<b>Notre-Dame Cathedral Fire Dataset</b><b># of images: </b>1,657 images ... more <b>Notre-Dame Cathedral Fire Dataset</b><b># of images: </b>1,657 images during or after the fire<br>If you use the dataset, please cite one of the following works:<br>Padilha, Rafael and Andaló, Fernanda A. and Pereira, Luís A. M. and Rocha, Anderson. "Unraveling the Notre Dame Cathedral fire in space and time: an X-coherence approach," in Crime Science and Digital Forensics: A holistic view. CRC Press by Taylor and Francis Group, in press.<br><br>Padilha, Rafael and Andaló, Fernanda A. and Rocha, Anderson. "Improving the chronological sorting of images through occlusion: A study on the Notre-Dame cathedral fire," in 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020. <br><br><br><br><br><b>Description of the event and data collection: </b>On April 15th, 2019, large parts of Notre-Dame Cathedral's structure and spire were devastated by a fire. People worldwide followed the tragic event through images and videos that were shared by the media and citizens.<br>From the generated imagery, we collected a total of 23,683 images posted on Twitter during and on the day after the fire. Even though most of them were related to the event, several were memes, cartoons, compositions and artwork, while some depicted the cathedral before the fire. As we focus on learning how the fire and appearance of the cathedral evolved during the event, we removed them, reducing our set to 5,206 relevant images. Among these, several examples were duplicates or near-duplicates of other images. Considering their little contribution to the training process, after their removal, we were left with 1,657 distinct images related to the event. The cleaning process involved using methods such as local sensitive hashing for filtering near-duplicates, and semi-supervised approaches based on Optimum-path Forest theory to mine for relevant and non-relevant imagery of the event. By analyzing the event's description, four main sub-events can be defined: <i>spire on fire</i>, <i>spire collapsing</i>, <i>fire continues [...]
In this paper, we examine the strength of deep learning technique for diagnosing lung cancer on m... more In this paper, we examine the strength of deep learning technique for diagnosing lung cancer on medical image analysis problem. Convolutional neural networks (CNNs) models become popular among the pattern recognition and computer vision research area because of their promising outcome on generating high-level image representations. We propose a new deep learning architecture for learning high-level image representation to achieve high classification accuracy with low variance in medical image binary classification tasks. We aim to learn discriminant compact features at beginning of our deep convolutional neural network. We evaluate our model on Kaggle Data Science Bowl 2017 (KDSB17) data set, and compare it with some related works proposed in the Kaggle competition.
Biometric systems are prevalent in access control but are vulnerable to frauds. A typical attempt... more Biometric systems are prevalent in access control but are vulnerable to frauds. A typical attempt of violating them is through presentation attacks, in which synthetic data is directly presented to an acquisition sensor to deceive these systems. A well-designed biometric system should have a presentation attack detection (PAD) module. A fruitful way to perform PAD is to model properties of peculiar traits (artifacts) in synthetic data. Studies have been advocating for approaches that seek to model the artifacts automatically from data (data-driven), achieving state-of-the-art results in PAD. However, the following questions arise from this literature: Which approaches are the state of the art? When do these approaches fail? How can such approaches complement the proposed ones based on human knowledge on PAD? How robust are these approaches under cross-dataset scenarios? Are these approaches robust against new attack types (e.g., face morphing)? Do these methods provide other ways to...
One of the goals of person re-identification systems is to support video-surveillance operators a... more One of the goals of person re-identification systems is to support video-surveillance operators and forensic investigators to find an individual of interest in videos acquired by a network of non-overlapping cameras. This is attained by sorting images of previously observed individuals for decreasing values of their similarity with a given probe individual. Existing appearance descriptors, together with their similarity measures, are mostly aimed at improving ranking quality. We propose two fuzzy-based descriptors which are fast in terms of the processing time on descriptor generation and matching score computation. We then evaluate our approach on three benchmark data sets (VIPeR, i-LIDS, and ETHZ) with comparison of some descriptors in the state-of-the-art.
Intelligent video-surveillance (IVS) is currently an active research field in computer vision and... more Intelligent video-surveillance (IVS) is currently an active research field in computer vision and machine learning and provides useful tools for surveillance operators and forensic video investigators. Person re-identification (PReID) is one of the most critical problems in IVS, and it consists of recognizing whether or not an individual has already been observed over a camera in a network. Solutions to PReID have myriad applications including retrieval of video-sequences showing an individual of interest or even pedestrian tracking over multiple camera views. Different techniques have been proposed to increase the performance of PReID in the literature, and more recently researchers utilized deep neural networks (DNNs) given their compelling performance on similar vision problems and fast execution at test time. Given the importance and wide range of applications of re-identification solutions, our objective herein is to discuss the work carried out in the area and come up with a s...
Intelligent video-surveillance is currently an active research field in computer vision and machi... more Intelligent video-surveillance is currently an active research field in computer vision and machine learning techniques. It provides useful tools for surveillance operators and forensic video investigators. Person re-identification (PReID) is one among these tools. It consists of recognizing whether an individual has already been observed over a camera in a network or not. This tool can also be employed in various possible applications such as off-line retrieval of all the video-sequences showing an individual of interest whose image is given a query, and online pedestrian tracking over multiple camera views. To this aim, many techniques have been proposed to increase the performance of PReID. Among the systems, many researchers utilized deep neural networks (DNNs) because of their better performance and fast execution at test time. Our objective is to provide for future researchers the work being done on PReID to date. Therefore, we summarized state-of-the-art DNN models being used...
<b>Notre-Dame Cathedral Fire Dataset</b><b># of images: </b>1,657 images ... more <b>Notre-Dame Cathedral Fire Dataset</b><b># of images: </b>1,657 images during or after the fire<br>If you use the dataset, please cite one of the following works:<br>Padilha, Rafael and Andaló, Fernanda A. and Pereira, Luís A. M. and Rocha, Anderson. "Unraveling the Notre Dame Cathedral fire in space and time: an X-coherence approach," in Crime Science and Digital Forensics: A holistic view. CRC Press by Taylor and Francis Group, in press.<br><br>Padilha, Rafael and Andaló, Fernanda A. and Rocha, Anderson. "Improving the chronological sorting of images through occlusion: A study on the Notre-Dame cathedral fire," in 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020. <br><br><br><br><br><b>Description of the event and data collection: </b>On April 15th, 2019, large parts of Notre-Dame Cathedral's structure and spire were devastated by a fire. People worldwide followed the tragic event through images and videos that were shared by the media and citizens.<br>From the generated imagery, we collected a total of 23,683 images posted on Twitter during and on the day after the fire. Even though most of them were related to the event, several were memes, cartoons, compositions and artwork, while some depicted the cathedral before the fire. As we focus on learning how the fire and appearance of the cathedral evolved during the event, we removed them, reducing our set to 5,206 relevant images. Among these, several examples were duplicates or near-duplicates of other images. Considering their little contribution to the training process, after their removal, we were left with 1,657 distinct images related to the event. The cleaning process involved using methods such as local sensitive hashing for filtering near-duplicates, and semi-supervised approaches based on Optimum-path Forest theory to mine for relevant and non-relevant imagery of the event. By analyzing the event's description, four main sub-events can be defined: <i>spire on fire</i>, <i>spire collapsing</i>, <i>fire continues [...]
In this paper, we examine the strength of deep learning technique for diagnosing lung cancer on m... more In this paper, we examine the strength of deep learning technique for diagnosing lung cancer on medical image analysis problem. Convolutional neural networks (CNNs) models become popular among the pattern recognition and computer vision research area because of their promising outcome on generating high-level image representations. We propose a new deep learning architecture for learning high-level image representation to achieve high classification accuracy with low variance in medical image binary classification tasks. We aim to learn discriminant compact features at beginning of our deep convolutional neural network. We evaluate our model on Kaggle Data Science Bowl 2017 (KDSB17) data set, and compare it with some related works proposed in the Kaggle competition.
Biometric systems are prevalent in access control but are vulnerable to frauds. A typical attempt... more Biometric systems are prevalent in access control but are vulnerable to frauds. A typical attempt of violating them is through presentation attacks, in which synthetic data is directly presented to an acquisition sensor to deceive these systems. A well-designed biometric system should have a presentation attack detection (PAD) module. A fruitful way to perform PAD is to model properties of peculiar traits (artifacts) in synthetic data. Studies have been advocating for approaches that seek to model the artifacts automatically from data (data-driven), achieving state-of-the-art results in PAD. However, the following questions arise from this literature: Which approaches are the state of the art? When do these approaches fail? How can such approaches complement the proposed ones based on human knowledge on PAD? How robust are these approaches under cross-dataset scenarios? Are these approaches robust against new attack types (e.g., face morphing)? Do these methods provide other ways to...
One of the goals of person re-identification systems is to support video-surveillance operators a... more One of the goals of person re-identification systems is to support video-surveillance operators and forensic investigators to find an individual of interest in videos taken by a network of non-overlapping cameras. This is attained by sorting images of previously observed individuals for decreasing values of their similarity with the query individual. Several appearance-based descriptors have been proposed so far, together with ad hoc similarity measures, mostly aimed at improving ranking quality. We address instead the issue of the processing time required to compute the similarity values, and propose a multi-stage ranking approach to attain a trade-off with ranking quality, for any given descriptor. We give a preliminary evaluation of our approach on the benchmark VIPeR data set, using different state-of-the-art descriptors.
Intelligent video-surveillance (IVS) is currently an active research field in computer vision and... more Intelligent video-surveillance (IVS) is currently an active research field in computer vision and machine learning and provides useful tools for surveillance operators and forensic video investigators. Person re-identification (PReID) is one of the most critical problems in IVS, and it consists of recognizing whether or not an individual has already been observed over a camera in a network. Solutions to PReID have myriad applications including retrieval of video-sequences showing an individual of interest or even pedestrian tracking over multiple camera views. Different techniques have been proposed to increase the performance of PReID in the literature, and more recently researchers utilized deep neural networks (DNNs) given their compelling performance on similar vision problems and fast execution at test time. Given the importance and wide range of applications of re-identification solutions, our objective herein is to discuss the work carried out in the area and come up with a s...
Intelligent video-surveillance is currently an active research field in computer vision and machi... more Intelligent video-surveillance is currently an active research field in computer vision and machine learning techniques. It provides useful tools for surveillance operators and forensic video investigators. Person re-identification (PReID) is one among these tools. It consists of recognizing whether an individual has already been observed over a camera in a network or not. This tool can also be employed in various possible applications such as off-line retrieval of all the video-sequences showing an individual of interest whose image is given a query, and online pedestrian tracking over multiple camera views. To this aim, many techniques have been proposed to increase the performance of PReID. Among the systems, many researchers utilized deep neural networks (DNNs) because of their better performance and fast execution at test time. Our objective is to provide for future researchers the work being done on PReID to date. Therefore, we summarized state-of-the-art DNN models being used...
<b>Notre-Dame Cathedral Fire Dataset</b><b># of images: </b>1,657 images ... more <b>Notre-Dame Cathedral Fire Dataset</b><b># of images: </b>1,657 images during or after the fire<br>If you use the dataset, please cite one of the following works:<br>Padilha, Rafael and Andaló, Fernanda A. and Pereira, Luís A. M. and Rocha, Anderson. "Unraveling the Notre Dame Cathedral fire in space and time: an X-coherence approach," in Crime Science and Digital Forensics: A holistic view. CRC Press by Taylor and Francis Group, in press.<br><br>Padilha, Rafael and Andaló, Fernanda A. and Rocha, Anderson. "Improving the chronological sorting of images through occlusion: A study on the Notre-Dame cathedral fire," in 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020. <br><br><br><br><br><b>Description of the event and data collection: </b>On April 15th, 2019, large parts of Notre-Dame Cathedral's structure and spire were devastated by a fire. People worldwide followed the tragic event through images and videos that were shared by the media and citizens.<br>From the generated imagery, we collected a total of 23,683 images posted on Twitter during and on the day after the fire. Even though most of them were related to the event, several were memes, cartoons, compositions and artwork, while some depicted the cathedral before the fire. As we focus on learning how the fire and appearance of the cathedral evolved during the event, we removed them, reducing our set to 5,206 relevant images. Among these, several examples were duplicates or near-duplicates of other images. Considering their little contribution to the training process, after their removal, we were left with 1,657 distinct images related to the event. The cleaning process involved using methods such as local sensitive hashing for filtering near-duplicates, and semi-supervised approaches based on Optimum-path Forest theory to mine for relevant and non-relevant imagery of the event. By analyzing the event's description, four main sub-events can be defined: <i>spire on fire</i>, <i>spire collapsing</i>, <i>fire continues [...]
In this paper, we examine the strength of deep learning technique for diagnosing lung cancer on m... more In this paper, we examine the strength of deep learning technique for diagnosing lung cancer on medical image analysis problem. Convolutional neural networks (CNNs) models become popular among the pattern recognition and computer vision research area because of their promising outcome on generating high-level image representations. We propose a new deep learning architecture for learning high-level image representation to achieve high classification accuracy with low variance in medical image binary classification tasks. We aim to learn discriminant compact features at beginning of our deep convolutional neural network. We evaluate our model on Kaggle Data Science Bowl 2017 (KDSB17) data set, and compare it with some related works proposed in the Kaggle competition.
Biometric systems are prevalent in access control but are vulnerable to frauds. A typical attempt... more Biometric systems are prevalent in access control but are vulnerable to frauds. A typical attempt of violating them is through presentation attacks, in which synthetic data is directly presented to an acquisition sensor to deceive these systems. A well-designed biometric system should have a presentation attack detection (PAD) module. A fruitful way to perform PAD is to model properties of peculiar traits (artifacts) in synthetic data. Studies have been advocating for approaches that seek to model the artifacts automatically from data (data-driven), achieving state-of-the-art results in PAD. However, the following questions arise from this literature: Which approaches are the state of the art? When do these approaches fail? How can such approaches complement the proposed ones based on human knowledge on PAD? How robust are these approaches under cross-dataset scenarios? Are these approaches robust against new attack types (e.g., face morphing)? Do these methods provide other ways to...
One of the goals of person re-identification systems is to support video-surveillance operators a... more One of the goals of person re-identification systems is to support video-surveillance operators and forensic investigators to find an individual of interest in videos acquired by a network of non-overlapping cameras. This is attained by sorting images of previously observed individuals for decreasing values of their similarity with a given probe individual. Existing appearance descriptors, together with their similarity measures, are mostly aimed at improving ranking quality. We propose two fuzzy-based descriptors which are fast in terms of the processing time on descriptor generation and matching score computation. We then evaluate our approach on three benchmark data sets (VIPeR, i-LIDS, and ETHZ) with comparison of some descriptors in the state-of-the-art.
Intelligent video-surveillance (IVS) is currently an active research field in computer vision and... more Intelligent video-surveillance (IVS) is currently an active research field in computer vision and machine learning and provides useful tools for surveillance operators and forensic video investigators. Person re-identification (PReID) is one of the most critical problems in IVS, and it consists of recognizing whether or not an individual has already been observed over a camera in a network. Solutions to PReID have myriad applications including retrieval of video-sequences showing an individual of interest or even pedestrian tracking over multiple camera views. Different techniques have been proposed to increase the performance of PReID in the literature, and more recently researchers utilized deep neural networks (DNNs) given their compelling performance on similar vision problems and fast execution at test time. Given the importance and wide range of applications of re-identification solutions, our objective herein is to discuss the work carried out in the area and come up with a s...
Intelligent video-surveillance is currently an active research field in computer vision and machi... more Intelligent video-surveillance is currently an active research field in computer vision and machine learning techniques. It provides useful tools for surveillance operators and forensic video investigators. Person re-identification (PReID) is one among these tools. It consists of recognizing whether an individual has already been observed over a camera in a network or not. This tool can also be employed in various possible applications such as off-line retrieval of all the video-sequences showing an individual of interest whose image is given a query, and online pedestrian tracking over multiple camera views. To this aim, many techniques have been proposed to increase the performance of PReID. Among the systems, many researchers utilized deep neural networks (DNNs) because of their better performance and fast execution at test time. Our objective is to provide for future researchers the work being done on PReID to date. Therefore, we summarized state-of-the-art DNN models being used...
<b>Notre-Dame Cathedral Fire Dataset</b><b># of images: </b>1,657 images ... more <b>Notre-Dame Cathedral Fire Dataset</b><b># of images: </b>1,657 images during or after the fire<br>If you use the dataset, please cite one of the following works:<br>Padilha, Rafael and Andaló, Fernanda A. and Pereira, Luís A. M. and Rocha, Anderson. "Unraveling the Notre Dame Cathedral fire in space and time: an X-coherence approach," in Crime Science and Digital Forensics: A holistic view. CRC Press by Taylor and Francis Group, in press.<br><br>Padilha, Rafael and Andaló, Fernanda A. and Rocha, Anderson. "Improving the chronological sorting of images through occlusion: A study on the Notre-Dame cathedral fire," in 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020. <br><br><br><br><br><b>Description of the event and data collection: </b>On April 15th, 2019, large parts of Notre-Dame Cathedral's structure and spire were devastated by a fire. People worldwide followed the tragic event through images and videos that were shared by the media and citizens.<br>From the generated imagery, we collected a total of 23,683 images posted on Twitter during and on the day after the fire. Even though most of them were related to the event, several were memes, cartoons, compositions and artwork, while some depicted the cathedral before the fire. As we focus on learning how the fire and appearance of the cathedral evolved during the event, we removed them, reducing our set to 5,206 relevant images. Among these, several examples were duplicates or near-duplicates of other images. Considering their little contribution to the training process, after their removal, we were left with 1,657 distinct images related to the event. The cleaning process involved using methods such as local sensitive hashing for filtering near-duplicates, and semi-supervised approaches based on Optimum-path Forest theory to mine for relevant and non-relevant imagery of the event. By analyzing the event's description, four main sub-events can be defined: <i>spire on fire</i>, <i>spire collapsing</i>, <i>fire continues [...]
In this paper, we examine the strength of deep learning technique for diagnosing lung cancer on m... more In this paper, we examine the strength of deep learning technique for diagnosing lung cancer on medical image analysis problem. Convolutional neural networks (CNNs) models become popular among the pattern recognition and computer vision research area because of their promising outcome on generating high-level image representations. We propose a new deep learning architecture for learning high-level image representation to achieve high classification accuracy with low variance in medical image binary classification tasks. We aim to learn discriminant compact features at beginning of our deep convolutional neural network. We evaluate our model on Kaggle Data Science Bowl 2017 (KDSB17) data set, and compare it with some related works proposed in the Kaggle competition.
Biometric systems are prevalent in access control but are vulnerable to frauds. A typical attempt... more Biometric systems are prevalent in access control but are vulnerable to frauds. A typical attempt of violating them is through presentation attacks, in which synthetic data is directly presented to an acquisition sensor to deceive these systems. A well-designed biometric system should have a presentation attack detection (PAD) module. A fruitful way to perform PAD is to model properties of peculiar traits (artifacts) in synthetic data. Studies have been advocating for approaches that seek to model the artifacts automatically from data (data-driven), achieving state-of-the-art results in PAD. However, the following questions arise from this literature: Which approaches are the state of the art? When do these approaches fail? How can such approaches complement the proposed ones based on human knowledge on PAD? How robust are these approaches under cross-dataset scenarios? Are these approaches robust against new attack types (e.g., face morphing)? Do these methods provide other ways to...
One of the goals of person re-identification systems is to support video-surveillance operators a... more One of the goals of person re-identification systems is to support video-surveillance operators and forensic investigators to find an individual of interest in videos taken by a network of non-overlapping cameras. This is attained by sorting images of previously observed individuals for decreasing values of their similarity with the query individual. Several appearance-based descriptors have been proposed so far, together with ad hoc similarity measures, mostly aimed at improving ranking quality. We address instead the issue of the processing time required to compute the similarity values, and propose a multi-stage ranking approach to attain a trade-off with ranking quality, for any given descriptor. We give a preliminary evaluation of our approach on the benchmark VIPeR data set, using different state-of-the-art descriptors.
Intelligent video-surveillance (IVS) is currently an active research field in computer vision and... more Intelligent video-surveillance (IVS) is currently an active research field in computer vision and machine learning and provides useful tools for surveillance operators and forensic video investigators. Person re-identification (PReID) is one of the most critical problems in IVS, and it consists of recognizing whether or not an individual has already been observed over a camera in a network. Solutions to PReID have myriad applications including retrieval of video-sequences showing an individual of interest or even pedestrian tracking over multiple camera views. Different techniques have been proposed to increase the performance of PReID in the literature, and more recently researchers utilized deep neural networks (DNNs) given their compelling performance on similar vision problems and fast execution at test time. Given the importance and wide range of applications of re-identification solutions, our objective herein is to discuss the work carried out in the area and come up with a s...
Intelligent video-surveillance is currently an active research field in computer vision and machi... more Intelligent video-surveillance is currently an active research field in computer vision and machine learning techniques. It provides useful tools for surveillance operators and forensic video investigators. Person re-identification (PReID) is one among these tools. It consists of recognizing whether an individual has already been observed over a camera in a network or not. This tool can also be employed in various possible applications such as off-line retrieval of all the video-sequences showing an individual of interest whose image is given a query, and online pedestrian tracking over multiple camera views. To this aim, many techniques have been proposed to increase the performance of PReID. Among the systems, many researchers utilized deep neural networks (DNNs) because of their better performance and fast execution at test time. Our objective is to provide for future researchers the work being done on PReID to date. Therefore, we summarized state-of-the-art DNN models being used...
Uploads
Papers