Material perception: What can you see in a brief glance?

By Lavanya Sharan, Ruth Rosenholtz, Edward H. Adelson. 2010

335 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Neuroscience, Cognitive Science & Psychology

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

In Neuroscience

In Cognitive Science & Psychology

Citations in the corpus

COCO-Stuff: Thing and Stuff Classes in Context (2016, neutral): “A related task is material recognition [44, 4, 5].”
Material recognition in the wild with the Materials in Context Database (2014, methodology): “To date, progress in material recognition has been facilitated by moderate-sized datasets like the Flickr Material Database (FMD) [26].”
Bilinear CNN Models for Fine-Grained Visual Recognition (2015, methodology): “8 shows some example inverse images for various categories for the DTD, FMD and MIT indoor datasets using B-CNN.”
DualGAN: Unsupervised Dual Learning for Image-to-Image Translation (2017, methodology): “These images were manually selected from Flickr and cover a variety of illumination conditions, compositions, color, texture, and material sub-types [17].”
Tree Species Identification from Bark Images Using Convolutional Neural Networks (2018, methodology): “segmentation algorithms, [23] used an SVM to classify texture materials, notably on the Flickr Material Dataset [24].”
From BoW to CNN: Two Decades of Texture Representation for Texture Classification (2018, methodology): “The Flickr Material Database (FMD) [206, 207] was built to address some of these limitations, by collecting many different object instances from the Internet grouped in 10 different material categories, with examples shown in Fig.”
Toward a Quantitative Survey of Dimension Reduction Techniques (2019, neutral): “Bank Marketing (bank) [33]: Direct marketing campaign data of a Portuguese bank used to predict whether a client will subscribe to a banking product or not; CIFAR10 (cifar10) [34]: Standard Computer Vision research dataset consisting of images of animals and vehicles, used for training image classfi”
Bilinear CNNs for Fine-grained Visual Recognition (2015, methodology): “We experiment on three texture datasets – the Describable Texture Dataset (DTD) [10], Flickr Material Dataset (FMD) [56], and KTH-TISP2-b (KTH-T2b) [7].”
Deep convolutional filter banks for texture recognition and segmentation (2014, background): “Perhaps the most studied task in texture understanding is the one of material recognition, as captured in benchmarks such as CuRET [8], KTH-TIPS [5], and, more recently, FMD [36].”
Recognizing Materials Using Perceptually Inspired Features (2013, methodology): “Details of these studies can be found elsewhere (Sharan et al. 2009).”
Visualizing and Understanding Deep Texture Representations (2015, methodology): “Using the Flickr Material Dataset (FMD) [34], Describable Texture Dataset (DTD) [3] and KTH-T2b [1] we show that it performs favorably to Fisher vector CNN model [4], which is the current state of the art.”
Crowdsourcing in Computer Vision (2016, positive): “, 2015] uses a three-stage Mechanical Turk pipeline to annotate three million material samples, significantly scaling up over the previous Flickr Material Dataset [Sharan et al., 2009] benchmark.”
Rigid-Motion Scattering for Texture Classification (2014, background): “State of the art results on four texture datasets containing different types and ranges of variability (KTH TIPS, 2004; UIUC Tex, 2005; UMD, 2009; FMD, 2009).”
Loss Functions for Top-k Error: Analysis and Insights (2015, neutral): “For CUB, Flowers, FMD, and ILSVRC 2012, we use MatConvNet [56] to extract the outputs of the last fully connected layer of the imagenet-vgg-verydeep-16 model which is pre-trained on ImageNet [16] and achieves state-of-the-art results in image classification [50].”