The 2005 PASCAL Visual Object Classes Challenge

By Mark Everingham, Andrew Zisserman, Christopher K. I. Williams, Luc Van Gool, Moray Allan, Charles M. Bishop, Olivier Chapelle, Navneet Dalal, Thomas Deselaers, Gyuri Dorkó and 24 more. 2005

525 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Evaluation & Benchmarks

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

1. Luc Van Gool
2. Trevor Darrell
3. Andrew Zisserman
4. Xiaogang Wang
5. Dacheng Tao
6. Jitendra Malik
7. Andrea Vedaldi
8. Bernt Schiele

In Media Technology

1. Andrew Zisserman
2. Li Fei-Fei
3. Cordelia Schmid
4. Luc Van Gool
5. Bernt Schiele
6. Arnold M. W. Smeulders
7. Antonio Torralba
8. Svetlana Lazebnik

In Evaluation & Benchmarks

1. Antonio Torralba
2. Li Fei-Fei
3. Trevor Darrell
4. Bernt Schiele
5. Jitendra Malik
6. Cordelia Schmid
7. Luc Van Gool
8. Yi Yang

Citations in the corpus

• A Survey of Autonomous Driving: Common Practices and Emerging Technologies (2019, methodology): “The PASCAL VOC dataset [288], which grew from 2005 to 2012, was one of the first dataset featuring a large amount of data with relevant classes for ADS.”
• The Devil is in the Tails: Fine-grained Classification in the Wild (2017, background): “…is learned from the data rather than hand-crafted by experts [14, 27, 29], (b) the design and construction of large and well annotated datasets [8, 11, 13, 30] supplying researchers with a sufficient amount of data to train learning-based algorithms, and (c) the availability of inexpensive and…”
• Large Scale Visual Recognition (2012, methodology): “Consider, for example, the PASCAL VOC [6, 7] challenge.”
• What Does Classifying More Than 10, 000 Image Categories Tell Us? (2010, methodology): “Following the convention of the PASCAL VOC Challenge, each category is randomly split 50%-50% into a set of training and test images, with a total of 4.5 million images for training and 4.5 million images for testing.”
• Geographic Image Retrieval Using Local Invariant Features (2013, background): “and 256 [21] object class image data sets, and the PASCAL visual object classes data sets [22]).”
• Dataset Issues in Object Recognition (2006, background): “Further details on the challenge, the tested algorithms, and the results of the evaluation can be found in [8].”
• Efficient Segmentation: Learning Downsampling Near Semantic Boundaries (2019, background): “Computational requirements of the contemporaneous approaches and the cost of annotations conditioned the low resolution of images or imprecise (rough) annotations in popular semantic segmentation datasets, such as Caltech [15], [3], Pascal VOC [13, 14, 20], COCO [34].”
• What Is Holding Back Convnets for Detection? (2015, background): “It enriches PASCAL VOC 2012 with 3D annotations in the form of aligned 3D CAD models for 11 classes ( aeroplane , bicycle , boat , bus , car , chair , diningtable , motorbike , sofa , train , and tv monitor ) of the train and val subsets.”
• Cascaded pose regression (2010, background): “Localization is a more subtle problem: in its simplest and most popular form [11], it consists of identifying the smallest rectangular region of the image that contains the object in question.”