The PASCAL Visual Object Classes Challenge

By Jianguo Zhang. 2006

3,406 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, 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. Dacheng Tao
3. Ming-Hsuan Yang
4. Xiaogang Wang
5. Jitendra Malik
6. Trevor Darrell
7. Andrew Zisserman
8. Andrea Vedaldi

In Evaluation & Benchmarks

1. Jitendra Malik
2. Trevor Darrell
3. Antonio Torralba
4. Luc Van Gool
5. Li Fei-Fei
6. Bernt Schiele
7. Kaiming He
8. Alexei A. Efros

Citations in the corpus

• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition (2014, methodology): “1% mean Average Precision (mAP) on Pascal VOC 2007 [9] using only a single full-image representation (single-view testing).”
• Data-Efficient Image Recognition with Contrastive Predictive Coding (2019, methodology): “For this we chose object detection on the PASCAL VOC 2007 dataset, a standard benchmark in computer vision (Everingham et al., 2007).”
• Learning Visual Representations with Caption Annotations (2020, methodology): “For TP LDA we use the publicly-available code of [20] to find 40 latent topics among all captions (the number of topics was validated on the validation set of VOC).”
• Colorful Image Colorization (2016, methodology): “We first test the network on PASCAL VOC 2007 [39] classification, following the protocol in [16].”
• Recurrent Neural Networks for Semantic Instance Segmentation (2017, background): “Pascal VOC 2012 [14]: Contains objects of 20 different categories.”
• DeepSetNet: Predicting Sets with Deep Neural Networks (2016, methodology): “The Pascal Visual Object Classes (VOC) [6] benchmark is one of the most widely used datasets for detection and classification.”
• Shape-aware Instance Segmentation (2016, methodology): “Instance-level semantic segmentation, which aims at jointly detecting, segmenting and classifying every individual object in an image, has recently become a core challenge in scene understanding [4, 21, 8].”
• Deep Watershed Transform for Instance Segmentation (2016, background): “, Pascal VOC [8], BSDS500 [17], and CVPPP [19]) Cityscapes has a large number of scenes involving dozens of instances with large degrees of occlusions at vastly different scales.”
• Deformable part models are convolutional neural networks (2014, methodology): “We conducted several preliminary experiments on the PASCAL VOC 2007 dataset [8] in order to find a DPM structure suited to conv5 features.”
• Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction (2016, methodology): “Our proposed methods outperform these alternatives, which indicates that (i) our choice of aggregating complementary signals improves performance (ii) concatenation is an appropriate choice of combining cross-channel encoders.”
• Generalized Decoding for Pixel, Image, and Language (2022, methodology): “, ADE20K [98] and Pascal [22]), outdoor (e.”