Visual learning and recognition of 3-d objects from appearance

By Hiroshi Murase, Shree K. Nayar. 2005

1,508 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, 3D Vision & Pose

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

In 3D Vision & Pose

Citations in the corpus

Multi-view Convolutional Neural Networks for 3D Shape Recognition (2015, methodology): “An early example of a view-based approach is the work by Murase and Nayar [24] that recognizes objects by matching their appearance in parametric eigenspaces formed by large sets of 2D renderings of 3D models under varying poses and illuminations.”
Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation (2018, neutral): “Multi-View Representation Our work connects to multi-view representations which capture the characteristics of a 3D object from multiple viewpoints in 2D [17, 26, 42, 32, 12, 39, 34], such as decomposing image silhouettes [23? ], Light Field Descriptors [2], and 2D panoramic mapping [38].”
Lifting Object Detection Datasets into 3D (2015, background): “which reasoned jointly about object identity and 3D geometry [12], [13], [14], was permanently upstaged in the 1990’s by a flurry of view-based approaches [15], [16].”
Deep visual foresight for planning robot motion (2016, methodology): “Learning and optimization-based methods have been applied to various parts of the state-estimation problem, such as object recognition [11], pose registration [12], and dynamics learning [13].”
Sharing Visual Features for Multiclass and Multiview Object Detection (2007, background): “There has been work on training a single multiclass classifier to distinguish between different classes of object, but this typically assumes that the object has been separated from the background (see e.g., [25], [22]).”
Principal Component Analysis (2003, neutral): “All 4 groups of raw duck meat samples and 4 groups of cooked duck meat samples were vacuumed and stored in a - 40℃ refrigerator for testing.”
Context-based vision system for place and object recognition (2003, background): “Another difference between our approach to object recognition and previous approaches is that we try to recognize a large set of object types (24) in a natural, unconstrained setting (images are collected by a wearable camera), as opposed to recognizing a small number of classes (such as faces and c”
Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes (2003, neutral): “[6, 5]).”
View-Invariant Recognition Using Corresponding Object Fragments (2004, methodology): “Note that the scheme uses only multiple-template representation for object parts, not for entire objects as was used by previous multiple template algorithms [5, 12 ,13].”
Incremental Learning for Visual Tracking (2004, background): “Note also that the view-based eigenspace representation has demonstrated its ability to model appearance of objects at different pose [13], and under different lighting conditions [2].”
Sharing features: efficient boosting procedures for multiclass object detection (2004, background): “In addition, it is possible to recognize many classes of objects, generalizing over intra-class variation , but only when the objects are presented against simple backgrounds [14] [15] [10] [4] [13].”
A Framework for Robust Subspace Learning (2003, positive): “Learned PCA representations have proven useful for solving problems such as face and object recognition, tracking, detection, and background modeling (Black and Jepson, 1998; Cootes et al., 1998; Moghaddam and Pentland, 1997; Murase and Nayar, 1995; Oliver et al., 1999).”
Pictorial Structures for Object Recognition (2004, methodology): “These include both appearance-based methods (e.g., [40] and [ 30 ]) and templatebasedmethodssuchasHausdorfimatching[22].”
Video-based face recognition using probabilistic appearance manifolds (2003, methodology): “Our work bears some resemblance to their method in the sense that both methods utilize local linear models, something advocated in several prior works [3, 1, 19], and both learn the relationships among these models [13, 20, 21, 25].”
Spectral Regression for Efficient Regularized Subspace Learning (2007, neutral): “One of the most successful and well-studied techniques to face recognition is the appearance-based method [15, 22].”
Learning a Spatially Smooth Subspace for Face Recognition (2007, neutral): “One of the most successful and well-studied techniques to face recognition is the appearance-based method [20, 24].”