Weakly Supervised Learning of Part-Based Spatial Models for Visual Object Recognition

By David J. Crandall, Dan Huttenlocher. 2006

207 citations recorded by the source corpus.

Subfields: Aerospace 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Webly Supervised Learning of Convolutional Networks (2015, methodology): “The outline of our approach is shown in Figure 2.”
Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts (2014, neutral): “In contrast to object detectors encoding parts using latent variables [5, 27, 11, 6, 9, 21, 17], we use semantic body parts.”
Scene recognition and weakly supervised object localization with deformable part-based models (2011, methodology): “Most existing weakly supervised localization techniques have been applied to relatively simple datasets such as Caltech04 [1, 3, 13, 15, 21] or Weizmann horses [20], or one or two PASCAL-VOC categories [20, 21].”
Object-Centric Spatial Pooling for Image Classification (2012, background): “Methods such as [1–7] attempt to localize objects to improve image classification accuracy but only demonstrate results on simple datasets such as subsets of Caltech101 classes.”
Weakly Supervised Object Localization and Detection: A Survey (2021, unknown): “Some early methods, such as [23], [41], learn to localize category-wise key points under the weak supervision, while this survey mainly focuses on the methods for localizing instances with bounding-boxes.”
Multi-fold MIL Training for Weakly Supervised Object Localization (2014, unknown): “[2, 8, 10, 11, 20, 22, 23, 25, 27, 29].”
On learning to localize objects with minimal supervision (2014, unknown): “Early efforts, such as (Weber et al., 2000a;b; Galleguillos et al., 2008; Fergus et al., 2007; Crandall & Huttenlocher, 2006; Chum & Zisserman, 2007; Chen et al., 2013), focused on datasets with strong object-in-the-center biases (e.g. Caltech-101).”
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-Supervised Object and Action Localization (2017, methodology): “Weakly-supervised approaches have been proposed for various visual classification and localization tasks including object detection [55, 13, 9, 41, 3, 50, 43, 8, 32, 61, 40], semantic segmentation [33, 26] and visual attribute localization [2, 53, 57, 52, 39].”
Weakly supervised object detector learning with model drift detection (2011, background): “Early works on applying MIL for solving vision problems have been focused on image categorisation [11, 5, 12, 13].”
A discriminatively trained, multiscale, deformable part model (2008, unknown): “In contrast to computationally demanding approaches such as [4], we can learn a model in 3 hours on a single CPU.”
Learning object class detectors from weakly annotated video (2012, background): “These methods typically try to approximately localize object instances while learning a model of the class [3, 6, 10, 9, 13, 16, 23, 37, 29].”
Weakly Supervised Localization and Learning with Generic Knowledge (2012, unknown): “However, most methods have been demonstrated on datasets such as CALTECH4 (Arora et al. 2007; Crandall and Huttenlocher 2006; Fergus et al. 2003; Galleguillos et al. 2008; Lee and Grauman 2009a; Nguyen et al. 2009; Winn and Jojic 2005a), Weizmann horses (Borenstein and Ullman 2004; Cao and Li 2007; ”
Closed-Loop Learning of Visual Control Policies (2011, unknown): “Crandall and Huttenlocher (2006) provide pointers to recent resources.”
Visual and Semantic Knowledge Transfer for Large Scale Semi-Supervised Object Detection (2016, unknown): “bounding box annotations [17], [18], [19], [20], [21], [22],”
Is object localization for free? - Weakly-supervised learning with convolutional neural networks (2015, unknown): “Initial work [2, 8, 11, 20, 57] on weakly supervised object localization has focused on learning from images containing prominent and centered objects in scenes with limited background clutter.”
Bayesian Joint Modelling for Object Localisation in Weakly Labelled Images (2015, background): “Weakly supervised object localisation is of particular interest [4], [11], [12], [13], [15], [15], [20], [21], [22], [23], due to the onerous demands of annotating object location information.”