scispace - formally typeset
Search or ask a question
Author

Richard P. Wildes

Bio: Richard P. Wildes is an academic researcher from York University. The author has contributed to research in topics: Motion estimation & Computer science. The author has an hindex of 35, co-authored 93 publications receiving 7752 citations. Previous affiliations of Richard P. Wildes include Sarnoff Corporation & University at Buffalo.


Papers
More filters
Journal ArticleDOI
01 Sep 1997
TL;DR: This paper examines automated iris recognition as a biometrically based technology for personal identification and verification from the observation that the human iris provides a particularly interesting structure on which to base a technology for noninvasive biometric assessment.
Abstract: This paper examines automated iris recognition as a biometrically based technology for personal identification and verification. The motivation for this endeavor stems from the observation that the human iris provides a particularly interesting structure on which to base a technology for noninvasive biometric assessment. In particular the biomedical literature suggests that irises are as distinct as fingerprints or patterns of retinal blood vessels. Further, since the iris is an overt body, its appearance is amenable to remote examination with the aid of a machine vision system. The body of this paper details issues in the design and operation of such systems. For the sake of illustration, extant systems are described in some amount of detail.

2,046 citations

Proceedings ArticleDOI
01 Jul 2017
TL;DR: A general ConvNet architecture for video action recognition based on multiplicative interactions of spacetime features that combines the appearance and motion pathways of a two-stream architecture by motion gating and is trained end-to-end.
Abstract: This paper presents a general ConvNet architecture for video action recognition based on multiplicative interactions of spacetime features. Our model combines the appearance and motion pathways of a two-stream architecture by motion gating and is trained end-to-end. We theoretically motivate multiplicative gating functions for residual networks and empirically study their effect on classification accuracy. To capture long-term dependencies we inject identity mapping kernels for learning temporal relationships. Our architecture is fully convolutional in spacetime and able to evaluate a video in a single forward pass. Empirical investigation reveals that our model produces state-of-the-art results on two standard action recognition datasets.

629 citations

Posted Content
TL;DR: In this article, the authors proposed spatiotemporal residual networks (ResNets) for action recognition in videos, which is a combination of two-stream convolutional networks and residual connections between appearance and motion pathways.
Abstract: Two-stream Convolutional Networks (ConvNets) have shown strong performance for human action recognition in videos. Recently, Residual Networks (ResNets) have arisen as a new technique to train extremely deep architectures. In this paper, we introduce spatiotemporal ResNets as a combination of these two approaches. Our novel architecture generalizes ResNets for the spatiotemporal domain by introducing residual connections in two ways. First, we inject residual connections between the appearance and motion pathways of a two-stream architecture to allow spatiotemporal interaction between the two streams. Second, we transform pretrained image ConvNets into spatiotemporal networks by equipping these with learnable convolutional filters that are initialized as temporal residual connections and operate on adjacent feature maps in time. This approach slowly increases the spatiotemporal receptive field as the depth of the model increases and naturally integrates image ConvNet design principles. The whole model is trained end-to-end to allow hierarchical learning of complex spatiotemporal features. We evaluate our novel spatiotemporal ResNet using two widely used action recognition benchmarks where it exceeds the previous state-of-the-art.

504 citations

Patent
05 Sep 1995
TL;DR: Iris recognition is achieved by iris acquisition that permits a user to self-position his or her eye (216) into an imager's (200) field of view without the need for any physical contact as discussed by the authors.
Abstract: Iris recognition is achieved by iris acquisition that permits a user to self-position his or her eye (216) into an imager's (200) field of view without the need for any physical contact, spatially locating the data defining that portion of a digitized video image of the user's eye that defines solely the iris thereof without any initial spatial condition of the iris being provided, and pattern matching the spatially located data defining the iris of the user's eye with stored data defining a model iris by employing normalized spatial correlation for first comparing, at each of a plurality of spatial scales, each of distinctive spatial characteristics of the respective irises that are spatially registered with one another to quantitatively determine, at each of the plurality of spatial scales, a goodness value of match at that spatial scale, and then judging whether or not the pattern which manifests solely the iris of the user's eye matches the digital data which manifests solely the model iris in accordance with a certain combination of the quantitatively-determined goodness values of match at each of said plurality of spatial scales.

499 citations

Proceedings Article
05 Dec 2016
TL;DR: The novel spatiotemporal ResNet is introduced and evaluated using two widely used action recognition benchmarks where it exceeds the previous state-of-the-art.
Abstract: Two-stream Convolutional Networks (ConvNets) have shown strong performance for human action recognition in videos. Recently, Residual Networks (ResNets) have arisen as a new technique to train extremely deep architectures. In this paper, we introduce spatiotemporal ResNets as a combination of these two approaches. Our novel architecture generalizes ResNets for the spatiotemporal domain by introducing residual connections in two ways. First, we inject residual connections between the appearance and motion pathways of a two-stream architecture to allow spatiotemporal interaction between the two streams. Second, we transform pretrained image ConvNets into spatiotemporal networks by equipping these with learnable convolutional filters that are initialized as temporal residual connections and operate on adjacent feature maps in time. This approach slowly increases the spatiotemporal receptive field as the depth of the model increases and naturally integrates image ConvNet design principles. The whole model is trained end-to-end to allow hierarchical learning of complex spatiotemporal features. We evaluate our novel spatiotemporal ResNet using two widely used action recognition benchmarks where it exceeds the previous state-of-the-art.

453 citations


Cited by
More filters
Proceedings ArticleDOI
18 Jun 2018
TL;DR: In this article, the non-local operation computes the response at a position as a weighted sum of the features at all positions, which can be used to capture long-range dependencies.
Abstract: Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family of building blocks for capturing long-range dependencies. Inspired by the classical non-local means method [4] in computer vision, our non-local operation computes the response at a position as a weighted sum of the features at all positions. This building block can be plugged into many computer vision architectures. On the task of video classification, even without any bells and whistles, our nonlocal models can compete or outperform current competition winners on both Kinetics and Charades datasets. In static image recognition, our non-local models improve object detection/segmentation and pose estimation on the COCO suite of tasks. Code will be made available.

8,059 citations

Proceedings ArticleDOI
07 Dec 2015
TL;DR: The learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks.
Abstract: We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are more suitable for spatiotemporal feature learning compared to 2D ConvNets, 2) A homogeneous architecture with small 3x3x3 convolution kernels in all layers is among the best performing architectures for 3D ConvNets, and 3) Our learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks. In addition, the features are compact: achieving 52.8% accuracy on UCF101 dataset with only 10 dimensions and also very efficient to compute due to the fast inference of ConvNets. Finally, they are conceptually very simple and easy to train and use.

7,091 citations

Proceedings ArticleDOI
21 Jul 2017
TL;DR: In this article, a Two-Stream Inflated 3D ConvNet (I3D) is proposed to learn seamless spatio-temporal feature extractors from video while leveraging successful ImageNet architecture designs and their parameters.
Abstract: The paucity of videos in current action classification datasets (UCF-101 and HMDB-51) has made it difficult to identify good video architectures, as most methods obtain similar performance on existing small-scale benchmarks. This paper re-evaluates state-of-the-art architectures in light of the new Kinetics Human Action Video dataset. Kinetics has two orders of magnitude more data, with 400 human action classes and over 400 clips per class, and is collected from realistic, challenging YouTube videos. We provide an analysis on how current architectures fare on the task of action classification on this dataset and how much performance improves on the smaller benchmark datasets after pre-training on Kinetics. We also introduce a new Two-Stream Inflated 3D ConvNet (I3D) that is based on 2D ConvNet inflation: filters and pooling kernels of very deep image classification ConvNets are expanded into 3D, making it possible to learn seamless spatio-temporal feature extractors from video while leveraging successful ImageNet architecture designs and even their parameters. We show that, after pre-training on Kinetics, I3D models considerably improve upon the state-of-the-art in action classification, reaching 80.2% on HMDB-51 and 97.9% on UCF-101.

5,073 citations

Journal ArticleDOI
TL;DR: A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects, is proposed, which employs a metric derived from the Bhattacharyya coefficient as similarity measure, and uses the mean shift procedure to perform the optimization.
Abstract: A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects, is proposed. The feature histogram-based target representations are regularized by spatial masking with an isotropic kernel. The masking induces spatially-smooth similarity functions suitable for gradient-based optimization, hence, the target localization problem can be formulated using the basin of attraction of the local maxima. We employ a metric derived from the Bhattacharyya coefficient as similarity measure, and use the mean shift procedure to perform the optimization. In the presented tracking examples, the new method successfully coped with camera motion, partial occlusions, clutter, and target scale variations. Integration with motion filters and data association techniques is also discussed. We describe only a few of the potential applications: exploitation of background information, Kalman tracking using motion models, and face tracking.

4,996 citations

Posted Content
TL;DR: In this article, the authors proposed a simple and effective approach for spatio-temporal feature learning using deep 3D convolutional networks (3D ConvNets) trained on a large scale supervised video dataset.
Abstract: We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are more suitable for spatiotemporal feature learning compared to 2D ConvNets; 2) A homogeneous architecture with small 3x3x3 convolution kernels in all layers is among the best performing architectures for 3D ConvNets; and 3) Our learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks. In addition, the features are compact: achieving 52.8% accuracy on UCF101 dataset with only 10 dimensions and also very efficient to compute due to the fast inference of ConvNets. Finally, they are conceptually very simple and easy to train and use.

3,786 citations