Search

Your search keyword '"Berg, Alexander C."' showing total 37 results
Start Over Author "Berg, Alexander C." Publisher ieee
37 results on '"Berg, Alexander C."'

17. Rebooting Computing and Low-Power Image Recognition Challenge

Author

Lu, Yung-Hsiang, primary, Kadin, Alan M., additional, Berg, Alexander C., additional, Conte, Thomas M., additional, DeBenedictis, Erik P., additional, Garg, Rachit, additional, Gingade, Ganesh, additional, Hoang, Bichlien, additional, Huang, Yongzhen, additional, Li, Boxun, additional, Liu, Jingyu, additional, Liu, Wei, additional, Mao, Huizi, additional, Peng, Junran, additional, Tang, Tianqi, additional, Track, Elie K., additional, Wang, Jingqiu, additional, Wang, Tao, additional, Wang, Yu, additional, and Yao, Jun, additional

Published
2015
Full Text
View/download PDF

33. Understanding and predicting importance in images.

Author

Berg, Alexander C., Berg, Tamara L., Daume, Hal, Dodge, Jesse, Goyal, Amit, Han, Xufeng, Mensch, Alyssa, Mitchell, Margaret, Sood, Aneesh, Stratos, Karl, and Yamaguchi, Kota

Abstract

What do people care about in an image? To drive computational visual recognition toward more human-centric outputs, we need a better understanding of how people perceive and judge the importance of content in images. In this paper, we explore how a number of factors relate to human perception of importance. Proposed factors fall into 3 broad types: 1) factors related to composition, e.g. size, location, 2) factors related to semantics, e.g. category of object or scene, and 3) contextual factors related to the likelihood of attribute-object, or object-scene pairs. We explore these factors using what people describe as a proxy for importance. Finally, we build models to predict what will be described about an image given either known image content, or image content estimated automatically by recognition systems. [ABSTRACT FROM PUBLISHER]

Published
2012
Full Text
View/download PDF

34. DCMSVM: Distributed parallel training for single-machine multiclass classifiers.

Author

Han, Xufeng and Berg, Alexander C.

Abstract

We present an algorithm and implementation for distributed parallel training of single-machine multiclass SVMs. While there is ongoing and healthy debate about the best strategy for multiclass classification, there are some features of the single-machine approach that are not available when training alternatives such as one-vs-all, and that are quite complex for tree based methods. One obstacle to exploring single-machine approaches on large datasets is that they are usually limited to running on a single machine! We build on a framework borrowed from parallel convex optimization — the alternating direction method of multipliers (ADMM) — to develop a new consensus based algorithm for distributed training of single-machine approaches. This is demonstrated with an implementation of our novel sequential dual algorithm (DCMSVM) which allows distributed parallel training with small communication requirements. Benchmark results show significant reduction in wall clock time compared to current state of the art multiclass SVM implementation (Liblinear) on a single node. Experiments are performed on large scale image classification including results with modern high-dimensional features. [ABSTRACT FROM PUBLISHER]

Published
2012
Full Text
View/download PDF

35. Hedging your bets: Optimizing accuracy-specificity trade-offs in large scale visual recognition.

Author

Deng, Jia, Krause, Jonathan, Berg, Alexander C., and Fei-Fei, Li

Abstract

As visual recognition scales up to ever larger numbers of categories, maintaining high accuracy is increasingly difficult. In this work, we study the problem of optimizing accuracy-specificity trade-offs in large scale recognition, motivated by the observation that object categories form a semantic hierarchy consisting of many levels of abstraction. A classifier can select the appropriate level, trading off specificity for accuracy in case of uncertainty. By optimizing this trade-off, we obtain classifiers that try to be as specific as possible while guaranteeing an arbitrarily high accuracy. We formulate the problem as maximizing information gain while ensuring a fixed, arbitrarily small error rate with a semantic hierarchy. We propose the Dual Accuracy Reward Trade-off Search (DARTS) algorithm and prove that, under practical conditions, it converges to an optimal solution. Experiments demonstrate the effectiveness of our algorithm on datasets ranging from 65 to over 10,000 categories. [ABSTRACT FROM PUBLISHER]

Published
2012
Full Text
View/download PDF

36. BabyTalk: Understanding and Generating Simple Image Descriptions.

Author

Kulkarni, Girish, Premraj, Visruth, Ordonez, Vicente, Dhar, Sagnik, Li, Siming, Choi, Yejin, Berg, Alexander C., and Berg, Tamara L.

Subjects
COMPUTER vision, IMAGE segmentation, NATURAL language processing, INFORMATION processing, GEOMETRICAL constructions, PATTERN recognition systems, COMPUTER algorithms
Abstract

We present a system to automatically generate natural language descriptions from images. This system consists of two parts. The first part, content planning, smooths the output of computer vision-based detection and recognition algorithms with statistics mined from large pools of visually descriptive text to determine the best content words to use to describe an image. The second step, surface realization, chooses words to construct natural language sentences based on the predicted content and general statistics from natural language. We present multiple approaches for the surface realization step and evaluate each using automatic measures of similarity to human generated reference descriptions. We also collect forced choice human evaluations between descriptions from the proposed generation system and descriptions from competing approaches. The proposed system is very effective at producing relevant sentences for images. It also generates descriptions that are notably more true to the specific image content than previous work. [ABSTRACT FROM PUBLISHER]

Published
2013
Full Text
View/download PDF

37. Efficient Classification for Additive Kernel SVMs.

Author

Maji, Subhransu, Berg, Alexander C., and Malik, Jitendra

Subjects
*SUPPORT vector machines, *KERNEL functions, *HISTOGRAMS, *IMAGE processing, *ALGORITHMS, *PEDESTRIANS
Abstract

We show that a class of nonlinear kernel SVMs admits approximate classifiers with runtime and memory complexity that is independent of the number of support vectors. This class of kernels, which we refer to as additive kernels, includes widely used kernels for histogram-based image comparison like intersection and chi-squared kernels. Additive kernel SVMs can offer significant improvements in accuracy over linear SVMs on a wide variety of tasks while having the same runtime, making them practical for large-scale recognition or real-time detection tasks. We present experiments on a variety of datasets, including the INRIA person, Daimler-Chrysler pedestrians, UIUC Cars, Caltech-101, MNIST, and USPS digits, to demonstrate the effectiveness of our method for efficient evaluation of SVMs with additive kernels. Since its introduction, our method has become integral to various state-of-the-art systems for PASCAL VOC object detection/image classification, ImageNet Challenge, TRECVID, etc. The techniques we propose can also be applied to settings where evaluation of weighted additive kernels is required, which include kernelized versions of PCA, LDA, regression, k-means, as well as speeding up the inner loop of SVM classifier training algorithms. [ABSTRACT FROM AUTHOR]

Published
2013
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results