Object Bank: A High-Level Image Representation for Scene Classification & Semantic Feature Sparsification

By Li-Jia Li, Hao Su, Eric P. Xing, Li Fei-Fei. 2010

1,082 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition (2013, methodology): “Our work is also related to representation learning schemes in computer vision which form an intermediate representation based on learning classiﬁers on related tasks (Li et al., 2010; Torresani et al., 2010; Quat-toni et al., 2008).”
What makes Paris look like Paris? (2012, neutral): “However, such systems require signiﬁcant manual e ↵ ort from an expert to specify the appropriate elements and rules for each architectural style.”
Interpretability Beyond Classification Output: Semantic Bottleneck Networks (2019, background): “The idea of basing classification on a predetermined interpretable basis is related to Object Bank introduced in 2010 [15].”
Jointly Modeling Deep Video and Compositional Text to Bridge Vision and Language in a Unified Framework (2015, methodology): “We apply the state-of-the-art motion descriptor, i.e. dense trajectory (Wang et al. 2011) and object descriptor , i.e. ObjectBank (Li et al. 2011) as visual features.”
From generic to specific deep representations for visual recognition (2014, background): “The concept of learning from related tasks using neural networks and ConvNets has appeared earlier in the literature see [28, 3, 14, 21] for a few examples.”
Watch and learn: Semi-supervised learning of object detectors from videos (2015, methodology): “For each labeled bounding box in Li, we compute a detection signature [24, 38, 54] using our exemplar detectors.”
Hierarchical Deep Temporal Models for Group Activity Recognition (2016, methodology): “HOG3D [18], spatio-temporal features [5], object interaction feature [19], and social role features [20] are used as unary component representations.”
Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs (2019, methodology): “Our method is inspired by recent work in computer vision that uses the information “banks” [1, 45, 76].”
Inferring the Why in Images (2014, methodology): “In order to give the vision-only baseline access to other visual concepts, we concatenate its features with a ground truth object bank [22].”
WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation (2017, positive): “We use a multi-scale setup where a different model is learned for each scale and they are combined with Object Bank [38] strategy.”
Learning hierarchical sparse features for RGB-(D) object recognition (2014, background): “…Torralba, 2009), Spatial Pyramid Matching (SPM) (Pandey and Lazebnik, 2011), Deformable Parts Models (DPM) (Felzenszwalb et al., 2010), Object Bank (Li et al., 2010), Reconﬁgurable Models (RBoW) (Parizi et al., 2012), and even the combination of SPM, DPM, and color GIST (Pandey and Lazebnik, 2011).”
Large-scale web video event classification by use of Fisher Vectors (2013, background): “Object Bank[9], for example, uses a list of more than 170 object concepts.”
Meta-class features for large-scale object categorization on a budget (2012, methodology): “of image descriptors encoding categorical information as features: the image is represented in terms of its relation to a set of basis object classes [33, 29, 7] or as the response map to a set of detectors [19].”