Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

By Aude Oliva, Antonio Torralba. 2001

7,162 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Representation & Self-Supervised Learning

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

In Media Technology

In Representation & Self-Supervised Learning

Citations in the corpus

ImageNet Large Scale Visual Recognition Challenge (2014, methodology): “sets in WordNet (Miller, 1995) as queries. However, since this data has not been manually veried, there are many errors, making it less suitable for algorithm evaluation. Datasets such as 15 Scenes (Oliva and Torralba, 2001; Fei-Fei and Perona, 2005; Lazebnik et al., 2006) or recent Places (Zhou et ”
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation (2013, methodology): “The second check uses GIST descriptor [31] matching, which was shown in [13] to have excellent performance at near-duplicate image detection in large (> 1 million) image collections.”
Group Normalization (2018, methodology): “Classical features of SIFT [39], HOG [9], and GIST [41] are group-wise representations by design, where each group of channels is constructed by some kind of histogram.”
Remote Sensing Image Scene Classification: Benchmark and State of the Art (2017, methodology): “Here, we briefly review several most representative handcrafted features, including color histograms [99], texture descriptors [104-106], GIST [107], scale invariant feature transform (SIFT) [108], and histogram of oriented gradients (HOG) [109].”
The Cityscapes Dataset for Semantic Urban Scene Understanding (2016, background): “Scene recognition aims to determine the overall scene category by putting emphasis on understanding its global properties, e.g. [46, 82].”
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition (2013, methodology): “In particular, we compare the features described in Section 3 with GIST features (Oliva & Torralba, 2001) and LLC features (Wang et al., 2010).”
SUN database: Large-scale scene recognition from abbey to zoo (2010, methodology): “How many kinds of scenes are there? How can the knowledge about environmental scenes be organized? How do the current state-of-art scene models perform on more realistic and ill-controlled environments, and how does this compare to human performance? To date, computational work on scene and place re”
Deep Learning Face Attributes in the Wild (2014, methodology): “Attribute Inference by Hand-crafted Features Extracting hand-crafted features, such as HOG [3], LBP [17], and GIST [18], at pre-defined landmarks is a standard step in attribute recognition.”
HMDB: A large video database for human motion recognition (2011, background): “…catch, draw sword, dribble, golf, hit something, kick ball, pick, pour, push something, ride bike, ride horse, shoot ball, shoot bow, shoot gun, swing baseball bat, sword exercise, throw; 5) Body movements for human interaction: fencing, hug, kick someone, kiss, punch, shake hands, sword fight.”
A Multi-View Embedding Space for Modeling Internet Images, Tags, and Their Semantics (2012, methodology): “For GIST features, we use the random Fourier feature mapping (Rahimi and Recht, 2007) that approximates the Gaussian kernel.”
LabelMe: A Database and Web-Based Tool for Image Annotation (2008, methodology): “For the experiments presented here, we used the Gist features (Oliva and Torralba 2001) (code available online) to represent each region.”
Generative Image Modeling Using Style and Structure Adversarial Networks (2016, positive): “We compare our method with the discriminator network in DCGAN and the baselines reported in [61]: GIST [64] feature as well as Places-AlexNet [58].”
Comparing Automatic Evaluation Measures for Image Description (2014, neutral): “, 2006), or rapidly-obtained scene properties (Oliva and Torralba, 2001).”
Recognizing Image Style (2013, background): “The classic gist descriptor [23] is known to perform well for scene classification and retrieval of images visually similar at a low-resolution scale, and thus can represent image composition to some extent.”
Transductive Multi-View Zero-Shot Learning (2015, methodology): “For multi-label zero-shot learning on Natural Scene, we use a multi-class single label dataset – Scene dataset [24] (totally 2688 images) as the auxiliary dataset which have been labelled with a non-overlapping set of labels such as street, coast and highway.”