Object Detection with Grammar Models

By Ross B. Girshick, Pedro F. Felzenszwalb, David A. McAllester. 2011

309 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

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation (2013, background): “This hypothesis is grounded, for example, in the wide range of papers that attempt to boost detection accuracy with work along four axes: (1) rich structured models [20, 42]; (2) multiple feature learning [38, 41]; (3) learned histogram-based features [11, 29, 32]; or (4) unsupervised feature learni”
Deformable part models are convolutional neural networks (2014, background): “However, the construction is general and naturally extends to a variety of models such as object detection grammars [16] and recent DPM variants, such as [34].”
Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts (2014, background): “[13] propose a grammar model to handle a variable number of parts.”
Bottom-Up Object Detection by Grouping Extreme and Center Points (2019, background): “In addition, top-down object detectors enumerate a large number of possible box locations without truly understanding the compositional visual grammars [9,13] of objects themselves.”
Robobarista: Object Part Based Transfer of Manipulation Trajectories from Crowd-Sourcing in 3D Pointclouds (2015, methodology): “Thus, rather than relying on scene understanding techniques [7, 31, 15], we”
The Role of Context for Object Detection and Semantic Segmentation in the Wild (2014, methodology): “For initialization, we first train a mixture, root-only model as in [15], without context.”
Bi-box Regression for Pedestrian Detection and Occlusion Estimation (2018, methodology): “A deformable part model [13] and its variants [15, 2, 42] can also be used for handling occlusions.”
Histograms of Sparse Codes for Object Detection (2013, background): “Most approaches have explored model structure, either through non-parametric mixtures or exemplars [21, 10], compositional grammar structure [15], supervised correspondences [5, 2], and low-dimensional projections [29, 25].”
Are Cars Just 3D Boxes? Jointly Estimating the 3D Shape of Multiple Objects (2014, background): “on the level of HOG [8] cells [35, 33, 14], object parts [17, 28, 40], or silhouettes [21].”
Efficient Structured Prediction with Latent Variables for General Graphical Models (2012, background): “Girshick et al. (2011) proposed to introduce a second loss function into the ‘latent variable prediction problem’ while Tarlow & Zemel (2012) investigate the impact of higher order loss functions.”
Analyzing 3D Objects in Cluttered Images (2012, background): “While deformable models and pictorial structures [10] [31] [11] are known to successfully model articulation , 3D viewpoint is still not well understood.”
Augmenting deformable part models with irregular-shaped object patches (2012, methodology): “[9] have proposed a method based on object grammars to allow more flexibility in describing objects.”
Parsing occluded people by flexible compositions (2014, background): “In order to handle people with different degrees of occlusion, we specify a binary occlusion decoupling variable γij ∈ {0, 1} for each edge (i, j) ∈ E , which enables the subtree Tj = (V(Tj), E(Tj)) rooted at part j to be decoupled from the graph at part i (the subtree does not contain part i,…”
Object Detection in 20 Years: A Survey (2019, unknown): “Later on, Girshick [14], [15], [33], [34] has further extended the star model to the “mixture models” to deal with the objects in the real world under more significant variations and has made a series of other improvements.”
Single-Pedestrian Detection Aided by Multi-pedestrian Detection (2013, methodology): “1) Classification approaches used include various boosting classifiers [32, 9, 37], SVM classifiers [4, 21, 13, 43], and grammar models [16] and deep model [23].”
Towards Unified Object Detection and Semantic Segmentation (2014, unknown): “(9) is linear in the model parameter w, thus this model can be effectively learned based on the latent structure SVM framework [41,22]:”
Discriminatively Activated Sparselets (2013, background): “These representations appear under a variety of guises, such as steerable ﬁlter banks (Freeman & Adelson, 1991), low-rank approximations for collaborative ﬁltering (Sarwar et al., 2000), and shared part models for object detection (Zhu et al., 2010; Ott & Everingham, 2011; Girshick et al., 2011).”