Andrew Zisserman

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.

Detect to Track and Track to Detect

Abstract: Recent approaches for high accuracy detection and tracking of object categories in video consist of complex multistage solutions that become more cumbersome each year. In this paper we propose a ConvNet architecture that jointly performs detection and tracking, solving the task in a simple and effective way. Our contributions are threefold: (i) we set up a ConvNet architecture for simultaneous detection and tracking, using a multi-task objective for frame-based object detection and across-frame track regression; (ii) we introduce correlation features that represent object co-occurrences across time to aid the ConvNet during tracking; and (iii) we link the frame level detections based on our across-frame tracklets to produce high accuracy detections at the video level. Our ConvNet architecture for spatiotemporal object detection is evaluated on the large-scale ImageNet VID dataset where it achieves state-of-the-art results. Our approach provides better single model performance than the winning method of the last ImageNet challenge while being conceptually much simpler. Finally, we show that by increasing the temporal stride we can dramatically increase the tracker speed.

Strike a pose: tracking people by finding stylized poses

Abstract: We develop an algorithm for finding and kinematically tracking multiple people in long sequences. Our basic assumption is that people tend to take on certain canonical poses, even when performing unusual activities like throwing a baseball or figure skating. We build a person detector that quite accurately detects and localizes limbs of people in lateral walking poses. We use the estimated limbs from a detection to build a discriminative appearance model; we assume the features that discriminate a figure in one frame will discriminate the figure in other frames. We then use the models as limb detectors in a pictorial structure framework, detecting figures in unrestricted poses in both previous and successive frames. We have run our tracker on hundreds of thousands of frames, and present and apply a methodology for evaluating tracking on such a large scale. We test our tracker on real sequences including a feature-length film, an hour of footage from a public park, and various sports sequences. We find that we can quite accurately automatically find and track multiple people interacting with each other while performing fast and unusual motions.

Vision Algorithms: Theory and Practice

Abstract: While many algorithms for computing stereo correspondence have been proposed, there has been very little work on experimentally evaluating algorithm performance, especially using real (rather than synthetic) imagery. In this paper we propose an experimental comparison of several different stereo algorithms. We use real imagery, and explore two different methodologies, with different strengths and weaknesses. Our first methodology is based upon manual computation of dense ground truth. Here we make use of a two stereo pairs: one of these, from the University of Tsukuba, contains mostly fronto-parallel surfaces; while the other, which we built, is a simple scene with a slanted surface. Our second methodology uses the notion of prediction error, which is the ability of a disparity map to predict an (unseen) third image, taken from a known camera position with respect to the input pair. We present results for both correlation-style stereo algorithms and techniques based on global methods such as energy minimization. Our experiments suggest that the two methodologies give qualitatively consistent results. Source images and additional materials, such as the implementations of various algorithms, are available on the web from http://www.research.microsoft.com/ ̃szeliski/stereo.

Objects that Sound

Abstract: In this paper our objectives are, first, networks that can embed audio and visual inputs into a common space that is suitable for cross-modal retrieval; and second, a network that can localize the object that sounds in an image, given the audio signal. We achieve both these objectives by training from unlabelled video using only audio-visual correspondence (AVC) as the objective function. This is a form of cross-modal self-supervision from video.

Wide baseline stereo matching

Abstract: The objective of this work is to enlarge the class of camera motions for which epipolar geometry and image correspondences can be computed automatically. This facilitates matching between quite disparate views-wide baseline stereo. Two extensions are made to the current small baseline algorithms: first, and most importantly, a viewpoint invariant measure is developed for assessing the affinity of corner neighbourhoods over image pairs; second, algorithms are given for generating putative corner matches between image pairs using local homographies. Two novel infrastructure developments are also described: the automatic generation of local homographies, and the combination of possibly conflicting sets of matches prior to RANSAC estimation. The wide baseline matching algorithm is demonstrated on a number of image pairs with varying relative motion, and for different scene types. All processing is automatic.

Deep Residual Learning for Image Recognition

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.

Very Deep Convolutional Networks for Large-Scale Image Recognition

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.

Very Deep Convolutional Networks for Large-Scale Image Recognition

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.

ImageNet: A large-scale hierarchical image database

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.

U-Net: Convolutional Networks for Biomedical Image Segmentation

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 .