Hierarchical semantic indexing for large scale image retrieval

By Jia Deng, Alexander C. Berg, Li Fei-Fei. 2011

268 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Retrieval & Search

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 Information Retrieval & Search

Citations in the corpus

VQA: Visual Question Answering (2015, methodology): “Related to VQA are the tasks of image tagging [8, 23], image captioning [24, 14, 34, 7, 13, 45, 9, 19, 32, 21] and video captioning [39, 17], where words or sentences are generated to describe visual content.”
A Survey on Metric Learning for Feature Vectors and Structured Data (2013, methodology): “The bilinear similarity has been used for instance in image retrieval (Deng et al., 2011) and has the following simple form: KM (x,x ) = xMx, where M ∈ Rd×d is not required to be PSD nor symmetric.”
Large Scale Visual Recognition (2012, background): “For instance given semantic attributes like containing a horse, dog, or windmill, a predefined hierarchy might let us know that an image containing a horse would be more similar to one contain1An early version of this chapter has been presented in [54].”
HydraNets: Specialized Dynamic Architectures for Efficient Inference (2018, methodology): “The hyper parameters k, nb and the point to branch were chosen empirically by searching over nb = [5, 10, 20, 25], k = [3, 4, 5] and branching at block 2 or block 3.”
Feature selection in machine learning: A new perspective (2018, background): “large samples and high dimensionality have appeared in various data mining fields, such as text mining and information retrieval [143, 144].”
Street-to-shop: Cross-scenario clothing retrieval via parts alignment and auxiliary set (2012, methodology): “Note that the evaluation method of [8] will results in different trends of the Precision @ k vs k curve regards different task difﬁculty.”
50 Years of object recognition: Directions forward (2013, background): “[185, 186], present an algorithm for learning hierarchical relations of semantic attributes from labelled images.”
DeepStore: In-Storage Acceleration for Intelligent Queries (2019, background): “Exploiting Query Properties: Conventional query systems leverage similarity between their data to build indices for fast lookups [20, 37, 58, 59, 85].”
A hierarchical loss and its problems when classifying non-hierarchically (2017, background): “The particular special cases discussed by them and by [4–9] allocate different weights to different leaves, not leveraging “ultrametric trees” as in the present paper (an ultrametric tree is a tree with a so-called ultrametric distance metric such that all leaves are at the same distance from the ro”
Meta-class features for large-scale object categorization on a budget (2012, background): “of image descriptors encoding categorical information as features: the image is represented in terms of its relation to a set of basis object classes [33, 29, 7] or as the response map to a set of detectors [19].”
Learning to place new objects in a scene (2012, methodology): “Our goal in this paper is to develop an algorithm for estimating good placements given the pointclouds of the objects and the scene as input.”
Deep learning of binary hash codes for fast image retrieval (2015, methodology): “We use a ranking based criterion [4] for evaluation.”
Contextualizing Object Detection and Classification (2015, background): “Context modeling with hundreds or thousands of object categories seeks to model this relationship with high level semantic structure or learned from data [11].”
Multi-class Open Set Recognition Using Probability of Inclusion (2014, methodology): “For multi-class recognition problems in computer vision, posterior probabilities are widely used to make decisions in applications such as pedestrian classification and orientation estimation [18], image retrieval [15], attribute fusion [42], part-based human tracking [47], large-scale multi-class o”
Example-based synthesis of 3D object arrangements (2012, background): “In contrast, researchers in computer vision have shown that hierarchical categories can improve performance on challenging tasks such as content-based image retrieval [Deng et al. 2011].”