Sharing features between objects and their attributes

By Sung Ju Hwang, Fei Sha, Kristen Grauman. 2011

125 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology

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

In Media Technology

Citations in the corpus

Transductive Multi-View Zero-Shot Learning (2015, background): “X S ∈ R n s × t and X T ∈ R n T × t denote the t − dimensional low-level feature vectors of auxiliary and target instances respectively. z S and z T are the auxiliary and target class label vectors.”
An embarrassingly simple approach to zero-shot learning (2015, background): “Many efforts have been made to improve the training stage [10, 15, 17], whereas the inference stage has received little attention [16].”
Multi-Task CNN Model for Attribute Prediction (2015, background): “If tasks are related and especially when one task lacks training data, it may receive visual knowledge from other, more fit tasks [1], [4], [19], [23], [31].”
Learning multiple visual tasks while discovering their structure (2015, methodology): “Empirical tests show that the proposed method compares favorably to state of the art techniques and further allows to recover interpretable structures, a problem of interest in its own right.”
Learning Attributes Equals Multi-Source Domain Generalization (2016, background): “Earlier work on attribute detection mainly focused on modeling the correlations among attributes [9, 32, 35, 8, 10, 12, 75, 31], localizing some special part-related attributes (e.”
Human Uncertainty Makes Classification More Robust (2019, background): “, sharing of representations [47, 9, 22], effective combination of models [23], or improved accuracy of classification through hierarchical prediction [32, 8].”
A Unified Probabilistic Approach Modeling Relationships between Attributes and Objects (2013, background): “Attributes are widely used in many different applications like object describing [6], zero-shot learning [17, 11], face verification [15], object recognition [34, 10], person and clothing describing [1, 2], image search and retrieval [16, 13, 36], and action/activity recognition [19, 35, 9] etc.”
Multi-Task Learning with Low Rank Attribute Embedding for Person Re-Identification (2015, background): “[19] consider attribute classifiers as auxiliary tasks to object classifiers and adopt MTL to learn a shared structure for better classification and attribute prediction.”
Semantic Kernel Forests from Multiple Taxonomies (2012, unknown): “, [27, 28, 29]).”
Discovering localized attributes for fine-grained recognition (2012, background): “Recent work has introduced visual attributes as intermediate-level features that are both machine-detectable and semantically meaningful (e.g. [2, 3, 6, 9, 11, 14, 28]).”
Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation (2014, background): “Most existing studies [18, 17, 25, 26, 30, 37, 1] assume that an exhaustive ontology of attributes has been manually specified at either the class or instance level.”
Large-Scale Object Classification Using Label Relation Graphs (2014, methodology): “In particular, label hierarchies have been used to share representations [15,2,8,17] and combine models [18,38,27].”
Multi-Task Learning with Low Rank Attribute Embedding for Multi-Camera Person Re-Identification (2018, methodology): “Both [59] and [60] assume attributes to be related tasks.”
Person Re-identification by Attributes (2012, background): “raw data for greater effectiveness [8, 13]; and finally they are a suitable representation for direct human interaction, therefore allowing searches to be specified or constrained by attributes [11, 12, 21].”
Learning with Whom to Share in Multi-task Feature Learning (2011, background): “Thus, its applicability to learning tasks with different characteristics, for example, classifying object categories versus detecting visual attributes, needs to be studied (Hwang et al., 2011).”
Learning semantic relationships for better action retrieval in images (2015, background): “Semantic hierarchy for vision In the last few years, different works [1, 7, 8, 9, 11, 16, 24, 26, 37, 44, 47] have tried to use preexisting structure between labels to train better models for image classification, and object segmentation [20].”