Object and scene recognition in tiny images
Reads0
Chats0
About:
This article is published in Journal of Vision.The article was published on 2010-03-18 and is currently open access. It has received 14 citations till now. The article focuses on the topics: 3D single-object recognition & Object (computer science).read more
Citations
More filters
Journal ArticleDOI
80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition
TL;DR: For certain classes that are particularly prevalent in the dataset, such as people, this work is able to demonstrate a recognition performance comparable to class-specific Viola-Jones style detectors.
80 million tiny images : a large dataset for non-parametric object and scene recognition
TL;DR: In this paper, a large dataset of 79,302,017 images collected from the Internet is used to explore the visual world with the aid of a variety of non-parametric methods.
Proceedings ArticleDOI
IM2GPS: estimating geographic information from a single image
James Hays,Alexei A. Efros +1 more
TL;DR: This paper proposes a simple algorithm for estimating a distribution over geographic locations from a single image using a purely data-driven scene matching approach and shows that geolocation estimates can provide the basis for numerous other image understanding tasks such as population density estimation, land cover estimation or urban/rural classification.
Journal ArticleDOI
Annotating Images by Mining Image Search Results
TL;DR: This paper proposes a novel attempt at model-free image annotation, which is a data-driven approach that annotates images by mining their search results, and enables annotating with unlimited vocabulary and is highly scalable and robust to outliers.
Proceedings ArticleDOI
Recognition by association via learning per-exemplar distances
TL;DR: This work uses the distance functions to detect and segment objects in novel images by associating the bottom-up segments obtained from multiple image segmentations with the exemplar regions and learns separate distance functions for each exemplar.