Detecting Avocados to Zucchinis: What Have We Done, and Where Are We Going?

By Olga Russakovsky, Jia Deng, Zhiheng Huang, Alexander C. Berg, Li Fei-Fei. 2013

92 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Discriminative k-shot learning using probabilistic models (2017, methodology): “The baselines are computed on the features x = Φ φ ( u ) from the last hidden layer of the trained CNN: (i) Nearest Neighbours with cosine distance and (ii) regularized logistic regression with regularisation constant set either by cross-validation or (iii) using the variance of the weights, C = 2 σ”
SUN Database: Exploring a Large Collection of Scene Categories (2014, methodology): “Following the criteria used in Russakovsky et al. (2013), the object scale in an image is calculated as the ratio between the area of a ground truth bounding box around the object and the area of the image.”
Multi-scale Orderless Pooling of Deep Convolutional Activation Features (2014, background): “ILSVRC2012/2013 [31,32], or ImageNet Large-Scale Visual Recognition Challenge, is the most prominent benchmark for comparing large-scale image classification methods and is the dataset on which the Caffe representation we use [24] is pre-trained.”
Bird Species Categorization Using Pose Normalized Deep Convolutional Nets (2014, methodology): “We propose a novel graph-based clustering algorithm for learning a compact pose normalization space.”
YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video (2017, background): “• ImageNet 2015 [42] has a video object detection data set with 5,400 videos.”
Reducing Network Agnostophobia (2018, background): “Ever since a convolutional neural network (CNN) [19] won the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) in 2012 [33], the extraordinary increase in the performance of deep learning architectures has contributed to the growing application of computer vision algorithms.”
Answering Visual-Relational Queries in Web-Extracted Knowledge Graphs (2017, methodology): “…Visual Data Previous work on combining relational and visual data has focused on object detection [Felzenszwalb et al., 2010, Girshick et al., 2014, Russakovsky et al., 2013, Marino et al., 2017, Li et al., 2017] and scene recognition [Doersch et al., 2013, Pandey and Lazebnik, 2011, Sadeghi and…”
Do More Dropouts in Pool5 Feature Maps for Better Object Detection (2014, background): “Small objects like bird and bottle are more difﬁcult to be detected, which is also described by Russakovsky et al. [28].”
VisKE: Visual knowledge extraction and question answering by visual verification of relation phrases (2015, methodology): “Most previous research in this area has primarily focused on the tasks of image classification [8], scene recognition [10, 27, 31, 38] and object detection [12, 16, 17, 30] that form the fundamental building blocks for higher order visual reasoning systems.”
Representation Learning for Visual-Relational Knowledge Graphs (2017, background): “Previous work on combining relational and visual data has focused on object detection [20,21,22,23,24] and scene recognition [25,26,27,28,29] which are required for more complex visual-relational reasoning.”
Diagnosing Error in Temporal Action Detectors (2018, methodology): “Inspired by this work, [11,19,27,30,31,32,36,44] provided insightful analysis of algorithms for multiple localization tasks such as human pose estimation, object detection at large-scale and multi-label action classification, in still images in most of the cases.”
Spatial Semantic Regularisation for Large Scale Object Detection (2015, background): “Recently, large scale detection approaches have been proposed which aim to distinguish hundreds or thousands of object categories [1, 3, 11, 12, 23].”
Objectness to improve the bag of visual words model (2014, methodology): “In the second experiment, the SVM classifier based on the one versus all scheme is used for the multi-class task.”