Learning Collections of Part Models for Object Recognition

By Ian Endres, Kevin J. Shih, Johnston Jiaa, Derek Hoiem. 2013

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

Unsupervised Visual Representation Learning by Context Prediction (2015, background): “mset mining. Finally, a number of works focus on geometry as a method for verifying links between images [5, 36, 19]. Finally, our work is related to a line of research on discriminative patch mining [11, 13, 23, 41, 9], which has emphasized weak supervision as a means of object discovery. Like the ”
Active Object Localization with Deep Reinforcement Learning (2015, methodology): “A popular sliding window method, based on HOG templates and SVM classifiers, has been extensively used to localize objects [11, 21], parts of objects [8, 20], discriminative patches [29, 17] and even salient components of scenes [24].”
On learning to localize objects with minimal supervision (2014, unknown): “Recent literature on unsupervised mid-level visual element discovery (Doersch et al., 2012; Singh et al., 2012; Endres et al., 2013; Juneja et al., 2013; Raptis et al., 2012) uses weak labels to discover visual elements that occur commonly in positive images but not in negative images.”
Finding Matches in a Haystack: A Max-Pooling Strategy for Graph Matching in the Presence of Outliers (2014, background): “Such better verified matches also could lead to more accurate localization of objects [12].”
Mid-level Visual Element Discovery as Discriminative Mode Seeking (2013, methodology): “, scene categories [12] or GPS coordinates [5] (but can also run unsupervised [23]), and have been recently used for tasks including image classification [12, 23, 27], object detection [6], visual data mining [5, 15], action recognition [11], and geometry estimation [7].”
Food-101 - Mining Discriminative Components with Random Forests (2014, methodology): “For classifying an image, we only need to score all of its superpixels using the previously trained component models, instead of applying multi scale sliding window detectors [7,35,38,25,8,19,34,40].”
Adaptive region pooling for object detection (2015, background): “Automatically discovering parts of objects provides a useful mid-level feature representation for numerous vision tasks [5, 31, 12, 23].”
Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals (2015, background): “Recent work on discriminative patch discovery [15, 44, 50] learns mid-level visual representations in a weakly-supervised mode, and use them for object recognition [15, 44] and discovery [13, 50].”
Context as Supervisory Signal: Discovering Objects with Predictable Context (2014, background): “A number of recent works have argued that weak supervision can be an effective way to get more visually meaningful clusters [14,15,16,17,18,19,20,21,22,23].”
Mining Mid-level Features for Image Classification (2014, background): “Based on this observation, some recent works (Boureau et al. 2010; Endres et al. 2013; Juneja et al. 2013; Lee et al. 2013; Sharma et al. 2013; Singh et al. 2012) have looked into the construction of more distinctive, mid-level features (sometimes also referred to as semi-local features or parts).”
Patch to the Future: Unsupervised Visual Prediction (2014, background): “Our work builds upon the recent success of mid-level discriminative patch discovery [4, 5, 6, 16, 28] and proposes a prediction framework based on these mid-level elements.”
Learning coarse-to-fine sparselets for efficient object detection and scene classification (2015, background): “In recent years, since the seminal work of [4, 5] and with the success of deformable part models (DPMs) [6, 7], part model-based methods have demonstrated impressive performance for object detection [6-13] and scene classification [14-21].”
Semantic Image Interpretation - Integration of Numerical Data and Logical Knowledge for Cognitive Vision (2018, unknown): “They leverage the part-whole relation between whole objects and their parts to improve the object detection [17, 32, 35, 38, 32, 70].”
Human Attribute Recognition by Rich Appearance Dictionary (2013, background): “In general, there are two considerations to be made in part learning, a 1More precisely, the poselet approach, after the initial learning stage, filters examples whose appearance is not consistent with the learned detector.”
ConceptMap: Mining Noisy Web Data for Concept Learning (2014, unknown): “[34] [50] [27] [50,9,8,25,10,26,35,7].”
Randomized Max-Margin Compositions for Visual Recognition (2014, background): “Moreover, the individual contributions of compositions and their parts are evaluated in separate experiments that demonstrate their potential.”
Using k-Poselets for Detecting People and Localizing Their Keypoints (2014, methodology): “The precision-recall curves computed for calibration are reused for AMP computation.”
Indoor Scene Understanding with RGB-D Images: Bottom-up Segmentation, Object Detection and Semantic Segmentation (2015, background): “Recently, in the context of intensity images there has been a lot of work in trying to get mid-level parts in an unsupervised manner from weak annotations like that of bounding boxes in intensity images [13], and in a supervised manner from strong annotations like that of keypoint annotation [5].”