Saeid Motiian, Marco Piccirilli, D. Adjeroh, Gianfranco Doretto
We explore the visual recognition problem from a main data view when an auxiliary data view is available during training. This is important because it allows improving the training of visual classifiers when paired additional data is cheaply available, and it improves the recognition from multi-view data when there is a missing view at testing time. The problem is challenging because of the intrinsic asymmetry caused by the missing auxiliary view during testing. We account for such view during training by extending the information bottleneck method, and by combining it with risk minimization. In this way, we establish an information theoretic principle for leaning any type of visual classifier under this particular setting. We use this principle to design a large-margin classifier with an efficient optimization in the primal space. We extensively compare our method with the state-of-the-art on different visual recognition datasets, and with different types of auxiliary data, and show that the proposed framework has a very promising potential.
{"title":"Information Bottleneck Learning Using Privileged Information for Visual Recognition","authors":"Saeid Motiian, Marco Piccirilli, D. Adjeroh, Gianfranco Doretto","doi":"10.1109/CVPR.2016.166","DOIUrl":"https://doi.org/10.1109/CVPR.2016.166","url":null,"abstract":"We explore the visual recognition problem from a main data view when an auxiliary data view is available during training. This is important because it allows improving the training of visual classifiers when paired additional data is cheaply available, and it improves the recognition from multi-view data when there is a missing view at testing time. The problem is challenging because of the intrinsic asymmetry caused by the missing auxiliary view during testing. We account for such view during training by extending the information bottleneck method, and by combining it with risk minimization. In this way, we establish an information theoretic principle for leaning any type of visual classifier under this particular setting. We use this principle to design a large-margin classifier with an efficient optimization in the primal space. We extensively compare our method with the state-of-the-art on different visual recognition datasets, and with different types of auxiliary data, and show that the proposed framework has a very promising potential.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"11 1","pages":"1496-1505"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87573115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. H. Rezatofighi, Anton Milan, Zhen Zhang, Javen Qinfeng Shi, A. Dick, I. Reid
Matching between two sets of objects is typically approached by finding the object pairs that collectively maximize the joint matching score. In this paper, we argue that this single solution does not necessarily lead to the optimal matching accuracy and that general one-to-one assignment problems can be improved by considering multiple hypotheses before computing the final similarity measure. To that end, we propose to utilize the marginal distributions for each entity. Previously, this idea has been neglected mainly because exact marginalization is intractable due to a combinatorial number of all possible matching permutations. Here, we propose a generic approach to efficiently approximate the marginal distributions by exploiting the m-best solutions of the original problem. This approach not only improves the matching solution, but also provides more accurate ranking of the results, because of the extra information included in the marginal distribution. We validate our claim on two distinct objectives: (i) person re-identification and temporal matching modeled as an integer linear program, and (ii) feature point matching using a quadratic cost function. Our experiments confirm that marginalization indeed leads to superior performance compared to the single (nearly) optimal solution, yielding state-of-the-art results in both applications on standard benchmarks.
{"title":"Joint Probabilistic Matching Using m-Best Solutions","authors":"S. H. Rezatofighi, Anton Milan, Zhen Zhang, Javen Qinfeng Shi, A. Dick, I. Reid","doi":"10.1109/CVPR.2016.22","DOIUrl":"https://doi.org/10.1109/CVPR.2016.22","url":null,"abstract":"Matching between two sets of objects is typically approached by finding the object pairs that collectively maximize the joint matching score. In this paper, we argue that this single solution does not necessarily lead to the optimal matching accuracy and that general one-to-one assignment problems can be improved by considering multiple hypotheses before computing the final similarity measure. To that end, we propose to utilize the marginal distributions for each entity. Previously, this idea has been neglected mainly because exact marginalization is intractable due to a combinatorial number of all possible matching permutations. Here, we propose a generic approach to efficiently approximate the marginal distributions by exploiting the m-best solutions of the original problem. This approach not only improves the matching solution, but also provides more accurate ranking of the results, because of the extra information included in the marginal distribution. We validate our claim on two distinct objectives: (i) person re-identification and temporal matching modeled as an integer linear program, and (ii) feature point matching using a quadratic cost function. Our experiments confirm that marginalization indeed leads to superior performance compared to the single (nearly) optimal solution, yielding state-of-the-art results in both applications on standard benchmarks.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"88 1","pages":"136-145"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88965242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
V. Sharmanska, D. Hernández-Lobato, José Miguel Hernández-Lobato, Novi Quadrianto
Imagine we show an image to a person and ask her/him to decide whether the scene in the image is warm or not warm, and whether it is easy or not to spot a squirrel in the image. For exactly the same image, the answers to those questions are likely to differ from person to person. This is because the task is inherently ambiguous. Such an ambiguous, therefore challenging, task is pushing the boundary of computer vision in showing what can and can not be learned from visual data. Crowdsourcing has been invaluable for collecting annotations. This is particularly so for a task that goes beyond a clear-cut dichotomy as multiple human judgments per image are needed to reach a consensus. This paper makes conceptual and technical contributions. On the conceptual side, we define disagreements among annotators as privileged information about the data instance. On the technical side, we propose a framework to incorporate annotation disagreements into the classifiers. The proposed framework is simple, relatively fast, and outperforms classifiers that do not take into account the disagreements, especially if tested on high confidence annotations.
{"title":"Ambiguity Helps: Classification with Disagreements in Crowdsourced Annotations","authors":"V. Sharmanska, D. Hernández-Lobato, José Miguel Hernández-Lobato, Novi Quadrianto","doi":"10.1109/CVPR.2016.241","DOIUrl":"https://doi.org/10.1109/CVPR.2016.241","url":null,"abstract":"Imagine we show an image to a person and ask her/him to decide whether the scene in the image is warm or not warm, and whether it is easy or not to spot a squirrel in the image. For exactly the same image, the answers to those questions are likely to differ from person to person. This is because the task is inherently ambiguous. Such an ambiguous, therefore challenging, task is pushing the boundary of computer vision in showing what can and can not be learned from visual data. Crowdsourcing has been invaluable for collecting annotations. This is particularly so for a task that goes beyond a clear-cut dichotomy as multiple human judgments per image are needed to reach a consensus. This paper makes conceptual and technical contributions. On the conceptual side, we define disagreements among annotators as privileged information about the data instance. On the technical side, we propose a framework to incorporate annotation disagreements into the classifiers. The proposed framework is simple, relatively fast, and outperforms classifiers that do not take into account the disagreements, especially if tested on high confidence annotations.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"52 1","pages":"2194-2202"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88977735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present a fully automatic approach to detect and segment fence-like occluders from a video clip. Unlike previous approaches that usually assume either static scenes or cameras, our method is capable of handling both dynamic scenes and moving cameras. Under a bottom-up framework, it first clusters pixels into coherent groups using color and motion features. These pixel groups are then analyzed in a fully connected graph, and labeled as either fence or non-fence using graph-cut optimization. Finally, we solve a dense Conditional Random Filed (CRF) constructed from multiple frames to enhance both spatial accuracy and temporal coherence of the segmentation. Once segmented, one can use existing hole-filling methods to generate a fencefree output. Extensive evaluation suggests that our method outperforms previous automatic and interactive approaches on complex examples captured by mobile devices.
{"title":"Automatic Fence Segmentation in Videos of Dynamic Scenes","authors":"Renjiao Yi, Jue Wang, P. Tan","doi":"10.1109/CVPR.2016.83","DOIUrl":"https://doi.org/10.1109/CVPR.2016.83","url":null,"abstract":"We present a fully automatic approach to detect and segment fence-like occluders from a video clip. Unlike previous approaches that usually assume either static scenes or cameras, our method is capable of handling both dynamic scenes and moving cameras. Under a bottom-up framework, it first clusters pixels into coherent groups using color and motion features. These pixel groups are then analyzed in a fully connected graph, and labeled as either fence or non-fence using graph-cut optimization. Finally, we solve a dense Conditional Random Filed (CRF) constructed from multiple frames to enhance both spatial accuracy and temporal coherence of the segmentation. Once segmented, one can use existing hole-filling methods to generate a fencefree output. Extensive evaluation suggests that our method outperforms previous automatic and interactive approaches on complex examples captured by mobile devices.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"120 1","pages":"705-713"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89127299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
K. Kulkarni, Suhas Lohit, P. Turaga, Ronan Kerviche, A. Ashok
The goal of this paper is to present a non-iterative and more importantly an extremely fast algorithm to reconstruct images from compressively sensed (CS) random measurements. To this end, we propose a novel convolutional neural network (CNN) architecture which takes in CS measurements of an image as input and outputs an intermediate reconstruction. We call this network, ReconNet. The intermediate reconstruction is fed into an off-the-shelf denoiser to obtain the final reconstructed image. On a standard dataset of images we show significant improvements in reconstruction results (both in terms of PSNR and time complexity) over state-of-the-art iterative CS reconstruction algorithms at various measurement rates. Further, through qualitative experiments on real data collected using our block single pixel camera (SPC), we show that our network is highly robust to sensor noise and can recover visually better quality images than competitive algorithms at extremely low sensing rates of 0.1 and 0.04. To demonstrate that our algorithm can recover semantically informative images even at a low measurement rate of 0.01, we present a very robust proof of concept real-time visual tracking application.
{"title":"ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Measurements","authors":"K. Kulkarni, Suhas Lohit, P. Turaga, Ronan Kerviche, A. Ashok","doi":"10.1109/CVPR.2016.55","DOIUrl":"https://doi.org/10.1109/CVPR.2016.55","url":null,"abstract":"The goal of this paper is to present a non-iterative and more importantly an extremely fast algorithm to reconstruct images from compressively sensed (CS) random measurements. To this end, we propose a novel convolutional neural network (CNN) architecture which takes in CS measurements of an image as input and outputs an intermediate reconstruction. We call this network, ReconNet. The intermediate reconstruction is fed into an off-the-shelf denoiser to obtain the final reconstructed image. On a standard dataset of images we show significant improvements in reconstruction results (both in terms of PSNR and time complexity) over state-of-the-art iterative CS reconstruction algorithms at various measurement rates. Further, through qualitative experiments on real data collected using our block single pixel camera (SPC), we show that our network is highly robust to sensor noise and can recover visually better quality images than competitive algorithms at extremely low sensing rates of 0.1 and 0.04. To demonstrate that our algorithm can recover semantically informative images even at a low measurement rate of 0.01, we present a very robust proof of concept real-time visual tracking application.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"16 1","pages":"449-458"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79655287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present a practical solution for generating 360° stereo panoramic videos using a single camera. Current approaches either use a moving camera that captures multiple images of a scene, which are then stitched together to form the final panorama, or use multiple cameras that are synchronized. A moving camera limits the solution to static scenes, while multi-camera solutions require dedicated calibrated setups. Our approach improves upon the existing solutions in two significant ways: It solves the problem using a single camera, thus minimizing the calibration problem and providing us the ability to convert any digital camera into a panoramic stereo capture device. It captures all the light rays required for stereo panoramas in a single frame using a compact custom designed mirror, thus making the design practical to manufacture and easier to use. We analyze several properties of the design as well as present panoramic stereo and depth estimation results.
{"title":"Panoramic Stereo Videos with a Single Camera","authors":"R. Aggarwal, Amrisha Vohra, A. Namboodiri","doi":"10.1109/CVPR.2016.408","DOIUrl":"https://doi.org/10.1109/CVPR.2016.408","url":null,"abstract":"We present a practical solution for generating 360° stereo panoramic videos using a single camera. Current approaches either use a moving camera that captures multiple images of a scene, which are then stitched together to form the final panorama, or use multiple cameras that are synchronized. A moving camera limits the solution to static scenes, while multi-camera solutions require dedicated calibrated setups. Our approach improves upon the existing solutions in two significant ways: It solves the problem using a single camera, thus minimizing the calibration problem and providing us the ability to convert any digital camera into a panoramic stereo capture device. It captures all the light rays required for stereo panoramas in a single frame using a compact custom designed mirror, thus making the design practical to manufacture and easier to use. We analyze several properties of the design as well as present panoramic stereo and depth estimation results.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"21 1","pages":"3755-3763"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89448346","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Multicamera rigs are used in a large number of 3D Vision applications, such as 3D modeling, motion capture or telepresence and a robust calibration is of utmost importance in order to achieve a high accuracy results. In many practical configurations the cameras in a rig are arranged in such a way, that they can observe each other, in other words a number of epipoles correspond to the real image points. In this paper we propose a solution for the automatic recovery of the external calibration of a multicamera system by enforcing only simple geometrical constraints, arising from the epipole visibility, without using any calibration object, such as checkerboards, laser pointers or similar. Additionally, we introduce an extension of the method that handles the case of epipoles being visible in the reflection of a planar mirror, which makes the algorithm suitable for the calibration of any multicamera system, irrespective of the number of cameras and their actual mutual visibility, and furthermore we remark that it requires only one or a few images per camera and therefore features a high speed and usability. We produce an evidence of the algorithm effectiveness by presenting a wide set of tests performed on synthetic as well as real datasets and we compare the results with those obtained using a traditional LED-based algorithm. The real datasets have been captured using a multicamera Virtual Reality (VR) rig and a spherical dome configuration for 3D reconstruction.
{"title":"Multicamera Calibration from Visible and Mirrored Epipoles","authors":"Andrey Bushnevskiy, L. Sorgi, B. Rosenhahn","doi":"10.1109/CVPR.2016.367","DOIUrl":"https://doi.org/10.1109/CVPR.2016.367","url":null,"abstract":"Multicamera rigs are used in a large number of 3D Vision applications, such as 3D modeling, motion capture or telepresence and a robust calibration is of utmost importance in order to achieve a high accuracy results. In many practical configurations the cameras in a rig are arranged in such a way, that they can observe each other, in other words a number of epipoles correspond to the real image points. In this paper we propose a solution for the automatic recovery of the external calibration of a multicamera system by enforcing only simple geometrical constraints, arising from the epipole visibility, without using any calibration object, such as checkerboards, laser pointers or similar. Additionally, we introduce an extension of the method that handles the case of epipoles being visible in the reflection of a planar mirror, which makes the algorithm suitable for the calibration of any multicamera system, irrespective of the number of cameras and their actual mutual visibility, and furthermore we remark that it requires only one or a few images per camera and therefore features a high speed and usability. We produce an evidence of the algorithm effectiveness by presenting a wide set of tests performed on synthetic as well as real datasets and we compare the results with those obtained using a traditional LED-based algorithm. The real datasets have been captured using a multicamera Virtual Reality (VR) rig and a spherical dome configuration for 3D reconstruction.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"8 Suppl 10 1","pages":"3373-3381"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89672979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bharat Singh, Tim K. Marks, Michael J. Jones, Oncel Tuzel, Ming Shao
We present a multi-stream bi-directional recurrent neural network for fine-grained action detection. Recently, twostream convolutional neural networks (CNNs) trained on stacked optical flow and image frames have been successful for action recognition in videos. Our system uses a tracking algorithm to locate a bounding box around the person, which provides a frame of reference for appearance and motion and also suppresses background noise that is not within the bounding box. We train two additional streams on motion and appearance cropped to the tracked bounding box, along with full-frame streams. Our motion streams use pixel trajectories of a frame as raw features, in which the displacement values corresponding to a moving scene point are at the same spatial position across several frames. To model long-term temporal dynamics within and between actions, the multi-stream CNN is followed by a bi-directional Long Short-Term Memory (LSTM) layer. We show that our bi-directional LSTM network utilizes about 8 seconds of the video sequence to predict an action label. We test on two action detection datasets: the MPII Cooking 2 Dataset, and a new MERL Shopping Dataset that we introduce and make available to the community with this paper. The results demonstrate that our method significantly outperforms state-of-the-art action detection methods on both datasets.
{"title":"A Multi-stream Bi-directional Recurrent Neural Network for Fine-Grained Action Detection","authors":"Bharat Singh, Tim K. Marks, Michael J. Jones, Oncel Tuzel, Ming Shao","doi":"10.1109/CVPR.2016.216","DOIUrl":"https://doi.org/10.1109/CVPR.2016.216","url":null,"abstract":"We present a multi-stream bi-directional recurrent neural network for fine-grained action detection. Recently, twostream convolutional neural networks (CNNs) trained on stacked optical flow and image frames have been successful for action recognition in videos. Our system uses a tracking algorithm to locate a bounding box around the person, which provides a frame of reference for appearance and motion and also suppresses background noise that is not within the bounding box. We train two additional streams on motion and appearance cropped to the tracked bounding box, along with full-frame streams. Our motion streams use pixel trajectories of a frame as raw features, in which the displacement values corresponding to a moving scene point are at the same spatial position across several frames. To model long-term temporal dynamics within and between actions, the multi-stream CNN is followed by a bi-directional Long Short-Term Memory (LSTM) layer. We show that our bi-directional LSTM network utilizes about 8 seconds of the video sequence to predict an action label. We test on two action detection datasets: the MPII Cooking 2 Dataset, and a new MERL Shopping Dataset that we introduce and make available to the community with this paper. The results demonstrate that our method significantly outperforms state-of-the-art action detection methods on both datasets.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"20 1","pages":"1961-1970"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90428901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhe Zhu, Dun Liang, Song-Hai Zhang, Xiaolei Huang, Baoli Li, Shimin Hu
Although promising results have been achieved in the areas of traffic-sign detection and classification, few works have provided simultaneous solutions to these two tasks for realistic real world images. We make two contributions to this problem. Firstly, we have created a large traffic-sign benchmark from 100000 Tencent Street View panoramas, going beyond previous benchmarks. It provides 100000 images containing 30000 traffic-sign instances. These images cover large variations in illuminance and weather conditions. Each traffic-sign in the benchmark is annotated with a class label, its bounding box and pixel mask. We call this benchmark Tsinghua-Tencent 100K. Secondly, we demonstrate how a robust end-to-end convolutional neural network (CNN) can simultaneously detect and classify trafficsigns. Most previous CNN image processing solutions target objects that occupy a large proportion of an image, and such networks do not work well for target objects occupying only a small fraction of an image like the traffic-signs here. Experimental results show the robustness of our network and its superiority to alternatives. The benchmark, source code and the CNN model introduced in this paper is publicly available1.
{"title":"Traffic-Sign Detection and Classification in the Wild","authors":"Zhe Zhu, Dun Liang, Song-Hai Zhang, Xiaolei Huang, Baoli Li, Shimin Hu","doi":"10.1109/CVPR.2016.232","DOIUrl":"https://doi.org/10.1109/CVPR.2016.232","url":null,"abstract":"Although promising results have been achieved in the areas of traffic-sign detection and classification, few works have provided simultaneous solutions to these two tasks for realistic real world images. We make two contributions to this problem. Firstly, we have created a large traffic-sign benchmark from 100000 Tencent Street View panoramas, going beyond previous benchmarks. It provides 100000 images containing 30000 traffic-sign instances. These images cover large variations in illuminance and weather conditions. Each traffic-sign in the benchmark is annotated with a class label, its bounding box and pixel mask. We call this benchmark Tsinghua-Tencent 100K. Secondly, we demonstrate how a robust end-to-end convolutional neural network (CNN) can simultaneously detect and classify trafficsigns. Most previous CNN image processing solutions target objects that occupy a large proportion of an image, and such networks do not work well for target objects occupying only a small fraction of an image like the traffic-signs here. Experimental results show the robustness of our network and its superiority to alternatives. The benchmark, source code and the CNN model introduced in this paper is publicly available1.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"89 1","pages":"2110-2118"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75223118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Given an image of a handwritten word, a CNN is employed to estimate its n-gram frequency profile, which is the set of n-grams contained in the word. Frequencies for unigrams, bigrams and trigrams are estimated for the entire word and for parts of it. Canonical Correlation Analysis is then used to match the estimated profile to the true profiles of all words in a large dictionary. The CNN that is used employs several novelties such as the use of multiple fully connected branches. Applied to all commonly used handwriting recognition benchmarks, our method outperforms, by a very large margin, all existing methods.
{"title":"CNN-N-Gram for HandwritingWord Recognition","authors":"Arik Poznanski, Lior Wolf","doi":"10.1109/CVPR.2016.253","DOIUrl":"https://doi.org/10.1109/CVPR.2016.253","url":null,"abstract":"Given an image of a handwritten word, a CNN is employed to estimate its n-gram frequency profile, which is the set of n-grams contained in the word. Frequencies for unigrams, bigrams and trigrams are estimated for the entire word and for parts of it. Canonical Correlation Analysis is then used to match the estimated profile to the true profiles of all words in a large dictionary. The CNN that is used employs several novelties such as the use of multiple fully connected branches. Applied to all commonly used handwriting recognition benchmarks, our method outperforms, by a very large margin, all existing methods.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"24 1","pages":"2305-2314"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75329797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：