters: Contrast based filtering for salient region detection (2012, background): “However, recent research has shown that computational models simulating low-level stimuli-driven attention [17, 20, 21] are quite successful and represent useful tools in many application scenarios, including image segmentation [14], resizing [5] and object detection [27].”
Enhanced-alignment Measure for Binary Foreground Map Evaluation (2018, background): “, 2014], object detection, recognition [Kanan and Cottrell, 2010; Rutishauser et al. , 2004], foreground extraction [Blake et al. , 2004], and salient object detection [Hou et al. , 2018; Borji et al. , 2015], and is crucial for making statements regarding which models perform better.”
Context based object categorization: A critical survey (2010, unknown): “[28] proposed that recognition performance for objects in highly cluttered scenes can be improved dramatically with use of bottom-up attentional frameworks.”
Context-aware saliency detection (2010, background): “This type of saliency is useful for several high-level tasks, such as object recognition [20] or segmentation [18].”
Space-Variant Descriptor Sampling for Action Recognition Based on Saliency and Eye Movements (2012, background): “Saliency-based approaches have been successfully applied to various computer vision tasks, too, such as image compression [10], quality assessment, and object recognition [11,12,13].”
Structure-Measure: A New Way to Evaluate Foreground Maps (2017, background): “, 2021), object detection and recognition (Borji et al., 2013a, 2015;Kanan& Cottrell, 2010; Rutishauser et al., 2004; Islam et al., 2018), video summarization (Ghosh et al.”
Discriminative Autoencoders for Small Targets Detection (2014, background): “In this case, the objects to be detected are deﬁned as the regions of the image which do not have the same statistics as the background e.g. [19], [20].”
Learning to Detect A Salient Object (2007, background): “Recent studies [18, 22, 26] demonstrated that visual attention helps object recognition, tracking, and detection as well.”