The success of fine-grained visual categorization (FGVC) extremely relies on the modeling of appearance and interactions of various semantic parts. This makes FGVC very challenging because: (i) part annotation and detection require expert guidance and are very expensive; (ii) parts are of different sizes; and (iii) the part interactions are complex and of higher-order. To address these issues, we propose an end-to-end framework based on higherorder integration of hierarchical convolutional activations for FGVC. By treating the convolutional activations as local descriptors, hierarchical convolutional activations can serve as a representation of local parts from different scales. A polynomial kernel based predictor is proposed to capture higher-order statistics of convolutional activations for modeling part interaction. To model inter-layer part interactions, we extend polynomial predictor to integrate hierarchical activations via kernel fusion. Our work also provides a new perspective for combining convolutional activations from multiple layers. While hypercolumns simply concatenate maps from different layers, and holistically-nested network uses weighted fusion to combine side-outputs, our approach exploits higher-order intra-layer and inter-layer relations for better integration of hierarchical convolutional features. The proposed framework yields more discriminative representation and achieves competitive results on the widely used FGVC datasets.
{"title":"Higher-Order Integration of Hierarchical Convolutional Activations for Fine-Grained Visual Categorization","authors":"Sijia Cai, W. Zuo, Lei Zhang","doi":"10.1109/ICCV.2017.63","DOIUrl":"https://doi.org/10.1109/ICCV.2017.63","url":null,"abstract":"The success of fine-grained visual categorization (FGVC) extremely relies on the modeling of appearance and interactions of various semantic parts. This makes FGVC very challenging because: (i) part annotation and detection require expert guidance and are very expensive; (ii) parts are of different sizes; and (iii) the part interactions are complex and of higher-order. To address these issues, we propose an end-to-end framework based on higherorder integration of hierarchical convolutional activations for FGVC. By treating the convolutional activations as local descriptors, hierarchical convolutional activations can serve as a representation of local parts from different scales. A polynomial kernel based predictor is proposed to capture higher-order statistics of convolutional activations for modeling part interaction. To model inter-layer part interactions, we extend polynomial predictor to integrate hierarchical activations via kernel fusion. Our work also provides a new perspective for combining convolutional activations from multiple layers. While hypercolumns simply concatenate maps from different layers, and holistically-nested network uses weighted fusion to combine side-outputs, our approach exploits higher-order intra-layer and inter-layer relations for better integration of hierarchical convolutional features. The proposed framework yields more discriminative representation and achieves competitive results on the widely used FGVC datasets.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"25 1","pages":"511-520"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91078721","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}
Yousef Atoum, Joseph Roth, Michael Bliss, Wende Zhang, Xiaoming Liu
This paper presents an automated monocular-camera-based computer vision system for autonomous self-backing-up a vehicle towards a trailer, by continuously estimating the 3D trailer coupler position and feeding it to the vehicle control system, until the alignment of the tow hitch with the trailers coupler. This system is made possible through our proposed distance-driven Multiplexer-CNN method, which selects the most suitable CNN using the estimated coupler-to-vehicle distance. The input of the multiplexer is a group made of a CNN detector, trackers, and 3D localizer. In the CNN detector, we propose a novel algorithm to provide a presence confidence score with each detection. The score reflects the existence of the target object in a region, as well as how accurate is the 2D target detection. We demonstrate the accuracy and efficiency of the system on a large trailer database. Our system achieves an estimation error of 1.4 cm when the ball reaches the coupler, while running at 18.9 FPS on a regular PC.
{"title":"Monocular Video-Based Trailer Coupler Detection Using Multiplexer Convolutional Neural Network","authors":"Yousef Atoum, Joseph Roth, Michael Bliss, Wende Zhang, Xiaoming Liu","doi":"10.1109/ICCV.2017.584","DOIUrl":"https://doi.org/10.1109/ICCV.2017.584","url":null,"abstract":"This paper presents an automated monocular-camera-based computer vision system for autonomous self-backing-up a vehicle towards a trailer, by continuously estimating the 3D trailer coupler position and feeding it to the vehicle control system, until the alignment of the tow hitch with the trailers coupler. This system is made possible through our proposed distance-driven Multiplexer-CNN method, which selects the most suitable CNN using the estimated coupler-to-vehicle distance. The input of the multiplexer is a group made of a CNN detector, trackers, and 3D localizer. In the CNN detector, we propose a novel algorithm to provide a presence confidence score with each detection. The score reflects the existence of the target object in a region, as well as how accurate is the 2D target detection. We demonstrate the accuracy and efficiency of the system on a large trailer database. Our system achieves an estimation error of 1.4 cm when the ball reaches the coupler, while running at 18.9 FPS on a regular PC.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"7 1","pages":"5478-5486"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81858465","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}
Alessandro Penna, Sadegh Mohammadi, N. Jojic, Vittorio Murino
A popular approach to training classifiers of new image classes is to use lower levels of a pre-trained feed-forward neural network and retrain only the top. Thus, most layers simply serve as highly nonlinear feature extractors. While these features were found useful for classifying a variety of scenes and objects, previous work also demonstrated unusual levels of sensitivity to the input especially for images which are veering too far away from the training distribution. This can lead to surprising results as an imperceptible change in an image can be enough to completely change the predicted class. This occurs in particular in applications involving personal data, typically acquired with wearable cameras (e.g., visual lifelogs), where the problem is also made more complex by the dearth of new labeled training data that make supervised learning with deep models difficult. To alleviate these problems, in this paper we propose a new generative model that captures the feature distribution in new data. Its latent space then becomes more representative of the new data, while still retaining the generalization properties. In particular, we use constrained Markov walks over a counting grid for modeling image sequences, which not only yield good latent representations, but allow for excellent classification with only a handful of labeled training examples of the new scenes or objects, a scenario typical in lifelogging applications.
{"title":"Summarization and Classification of Wearable Camera Streams by Learning the Distributions over Deep Features of Out-of-Sample Image Sequences","authors":"Alessandro Penna, Sadegh Mohammadi, N. Jojic, Vittorio Murino","doi":"10.1109/ICCV.2017.464","DOIUrl":"https://doi.org/10.1109/ICCV.2017.464","url":null,"abstract":"A popular approach to training classifiers of new image classes is to use lower levels of a pre-trained feed-forward neural network and retrain only the top. Thus, most layers simply serve as highly nonlinear feature extractors. While these features were found useful for classifying a variety of scenes and objects, previous work also demonstrated unusual levels of sensitivity to the input especially for images which are veering too far away from the training distribution. This can lead to surprising results as an imperceptible change in an image can be enough to completely change the predicted class. This occurs in particular in applications involving personal data, typically acquired with wearable cameras (e.g., visual lifelogs), where the problem is also made more complex by the dearth of new labeled training data that make supervised learning with deep models difficult. To alleviate these problems, in this paper we propose a new generative model that captures the feature distribution in new data. Its latent space then becomes more representative of the new data, while still retaining the generalization properties. In particular, we use constrained Markov walks over a counting grid for modeling image sequences, which not only yield good latent representations, but allow for excellent classification with only a handful of labeled training examples of the new scenes or objects, a scenario typical in lifelogging applications.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"14 1","pages":"4336-4344"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81916672","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}
To compress large datasets of high-dimensional descriptors, modern quantization schemes learn multiple codebooks and then represent individual descriptors as combinations of codewords. Once the codebooks are learned, these schemes encode descriptors independently. In contrast to that, we present a new coding scheme that arranges dataset descriptors into a set of arborescence graphs, and then encodes non-root descriptors by quantizing their displacements with respect to their parent nodes. By optimizing the structure of arborescences, our coding scheme can decrease the quantization error considerably, while incurring only minimal overhead on the memory footprint and the speed of nearest neighbor search in the compressed dataset compared to the independent quantization. The advantage of the proposed scheme is demonstrated in a series of experiments with datasets of SIFT and deep descriptors.
{"title":"AnnArbor: Approximate Nearest Neighbors Using Arborescence Coding","authors":"Artem Babenko, V. Lempitsky","doi":"10.1109/ICCV.2017.523","DOIUrl":"https://doi.org/10.1109/ICCV.2017.523","url":null,"abstract":"To compress large datasets of high-dimensional descriptors, modern quantization schemes learn multiple codebooks and then represent individual descriptors as combinations of codewords. Once the codebooks are learned, these schemes encode descriptors independently. In contrast to that, we present a new coding scheme that arranges dataset descriptors into a set of arborescence graphs, and then encodes non-root descriptors by quantizing their displacements with respect to their parent nodes. By optimizing the structure of arborescences, our coding scheme can decrease the quantization error considerably, while incurring only minimal overhead on the memory footprint and the speed of nearest neighbor search in the compressed dataset compared to the independent quantization. The advantage of the proposed scheme is demonstrated in a series of experiments with datasets of SIFT and deep descriptors.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"121 1","pages":"4895-4903"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76689321","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}
Detecting pedestrians that are partially occluded remains a challenging problem due to variations and uncertainties of partial occlusion patterns. Following a commonly used framework of handling partial occlusions by part detection, we propose a multi-label learning approach to jointly learn part detectors to capture partial occlusion patterns. The part detectors share a set of decision trees via boosting to exploit part correlations and also reduce the computational cost of applying these part detectors. The learned decision trees capture the overall distribution of all the parts. When used as a pedestrian detector individually, our part detectors learned jointly show better performance than their counterparts learned separately in different occlusion situations. The learned part detectors can be further integrated to better detect partially occluded pedestrians. Experiments on the Caltech dataset show state-of-the-art performance of our approach for detecting heavily occluded pedestrians.
{"title":"Multi-label Learning of Part Detectors for Heavily Occluded Pedestrian Detection","authors":"Chunluan Zhou, Junsong Yuan","doi":"10.1109/ICCV.2017.377","DOIUrl":"https://doi.org/10.1109/ICCV.2017.377","url":null,"abstract":"Detecting pedestrians that are partially occluded remains a challenging problem due to variations and uncertainties of partial occlusion patterns. Following a commonly used framework of handling partial occlusions by part detection, we propose a multi-label learning approach to jointly learn part detectors to capture partial occlusion patterns. The part detectors share a set of decision trees via boosting to exploit part correlations and also reduce the computational cost of applying these part detectors. The learned decision trees capture the overall distribution of all the parts. When used as a pedestrian detector individually, our part detectors learned jointly show better performance than their counterparts learned separately in different occlusion situations. The learned part detectors can be further integrated to better detect partially occluded pedestrians. Experiments on the Caltech dataset show state-of-the-art performance of our approach for detecting heavily occluded pedestrians.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"177 1","pages":"3506-3515"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77369814","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}
Transferring objects from one place to another place is a common task performed by human in daily life. During this process, it is usually intuitive for humans to choose an object as a proper container and to use an efficient pose to carry objects; yet, it is non-trivial for current computer vision and machine learning algorithms. In this paper, we propose an approach to jointly infer container and human pose for transferring objects by minimizing the costs associated both object and pose candidates. Our approach predicts which object to choose as a container while reasoning about how humans interact with physical surroundings to accomplish the task of transferring objects given visual input. In the learning phase, the presented method learns how humans make rational choices of containers and poses for transferring different objects, as well as the physical quantities required by the transfer task (e.g., compatibility between container and containee, energy cost of carrying pose) via a structured learning approach. In the inference phase, given a scanned 3D scene with different object candidates and a dictionary of human poses, our approach infers the best object as a container together with human pose for transferring a given object.
{"title":"Transferring Objects: Joint Inference of Container and Human Pose","authors":"Hanqing Wang, Wei Liang, L. Yu","doi":"10.1109/ICCV.2017.319","DOIUrl":"https://doi.org/10.1109/ICCV.2017.319","url":null,"abstract":"Transferring objects from one place to another place is a common task performed by human in daily life. During this process, it is usually intuitive for humans to choose an object as a proper container and to use an efficient pose to carry objects; yet, it is non-trivial for current computer vision and machine learning algorithms. In this paper, we propose an approach to jointly infer container and human pose for transferring objects by minimizing the costs associated both object and pose candidates. Our approach predicts which object to choose as a container while reasoning about how humans interact with physical surroundings to accomplish the task of transferring objects given visual input. In the learning phase, the presented method learns how humans make rational choices of containers and poses for transferring different objects, as well as the physical quantities required by the transfer task (e.g., compatibility between container and containee, energy cost of carrying pose) via a structured learning approach. In the inference phase, given a scanned 3D scene with different object candidates and a dictionary of human poses, our approach infers the best object as a container together with human pose for transferring a given object.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"156 1","pages":"2952-2960"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77483028","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}
Zhouxia Wang, Tianshui Chen, Guanbin Li, Ruijia Xu, Liang Lin
This paper proposes a novel deep architecture to address multi-label image recognition, a fundamental and practical task towards general visual understanding. Current solutions for this task usually rely on an extra step of extracting hypothesis regions (i.e., region proposals), resulting in redundant computation and sub-optimal performance. In this work, we achieve the interpretable and contextualized multi-label image classification by developing a recurrent memorized-attention module. This module consists of two alternately performed components: i) a spatial transformer layer to locate attentional regions from the convolutional feature maps in a region-proposal-free way and ii) an LSTM (Long-Short Term Memory) sub-network to sequentially predict semantic labeling scores on the located regions while capturing the global dependencies of these regions. The LSTM also output the parameters for computing the spatial transformer. On large-scale benchmarks of multi-label image classification (e.g., MS-COCO and PASCAL VOC 07), our approach demonstrates superior performances over other existing state-of-the-arts in both accuracy and efficiency.
{"title":"Multi-label Image Recognition by Recurrently Discovering Attentional Regions","authors":"Zhouxia Wang, Tianshui Chen, Guanbin Li, Ruijia Xu, Liang Lin","doi":"10.1109/ICCV.2017.58","DOIUrl":"https://doi.org/10.1109/ICCV.2017.58","url":null,"abstract":"This paper proposes a novel deep architecture to address multi-label image recognition, a fundamental and practical task towards general visual understanding. Current solutions for this task usually rely on an extra step of extracting hypothesis regions (i.e., region proposals), resulting in redundant computation and sub-optimal performance. In this work, we achieve the interpretable and contextualized multi-label image classification by developing a recurrent memorized-attention module. This module consists of two alternately performed components: i) a spatial transformer layer to locate attentional regions from the convolutional feature maps in a region-proposal-free way and ii) an LSTM (Long-Short Term Memory) sub-network to sequentially predict semantic labeling scores on the located regions while capturing the global dependencies of these regions. The LSTM also output the parameters for computing the spatial transformer. On large-scale benchmarks of multi-label image classification (e.g., MS-COCO and PASCAL VOC 07), our approach demonstrates superior performances over other existing state-of-the-arts in both accuracy and efficiency.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"18 1","pages":"464-472"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79276494","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}
M. Denitto, S. Melzi, M. Bicego, U. Castellani, A. Farinelli, Mário A. T. Figueiredo, Yanir Kleiman, M. Ovsjanikov
Region-based correspondence (RBC) is a highly relevant and non-trivial computer vision problem. Given two 3D shapes, RBC seeks segments/regions on these shapes that can be reliably put in correspondence. The problem thus consists both in finding the regions and determining the correspondences between them. This problem statement is similar to that of “biclustering ”, implying that RBC can be cast as a biclustering problem. Here, we exploit this implication by tackling RBC via a novel biclustering approach, called S4B (spatially smooth spike and slab biclustering), which: (i) casts the problem in a probabilistic low-rank matrix factorization perspective; (ii) uses a spike and slab prior to induce sparsity; (iii) is enriched with a spatial smoothness prior, based on geodesic distances, encouraging nearby vertices to belong to the same bicluster. This type of spatial prior cannot be used in classical biclustering techniques. We test the proposed approach on the FAUST dataset, outperforming both state-of-the-art RBC techniques and classical biclustering methods.
{"title":"Region-Based Correspondence Between 3D Shapes via Spatially Smooth Biclustering","authors":"M. Denitto, S. Melzi, M. Bicego, U. Castellani, A. Farinelli, Mário A. T. Figueiredo, Yanir Kleiman, M. Ovsjanikov","doi":"10.1109/ICCV.2017.457","DOIUrl":"https://doi.org/10.1109/ICCV.2017.457","url":null,"abstract":"Region-based correspondence (RBC) is a highly relevant and non-trivial computer vision problem. Given two 3D shapes, RBC seeks segments/regions on these shapes that can be reliably put in correspondence. The problem thus consists both in finding the regions and determining the correspondences between them. This problem statement is similar to that of “biclustering ”, implying that RBC can be cast as a biclustering problem. Here, we exploit this implication by tackling RBC via a novel biclustering approach, called S4B (spatially smooth spike and slab biclustering), which: (i) casts the problem in a probabilistic low-rank matrix factorization perspective; (ii) uses a spike and slab prior to induce sparsity; (iii) is enriched with a spatial smoothness prior, based on geodesic distances, encouraging nearby vertices to belong to the same bicluster. This type of spatial prior cannot be used in classical biclustering techniques. We test the proposed approach on the FAUST dataset, outperforming both state-of-the-art RBC techniques and classical biclustering methods.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"93 1","pages":"4270-4279"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79433023","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}
In this paper, we present a technique that places 3D bounding boxes around objects in an RGB-D scene. Our approach makes best use of the 2D information to quickly reduce the search space in 3D, benefiting from state-of-the-art 2D object detection techniques. We then use the 3D information to orient, place, and score bounding boxes around objects. We independently estimate the orientation for every object, using previous techniques that utilize normal information. Object locations and sizes in 3D are learned using a multilayer perceptron (MLP). In the final step, we refine our detections based on object class relations within a scene. When compared to state-of-the-art detection methods that operate almost entirely in the sparse 3D domain, extensive experiments on the well-known SUN RGB-D dataset [29] show that our proposed method is much faster (4.1s per image) in detecting 3D objects in RGB-D images and performs better (3 mAP higher) than the state-of-the-art method that is 4.7 times slower and comparably to the method that is two orders of magnitude slower. This work hints at the idea that 2D-driven object detection in 3D should be further explored, especially in cases where the 3D input is sparse.
{"title":"2D-Driven 3D Object Detection in RGB-D Images","authors":"Jean Lahoud, Bernard Ghanem","doi":"10.1109/ICCV.2017.495","DOIUrl":"https://doi.org/10.1109/ICCV.2017.495","url":null,"abstract":"In this paper, we present a technique that places 3D bounding boxes around objects in an RGB-D scene. Our approach makes best use of the 2D information to quickly reduce the search space in 3D, benefiting from state-of-the-art 2D object detection techniques. We then use the 3D information to orient, place, and score bounding boxes around objects. We independently estimate the orientation for every object, using previous techniques that utilize normal information. Object locations and sizes in 3D are learned using a multilayer perceptron (MLP). In the final step, we refine our detections based on object class relations within a scene. When compared to state-of-the-art detection methods that operate almost entirely in the sparse 3D domain, extensive experiments on the well-known SUN RGB-D dataset [29] show that our proposed method is much faster (4.1s per image) in detecting 3D objects in RGB-D images and performs better (3 mAP higher) than the state-of-the-art method that is 4.7 times slower and comparably to the method that is two orders of magnitude slower. This work hints at the idea that 2D-driven object detection in 3D should be further explored, especially in cases where the 3D input is sparse.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"12 1","pages":"4632-4640"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73220590","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}
Detecting logo frequency and duration in sports videos provides sponsors an effective way to evaluate their advertising efforts. However, general-purposed object detection methods cannot address all the challenges in sports videos. In this paper, we propose a mutual-enhanced approach that can improve the detection of a logo through the information obtained from other simultaneously occurred logos. In a Fast-RCNN-based framework, we first introduce a homogeneity-enhanced re-ranking method by analyzing the characteristics of homogeneous logos in each frame, including type repetition, color consistency, and mutual exclusion. Different from conventional enhance mechanism that improves the weak proposals with the dominant proposals, our mutual method can also enhance the relatively significant proposals with weak proposals. Mutual enhancement is also included in our frame propagation mechanism that improves logo detection by utilizing the continuity of logos across frames. We use a tennis video dataset and an associated logo collection for detection evaluation. Experiments show that the proposed method outperforms existing methods with a higher accuracy.
{"title":"Mutual Enhancement for Detection of Multiple Logos in Sports Videos","authors":"Yuan Liao, Xiaoqing Lu, Chengcui Zhang, Yongtao Wang, Zhi Tang","doi":"10.1109/ICCV.2017.519","DOIUrl":"https://doi.org/10.1109/ICCV.2017.519","url":null,"abstract":"Detecting logo frequency and duration in sports videos provides sponsors an effective way to evaluate their advertising efforts. However, general-purposed object detection methods cannot address all the challenges in sports videos. In this paper, we propose a mutual-enhanced approach that can improve the detection of a logo through the information obtained from other simultaneously occurred logos. In a Fast-RCNN-based framework, we first introduce a homogeneity-enhanced re-ranking method by analyzing the characteristics of homogeneous logos in each frame, including type repetition, color consistency, and mutual exclusion. Different from conventional enhance mechanism that improves the weak proposals with the dominant proposals, our mutual method can also enhance the relatively significant proposals with weak proposals. Mutual enhancement is also included in our frame propagation mechanism that improves logo detection by utilizing the continuity of logos across frames. We use a tennis video dataset and an associated logo collection for detection evaluation. Experiments show that the proposed method outperforms existing methods with a higher accuracy.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"25 1","pages":"4856-4865"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73657557","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：