From Large Scale Image Categorization to Entry-Level Categories

By Vicente Ordonez, Jia Deng, Yejin Choi, Alexander C. Berg, Tamara L. Berg. 2013

117 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

ImageNet Large Scale Visual Recognition Challenge (2014, methodology): “Best paper awards at top vision conferences in 2013 were awarded to large-scale recognition methods: at CVPR 2013 to ”Fast, Accurate Detection of 100,000 Object Classes on a Single Machine” (Dean et al., 2013) and at ICCV 2013 to ”From Large Scale Image Cate-gorization to Entry-Level Categories” (Or”
Microsoft COCO: Common Objects in Context (2014, methodology): “Unlike previous datasets containing entry-level categories [29], such as “dog” or “chair,” like [28], ImageNet used the WordNet Hierarchy [30] to obtain both entry-level and ﬁne-grained [31] categories.”
ReferItGame: Referring to Objects in Photographs of Natural Scenes (2014, background): “The entry-level category attribute is related to the concept of entry-level categories first proposed by Psychologists in the 1970s (Rosch, 1978) and recently explored in visual recognition (Ordonez et al., 2013).”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, background): “More generally, dealing with novel images remains difficult, though experiments have been performed on using outof-domain training data to expand vocabulary (Ordonez et al., 2013), learn novel concepts (Mao et al.”
Déjà Image-Captions: A Corpus of Expressive Descriptions in Repetition (2015, background): “The idea is to prefer a caption for which the query image is likely to be a prototypical visual rendering (Ordonez et al., 2013; Deselaers and Ferrari, 2011), hence avoid an unusual association between the text and the visual information.”
Nonparametric Method for Data-driven Image Captioning (2014, background): “, 2012) and more recently, the best paper award winner at ICCV (Ordonez et al., 2013).”
Open Vocabulary Scene Parsing (2017, background): “[21], on the other hand, proposed to make entry-level predictions when dealing with a large number of categories.”
Open-vocabulary Object Retrieval (2014, methodology): “Therefore, our score function is based on comparing the given text query q with m different representations of an image in a weighted open-vocabulary text space.”
From categories to subcategories: Large-scale image classification with partial class label refinement (2015, unknown): “We present this improvement in Section 3.”
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].”
Network of Experts for Large-Scale Image Categorization (2016, background): “Hierarchies of classes have also been used to infer class abstraction [19], to trade off concept specificity versus accuracy [8, 31], to allow rare objects to borrow statistical strength from related but more frequent objects [32, 36], and also for unsupervised discovery of objects [34].”
Deep Classifiers from Image Tags in the Wild (2015, background): “Frequently-omitted tags are often nonentry-level categories [21] (e.”
Learning Everything about Anything: Webly-Supervised Visual Concept Learning (2014, background): “Such an exhaustive vocabulary helps in generating fine-grained descriptions of images [17, 29, 34, 40, 50].”
Dynamic-Structured Semantic Propagation Network (2018, background): “[30] learns the mapping of common concepts to entry-level concepts.”