Automatic thumbnail cropping and its effectiveness

By Bongwon Suh, Haibin Ling, B. Bederson, David W. Jacobs. ACM Symposium on User Interface Software and Technology, 2003

484 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/df94ebff0290bfcb4bed05e2ab1693d42fdec97d

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

What Do Different Evaluation Metrics Tell Us About Saliency Models? (2016, background): “[54], [87], thumbnailing [55], [76], content-aware image re-targeting and cropping [3], [4], [69], [72], [85], rendering and visualization [42], [52], collage [31], [86] and artistic rendering [20], [41] require ranking (by importance or saliency) different image regions.”
Saliency Detection on Light Field (2017, unknown): “For example, successful salient object detection algorithms facilitate automated image segmentation [1], more reliable object detection [2], effective image thumbnailling [3] and retargeting [4].”
Attentive Systems: A Survey (2017, methodology): “Suh et al. (2003) propose a general thumbnail cropping method based on a saliency model that finds the informative portion of images and cuts out the non-core part of images.”
An Assisted Photography Framework to Help Visually Impaired Users Properly Aim a Camera (2014, background): “One could also opt to apply image filters, crop the final best image to focus on an ROI [Suh et al. 2003], perform a content-aware resizing operation [Avidan and Shamir 2007], or another image improvement process.”
Context-aware saliency detection (2010, background): “Examples include image classification [14], summarization of a photo collection [17], thumbnailing [21], and retargeting [19].”
Unconstrained Salient Object Detection via Proposal Subset Optimization (2016, methodology): “Given a saliency map, some methods find the best detection window based on heuristics [29, 48, 45, 32].”
A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping (2019, methodology): “ATC [16] 0.”
Gaze-based interaction for semi-automatic photo cropping (2006, methodology): “These models can be used to make predictions about important content under the assumption that something distinctive must therefore be important [28, 29].”
Mesh saliency (2005, methodology): “The motivation behind this is that the key image property whose variations are critical is the intensity.”
Gender shades : intersectional phenotypic and demographic evaluation of face datasets and gender classifiers (2017, background): “For image editing, face detection can enable automatic photo cropping that retains the majority of a face within the resulting photo (Suh et al., 2003; Yamamoto et al., 2016).”
Summarizing visual data using bidirectional similarity (2008, methodology): “(ii) Importance-based cropping methods [3, 11, 15] provide nice results when the interesting information is concentrated in one region (spatial or temporal).”
Scale and object aware image retargeting for thumbnail browsing (2011, methodology): “The traditional method, scaling, which shrinks original images directly into thumbnails, often brings difﬁ-culties in searching and recognition [21], especially for tiny thumbnails shown on small size screens, such as cell phones or PDAs.”
Non-homogeneous Content-driven Video-retargeting (2007, background): “[8] considered the problem of cropping optimal thumbnails from an input image.”
Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency (2021, background): “In addition, automated image cropping can help individuals identify important content in the image and do it faster compared to no-crop [62].”