scispace - formally typeset
Search or ask a question
Author

Andrew Zisserman

Other affiliations: University of Edinburgh, Microsoft, University of Leeds  ...read more
Bio: Andrew Zisserman is an academic researcher from University of Oxford. The author has contributed to research in topics: Real image & Convolutional neural network. The author has an hindex of 167, co-authored 808 publications receiving 261717 citations. Previous affiliations of Andrew Zisserman include University of Edinburgh & Microsoft.


Papers
More filters
Book ChapterDOI
18 Sep 2011
TL;DR: This work enables the user to select a query Region Of Interest (ROI) and automatically detect the corresponding regions within all returned images, which allows the returned images to be ranked on the content of the ROI, rather than the entire image.
Abstract: The objective of this work is a scalable, real-time visual search engine for medical images. In contrast to existing systems that retrieve images that are globally similar to a query image, we enable the user to select a query Region Of Interest (ROI) and automatically detect the corresponding regions within all returned images. This allows the returned images to be ranked on the content of the ROI, rather than the entire image. Our contribution is two-fold: (i) immediate retrieval - the data is appropriately pre-processed so that the search engine returns results in real-time for any query image and ROI; (ii) structured output - returning ROIs with a choice of ranking functions. The retrieval performance is assessed on a number of annotated queries for images from the IRMA X-ray dataset and compared to a baseline.

19 citations

Book ChapterDOI
01 Nov 2014
TL;DR: This work studies the task of recognizing human actions in video whilst paying attention to the shot and thread editing structure, which is generally present in edited TV and film material.
Abstract: We study the task of recognizing human actions in video whilst paying attention to the shot and thread editing structure. Most existing action recognition algorithms ignore this structure, but it is generally present in edited TV and film material.

19 citations

Proceedings ArticleDOI
01 Sep 2014
TL;DR: A pose estimation model with the following novelties: the joints are estimated sequentially, taking account of the human kinematic chain, and dense optical flow is used to align multiple expert joint position proposals from nearby frames, and thereby improve the robustness of the estimates.
Abstract: Our objective is to efficiently and accurately estimate human upper body pose in gesture videos. To this end, we build on the recent successful applications of random forests (RF) classifiers and regressors, and develop a pose estimation model with the following novelties: (i) the joints are estimated sequentially, taking account of the human kinematic chain. This means that we don't have to make the simplifying assumption of most previous RF methods - that the joints are estimated independently; (ii) by combining both classifiers (as a mixture of experts) and regressors, we show that the learning problem is tractable and that more context can be taken into account; and (iii) dense optical flow is used to align multiple expert joint position proposals from nearby frames, and thereby improve the robustness of the estimates. The resulting method is computationally efficient and can overcome a number of the errors (e.g. confusing left/right hands) made by RF pose estimators that infer their locations independently. We show that we improve over the state of the art on upper body pose estimation for two public datasets: the BBC TV Signing dataset and the ChaLearn Gesture Recognition dataset.

19 citations

Proceedings ArticleDOI
01 Oct 1994
TL;DR: It is demonstrated that viewpoint-invariant representations can be obtained from images for a useful class of 3D smooth object, which includes canal surfaces and surfaces of revolution, and are used as the basis for a model-based object recognition system.
Abstract: We demonstrate that viewpoint-invariant representations can be obtained from images for a useful class of 3D smooth object. The class of surfaces are those generated as the envelope of a sphere of varying radius swept along an axis. This class includes canal surfaces and surfaces of revolution. The representations are computed, using only image information, from the symmetry set of the object's outline. They are viewpoint-invariant under weak-perspective imaging, and quasi-invariant to an excellent approximation under perspective imaging. To this approximation, the planar axis of a canal surface is recovered up to an affine ambiguity from perspective images. Examples are given of the representations obtained from real images, which demonstrate stability and object discrimination, for both canal surfaces and surfaces of revolution. Finally, the representations are used as the basis for a model-based object recognition system

18 citations

Posted Content
16 Jul 2020
TL;DR: A simple approach to determining correspondences between image pairs under large changes in illumination, viewpoint, context, and material and can be used to achieve state of the art or competitive results on a wide range of tasks: local matching, camera localization, 3D reconstruction, and image stylization.
Abstract: We propose a new approach to determining correspondences between image pairs under large changes in illumination, viewpoint, context, and material. While most approaches seek to extract a set of reliably detectable regions in each image which are then compared (sparse-to-sparse) using increasingly complicated or specialized pipelines, we propose a simple approach for matching all points between the images (dense-to-dense) and subsequently selecting the best matches. The two key parts of our approach are: (i) to condition the learned features on both images, and (ii) to learn a distinctiveness score which is used to choose the best matches at test time. We demonstrate that our model can be used to achieve state of the art or competitive results on a wide range of tasks: local matching, camera localization, 3D reconstruction, and image stylization.

18 citations


Cited by
More filters
Proceedings ArticleDOI
27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

123,388 citations

Proceedings Article
04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

55,235 citations

Proceedings Article
01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

49,914 citations

Proceedings ArticleDOI
Jia Deng1, Wei Dong1, Richard Socher1, Li-Jia Li1, Kai Li1, Li Fei-Fei1 
20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Abstract: The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images and multimedia data. But exactly how such data can be harnessed and organized remains a critical problem. We introduce here a new database called “ImageNet”, a large-scale ontology of images built upon the backbone of the WordNet structure. ImageNet aims to populate the majority of the 80,000 synsets of WordNet with an average of 500-1000 clean and full resolution images. This will result in tens of millions of annotated images organized by the semantic hierarchy of WordNet. This paper offers a detailed analysis of ImageNet in its current state: 12 subtrees with 5247 synsets and 3.2 million images in total. We show that ImageNet is much larger in scale and diversity and much more accurate than the current image datasets. Constructing such a large-scale database is a challenging task. We describe the data collection scheme with Amazon Mechanical Turk. Lastly, we illustrate the usefulness of ImageNet through three simple applications in object recognition, image classification and automatic object clustering. We hope that the scale, accuracy, diversity and hierarchical structure of ImageNet can offer unparalleled opportunities to researchers in the computer vision community and beyond.

49,639 citations

Book ChapterDOI
05 Oct 2015
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Abstract: There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net .

49,590 citations