Learning Spatial Context: Using Stuff to Find Things

By Geremy Heitz, Daphne Koller. 2008

477 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Automotive Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Artificial Intelligence

In Automotive Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Microsoft COCO: Common Objects in Context (2014, background): “Other important decisions are whether to include both “thing” and “stuff” categories [39] and whether fine-grained [31,1] and object-part categories should be included.”
COCO-Stuff: Thing and Stuff Classes in Context (2016, background): “Moreover, several works have shown that stuff is a useful contextual cue to detect things and vice versa [41, 27, 31, 38, 45].”
Object-Proposal Evaluation Protocol is ‘Gameable’ (2015, neutral): ““stuff” discussion, see [41].”
Scene Parsing through ADE20K Dataset (2017, background): “For example, MRF frameworks are proposed to parse images in different levels [30] or segment rare object classes [33]; detection is combined with segmentation to improve the performance [31]; stuff classes are leveraged to localize objects [13].”
Cross-Stitch Networks for Multi-task Learning (2016, methodology): “In particular, we select four well established and diverse tasks on different types of image datasets: 1) We pair semantic segmentation [27, 45, 46] and surface normal estimation [11, 18, 52], both of which require predictions over all pixels, on the NYU-v2 indoor dataset [47].”
Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation (2015, methodology): “A more detailed discussion of the value of spatial context can be found in [21].”
An empirical study of context in object detection (2009, background): “Several recent computer vision approaches have demonstrated that the use of context improves recognition performance [4, 11, 14, 17, 24, 26, 32, 35, 39, 41].”
Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation (2021, background): “The difference between objects and stuff has been discussed previously [18, 2, 4].”
Modeling Visual Context is Key to Augmenting Object Detection Datasets (2018, methodology): “Before the deep learning/ImageNet revolution, the previous generation of object detectors such as [3,4,5,6] modeled the interaction between object locations, categories, and context by manual engineering of local descriptors, feature aggregation methods, and by defining structural relationship betwe”
Fast PRISM: Branch and Bound Hough Transform for Object Class Detection (2011, background): “, things and not stuff (Heitz and Koller 2008) and we are not interested in reconstructing the image.”
Multi-spectral SIFT for scene category recognition (2011, methodology): “We extensively test our algorithms using a new dataset of several hundred RGB-NIR scene images, as well as benchmarking against Torralba’s scene categorization dataset.”
Synthetic Data for Deep Learning (2019, background): “, things in the terminology of [241]) are well”
Semantic Labeling of 3D Point Clouds for Indoor Scenes (2011, background): “A number of works propose models that explicitly capture the relations between different parts of the object e.g., Pedro et al.’s part-based models [6], and between different objects in 2D images [13, 14].”
Object localization in ImageNet by looking out of the window (2015, methodology): “This is related to previous work on context [7, 10, 17, 18, 25, 26, 30] as well as to works that use structured output regression formulation [6, 19, 20, 33].”
Beyond Actions: Discriminative Models for Contextual Group Activities (2010, unknown): “In that work, person-person context is exploited by a new feature descriptor extracted from a person and its surrounding area.”
What, Where and How Many? Combining Object Detectors and CRFs (2010, methodology): “The distinction between these two sets of classes — referred to as things and stuff respectively — is well known [10,11,12].”
What is an object? (2010, background): “Objects are standalone things with a welldefined boundary and center, such as cows, cars, and telephones, as opposed to amorphous background stuff, such as sky, grass, and road (as in the ‘things vs. stuff’ distinction of [16]).”