Describing objects by their attributes

By Ali Farhadi, Ian Endres, Derek Hoiem, D.A. Forsyth. 2009

2,167 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Microsoft COCO: Common Objects in Context (2014, methodology): “Finally, our dataset could provide a good benchmark for other types of labels, including scene types [3], attributes [9], [8] and full sentence written descriptions [51].”
Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions (2015, background): “In [6], the training set attributes are predicted along with the image label at test time.”
Zero-Shot Learning Through Cross-Modal Transfer (2013, background): “[21, 10] were two of the first to use well-designed visual attributes of unseen classes to classify them.”
Generative Adversarial Text to Image Synthesis (2016, background): “Traditionally this type of detailed visual information about an object has been captured in attribute representations distinguishing characteristics the object category encoded into a vector (Farhadi et al., 2009; Kumar et al., 2009; Parikh & Grauman, 2011; Lampert et al., 2014), in particular to en”
Describing Textures in the Wild (2013, background): “Recently visual attributes have raised signiﬁcant interest in the community [6, 11, 17, 25].”
Joint Discovery of Object States and Manipulation Actions (2017, background): “Prior work has addressed recognition of object attributes [15, 33, 34], which can be seen as different object states in some cases.”
ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models (2022, neutral): “, Animal with Attributes (AwA) [31], Caltech-UCSD Birds-200 (CUB) [64], SUN [47], aPY [14], and ZS-ImageNet [52, 17].”
Deep Learning Face Attributes in the Wild (2014, background): “Extracting hand-crafted features at pre-defined landmarks has become a standard step in attribute recognition [9, 15, 4, 2].”
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition (2014, background): “The first dataset is the UIUC 64 object attributes dataset [13].”
Cross-Stitch Networks for Multi-task Learning (2016, methodology): “For this experiment, we use the attribute PASCAL dataset [12, 16].”
A Joint Model of Language and Perception for Grounded Attribute Learning (2012, background): “attributes provide rich descriptions of objects, and have become a popular topic in the vision community (Farhadi et al., 2009; Parikh & Grauman, 2011); although very successful, we still lack a deep understanding of the design rules underlying them and how they measure similarity.”
The More You Know: Using Knowledge Graphs for Image Classification (2016, background): “Our work is also related to attribute approaches [8] to vision such as [16] which uses a fixed set of binary attributes to do zero-shot prediction, [34] which uses attributes shared across categories to prevent semantic drift in semi-supervised learning and [5] which automatically discovers attribut”
Transductive Multi-View Zero-Shot Learning (2015, background): “Different from the multi-view hypergraphs proposed in [19] which are homogeneous, that is, constructed in each view independently, we construct a multi-view heterogeneous hypergraph: using the nodes from one view as query nodes to compute hyperedges in another view.”
Rectification-based Knowledge Retention for Continual Learning (2021, background): “Attribute Pascal and Yahoo (aPY) [6], Animals with Attributes 1 (AWA1) [31], Caltech-UCSD-Birds 200-2011 (CUB) [29], and SUN Attribute dataset (SUN) [19].”
Learning to Reconstruct Shapes from Unseen Classes (2018, background): “A number of earlier papers have explored sharing features across categories to recognize new objects from a few examples [Bart and Ullman, 2005, Farhadi et al., 2009, Lampert et al., 2009, Torralba et al., 2007].”
Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly (2017, methodology): “TABLE 1 Statistics for SUN [16], CUB [17], AWA1 [1], Proposed AWA2, aPY [18] in Terms of Size, Granularity, Number of Attributes, Number of Classes in Ytr and Yts, Number of Images at Training and Test Time for Standard Split (SS) and Our Proposed Splits (PS)”
Video In Sentences Out (2012, background): “There has also been work on generating sentential descriptions of static images (Farhadi et al., 2009; Kulkarni et al., 2011; Yao et al., 2010).”