Motion blur and rolling shutter deformations both inhibit visual motion registration, whether it be due to a moving sensor or a moving target. Whilst both deformations exist simultaneously, no models have been proposed to handle them together. Furthermore, neither deformation has been considered previously in the context of monocular full-image 6 degrees of freedom registration or RGB-D structure and motion. As will be shown, rolling shutter deformation is observed when a camera moves faster than a single pixel in parallax between subsequent scan-lines. Blur is a function of the pixel exposure time and the motion vector. In this paper a complete dense 3D registration model will be derived to account for both motion blur and rolling shutter deformations simultaneously. Various approaches will be compared with respect to ground truth and live real-time performance will be demonstrated for complex scenarios where both blur and shutter deformations are dominant.
{"title":"A Unified Rolling Shutter and Motion Blur Model for 3D Visual Registration","authors":"Maxime Meilland, T. Drummond, Andrew I. Comport","doi":"10.1109/ICCV.2013.252","DOIUrl":"https://doi.org/10.1109/ICCV.2013.252","url":null,"abstract":"Motion blur and rolling shutter deformations both inhibit visual motion registration, whether it be due to a moving sensor or a moving target. Whilst both deformations exist simultaneously, no models have been proposed to handle them together. Furthermore, neither deformation has been considered previously in the context of monocular full-image 6 degrees of freedom registration or RGB-D structure and motion. As will be shown, rolling shutter deformation is observed when a camera moves faster than a single pixel in parallax between subsequent scan-lines. Blur is a function of the pixel exposure time and the motion vector. In this paper a complete dense 3D registration model will be derived to account for both motion blur and rolling shutter deformations simultaneously. Various approaches will be compared with respect to ground truth and live real-time performance will be demonstrated for complex scenarios where both blur and shutter deformations are dominant.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"60 1","pages":"2016-2023"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84470001","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}
Zhenyang Li, E. Gavves, K. V. D. Sande, Cees G. M. Snoek, A. Smeulders
In this paper we aim for segmentation and classification of objects. We propose codemaps that are a joint formulation of the classification score and the local neighborhood it belongs to in the image. We obtain the codemap by reordering the encoding, pooling and classification steps over lattice elements. Other than existing linear decompositions who emphasize only the efficiency benefits for localized search, we make three novel contributions. As a preliminary, we provide a theoretical generalization of the sufficient mathematical conditions under which image encodings and classification becomes locally decomposable. As first novelty we introduce l2 normalization for arbitrarily shaped image regions, which is fast enough for semantic segmentation using our Fisher codemaps. Second, using the same lattice across images, we propose kernel pooling which embeds nonlinearities into codemaps for object classification by explicit or approximate feature mappings. Results demonstrate that l2 normalized Fisher codemaps improve the state-of-the-art in semantic segmentation for PASCAL VOC. For object classification the addition of nonlinearities brings us on par with the state-of-the-art, but is 3x faster. Because of the codemaps' inherent efficiency, we can reach significant speed-ups for localized search as well. We exploit the efficiency gain for our third novelty: object segment retrieval using a single query image only.
{"title":"Codemaps - Segment, Classify and Search Objects Locally","authors":"Zhenyang Li, E. Gavves, K. V. D. Sande, Cees G. M. Snoek, A. Smeulders","doi":"10.1109/ICCV.2013.454","DOIUrl":"https://doi.org/10.1109/ICCV.2013.454","url":null,"abstract":"In this paper we aim for segmentation and classification of objects. We propose codemaps that are a joint formulation of the classification score and the local neighborhood it belongs to in the image. We obtain the codemap by reordering the encoding, pooling and classification steps over lattice elements. Other than existing linear decompositions who emphasize only the efficiency benefits for localized search, we make three novel contributions. As a preliminary, we provide a theoretical generalization of the sufficient mathematical conditions under which image encodings and classification becomes locally decomposable. As first novelty we introduce l2 normalization for arbitrarily shaped image regions, which is fast enough for semantic segmentation using our Fisher codemaps. Second, using the same lattice across images, we propose kernel pooling which embeds nonlinearities into codemaps for object classification by explicit or approximate feature mappings. Results demonstrate that l2 normalized Fisher codemaps improve the state-of-the-art in semantic segmentation for PASCAL VOC. For object classification the addition of nonlinearities brings us on par with the state-of-the-art, but is 3x faster. Because of the codemaps' inherent efficiency, we can reach significant speed-ups for localized search as well. We exploit the efficiency gain for our third novelty: object segment retrieval using a single query image only.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"148 1","pages":"2136-2143"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85145528","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 work we propose a novel method to include a connectivity prior into image segmentation that is based on a binary labeling of a directed graph, in this case a geodesic shortest path tree. Specifically we make two contributions: First, we construct a geodesic shortest path tree with a distance measure that is related to the image data and the bending energy of each path in the tree. Second, we include a connectivity prior in our segmentation model, that allows to segment not only a single elongated structure, but instead a whole connected branching tree. Because both our segmentation model and the connectivity constraint are convex a global optimal solution can be found. To this end, we generalize a recent primal-dual algorithm for continuous convex optimization to an arbitrary graph structure. To validate our method we present results on data from medical imaging in angiography and retinal blood vessel segmentation.
{"title":"Tree Shape Priors with Connectivity Constraints Using Convex Relaxation on General Graphs","authors":"Jan Stühmer, P. Schröder, D. Cremers","doi":"10.1109/ICCV.2013.290","DOIUrl":"https://doi.org/10.1109/ICCV.2013.290","url":null,"abstract":"In this work we propose a novel method to include a connectivity prior into image segmentation that is based on a binary labeling of a directed graph, in this case a geodesic shortest path tree. Specifically we make two contributions: First, we construct a geodesic shortest path tree with a distance measure that is related to the image data and the bending energy of each path in the tree. Second, we include a connectivity prior in our segmentation model, that allows to segment not only a single elongated structure, but instead a whole connected branching tree. Because both our segmentation model and the connectivity constraint are convex a global optimal solution can be found. To this end, we generalize a recent primal-dual algorithm for continuous convex optimization to an arbitrary graph structure. To validate our method we present results on data from medical imaging in angiography and retinal blood vessel segmentation.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"44 1","pages":"2336-2343"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80845859","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}
Among image segmentation algorithms there are two major groups: (a) methods assuming known appearance models and (b) methods estimating appearance models jointly with segmentation. Typically, the first group optimizes appearance log-likelihoods in combination with some spacial regularization. This problem is relatively simple and many methods guarantee globally optimal results. The second group treats model parameters as additional variables transforming simple segmentation energies into high-order NP-hard functionals (Zhu-Yuille, Chan-Vese, Grab Cut, etc). It is known that such methods indirectly minimize the appearance overlap between the segments. We propose a new energy term explicitly measuring L1 distance between the object and background appearance models that can be globally maximized in one graph cut. We show that in many applications our simple term makes NP-hard segmentation functionals unnecessary. Our one cut algorithm effectively replaces approximate iterative optimization techniques based on block coordinate descent.
{"title":"GrabCut in One Cut","authors":"Meng Tang, Lena Gorelick, O. Veksler, Yuri Boykov","doi":"10.1109/ICCV.2013.222","DOIUrl":"https://doi.org/10.1109/ICCV.2013.222","url":null,"abstract":"Among image segmentation algorithms there are two major groups: (a) methods assuming known appearance models and (b) methods estimating appearance models jointly with segmentation. Typically, the first group optimizes appearance log-likelihoods in combination with some spacial regularization. This problem is relatively simple and many methods guarantee globally optimal results. The second group treats model parameters as additional variables transforming simple segmentation energies into high-order NP-hard functionals (Zhu-Yuille, Chan-Vese, Grab Cut, etc). It is known that such methods indirectly minimize the appearance overlap between the segments. We propose a new energy term explicitly measuring L1 distance between the object and background appearance models that can be globally maximized in one graph cut. We show that in many applications our simple term makes NP-hard segmentation functionals unnecessary. Our one cut algorithm effectively replaces approximate iterative optimization techniques based on block coordinate descent.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"35 1","pages":"1769-1776"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83579402","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 many cases, the predictive power of structured models for for complex vision tasks is limited by a trade-off between the expressiveness and the computational tractability of the model. However, choosing this trade-off statically a priori is sub optimal, as images and videos in different settings vary tremendously in complexity. On the other hand, choosing the trade-off dynamically requires knowledge about the accuracy of different structured models on any given example. In this work, we propose a novel two-tier architecture that provides dynamic speed/accuracy trade-offs through a simple type of introspection. Our approach, which we call dynamic structured model selection (DMS), leverages typically intractable features in structured learning problems in order to automatically determine' which of several models should be used at test-time in order to maximize accuracy under a fixed budgetary constraint. We demonstrate DMS on two sequential modeling vision tasks, and we establish a new state-of-the-art in human pose estimation in video with an implementation that is roughly 23× faster than the previous standard implementation.
{"title":"Dynamic Structured Model Selection","authors":"David J. Weiss, Benjamin Sapp, B. Taskar","doi":"10.1109/ICCV.2013.330","DOIUrl":"https://doi.org/10.1109/ICCV.2013.330","url":null,"abstract":"In many cases, the predictive power of structured models for for complex vision tasks is limited by a trade-off between the expressiveness and the computational tractability of the model. However, choosing this trade-off statically a priori is sub optimal, as images and videos in different settings vary tremendously in complexity. On the other hand, choosing the trade-off dynamically requires knowledge about the accuracy of different structured models on any given example. In this work, we propose a novel two-tier architecture that provides dynamic speed/accuracy trade-offs through a simple type of introspection. Our approach, which we call dynamic structured model selection (DMS), leverages typically intractable features in structured learning problems in order to automatically determine' which of several models should be used at test-time in order to maximize accuracy under a fixed budgetary constraint. We demonstrate DMS on two sequential modeling vision tasks, and we establish a new state-of-the-art in human pose estimation in video with an implementation that is roughly 23× faster than the previous standard implementation.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"13 1","pages":"2656-2663"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78292976","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 propose a novel approach for bird part localization, targeting fine-grained categories with wide variations in appearance due to different poses (including aspect and orientation) and subcategories. As it is challenging to represent such variations across a large set of diverse samples with tractable parametric models, we turn to individual exemplars. Specifically, we extend the exemplar-based models in [4] by enforcing pose and subcategory consistency at the parts. During training, we build pose-specific detectors scoring part poses across subcategories, and subcategory-specific detectors scoring part appearance across poses. At the testing stage, likely exemplars are matched to the image, suggesting part locations whose pose and subcategory consistency are well-supported by the image cues. From these hypotheses, part configuration can be predicted with very high accuracy. Experimental results demonstrate significant performance gains from our method on an extensive dataset: CUB-200-2011 [30], for both localization and classification tasks.
{"title":"Bird Part Localization Using Exemplar-Based Models with Enforced Pose and Subcategory Consistency","authors":"Jiongxin Liu, P. Belhumeur","doi":"10.1109/ICCV.2013.313","DOIUrl":"https://doi.org/10.1109/ICCV.2013.313","url":null,"abstract":"In this paper, we propose a novel approach for bird part localization, targeting fine-grained categories with wide variations in appearance due to different poses (including aspect and orientation) and subcategories. As it is challenging to represent such variations across a large set of diverse samples with tractable parametric models, we turn to individual exemplars. Specifically, we extend the exemplar-based models in [4] by enforcing pose and subcategory consistency at the parts. During training, we build pose-specific detectors scoring part poses across subcategories, and subcategory-specific detectors scoring part appearance across poses. At the testing stage, likely exemplars are matched to the image, suggesting part locations whose pose and subcategory consistency are well-supported by the image cues. From these hypotheses, part configuration can be predicted with very high accuracy. Experimental results demonstrate significant performance gains from our method on an extensive dataset: CUB-200-2011 [30], for both localization and classification tasks.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"178 1","pages":"2520-2527"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77776204","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}
Dense motion of image points over many video frames can provide important information about the world. However, occlusions and drift make it impossible to compute long motion paths by merely concatenating optical flow vectors between consecutive frames. Instead, we solve for entire paths directly, and flag the frames in which each is visible. As in previous work, we anchor each path to a unique pixel which guarantees an even spatial distribution of paths. Unlike earlier methods, we allow paths to be anchored in any frame. By explicitly requiring that at least one visible path passes within a small neighborhood of every pixel, we guarantee complete coverage of all visible points in all frames. We achieve state-of-the-art results on real sequences including both rigid and non-rigid motions with significant occlusions.
{"title":"Video Motion for Every Visible Point","authors":"Susanna Ricco, Carlo Tomasi","doi":"10.1109/ICCV.2013.306","DOIUrl":"https://doi.org/10.1109/ICCV.2013.306","url":null,"abstract":"Dense motion of image points over many video frames can provide important information about the world. However, occlusions and drift make it impossible to compute long motion paths by merely concatenating optical flow vectors between consecutive frames. Instead, we solve for entire paths directly, and flag the frames in which each is visible. As in previous work, we anchor each path to a unique pixel which guarantees an even spatial distribution of paths. Unlike earlier methods, we allow paths to be anchored in any frame. By explicitly requiring that at least one visible path passes within a small neighborhood of every pixel, we guarantee complete coverage of all visible points in all frames. We achieve state-of-the-art results on real sequences including both rigid and non-rigid motions with significant occlusions.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"179 1","pages":"2464-2471"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76768332","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}
Martin Schiegg, Philipp Hanslovsky, Bernhard X. Kausler, L. Hufnagel, F. Hamprecht
The quality of any tracking-by-assignment hinges on the accuracy of the foregoing target detection / segmentation step. In many kinds of images, errors in this first stage are unavoidable. These errors then propagate to, and corrupt, the tracking result. Our main contribution is the first probabilistic graphical model that can explicitly account for over- and under segmentation errors even when the number of tracking targets is unknown and when they may divide, as in cell cultures. The tracking model we present implements global consistency constraints for the number of targets comprised by each detection and is solved to global optimality on reasonably large 2D+t and 3D+t datasets. In addition, we empirically demonstrate the effectiveness of a post processing that allows to establish target identity even across occlusion / under segmentation. The usefulness and efficiency of this new tracking method is demonstrated on three different and challenging 2D+t and 3D+t datasets from developmental biology.
{"title":"Conservation Tracking","authors":"Martin Schiegg, Philipp Hanslovsky, Bernhard X. Kausler, L. Hufnagel, F. Hamprecht","doi":"10.1109/ICCV.2013.364","DOIUrl":"https://doi.org/10.1109/ICCV.2013.364","url":null,"abstract":"The quality of any tracking-by-assignment hinges on the accuracy of the foregoing target detection / segmentation step. In many kinds of images, errors in this first stage are unavoidable. These errors then propagate to, and corrupt, the tracking result. Our main contribution is the first probabilistic graphical model that can explicitly account for over- and under segmentation errors even when the number of tracking targets is unknown and when they may divide, as in cell cultures. The tracking model we present implements global consistency constraints for the number of targets comprised by each detection and is solved to global optimality on reasonably large 2D+t and 3D+t datasets. In addition, we empirically demonstrate the effectiveness of a post processing that allows to establish target identity even across occlusion / under segmentation. The usefulness and efficiency of this new tracking method is demonstrated on three different and challenging 2D+t and 3D+t datasets from developmental biology.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"32 1","pages":"2928-2935"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82158568","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}
Joint segmentation of image sets has great importance for object recognition, image classification, and image retrieval. In this paper, we aim to jointly segment a set of images starting from a small number of labeled images or none at all. To allow the images to share segmentation information with each other, we build a network that contains segmented as well as unsegmented images, and extract functional maps between connected image pairs based on image appearance features. These functional maps act as general property transporters between the images and, in particular, are used to transfer segmentations. We define and operate in a reduced functional space optimized so that the functional maps approximately satisfy cycle-consistency under composition in the network. A joint optimization framework is proposed to simultaneously generate all segmentation functions over the images so that they both align with local segmentation cues in each particular image, and agree with each other under network transportation. This formulation allows us to extract segmentations even with no training data, but can also exploit such data when available. The collective effect of the joint processing using functional maps leads to accurate information sharing among images and yields superior segmentation results, as shown on the iCoseg, MSRC, and PASCAL data sets.
{"title":"Image Co-segmentation via Consistent Functional Maps","authors":"F. Wang, Qi-Xing Huang, L. Guibas","doi":"10.1109/ICCV.2013.110","DOIUrl":"https://doi.org/10.1109/ICCV.2013.110","url":null,"abstract":"Joint segmentation of image sets has great importance for object recognition, image classification, and image retrieval. In this paper, we aim to jointly segment a set of images starting from a small number of labeled images or none at all. To allow the images to share segmentation information with each other, we build a network that contains segmented as well as unsegmented images, and extract functional maps between connected image pairs based on image appearance features. These functional maps act as general property transporters between the images and, in particular, are used to transfer segmentations. We define and operate in a reduced functional space optimized so that the functional maps approximately satisfy cycle-consistency under composition in the network. A joint optimization framework is proposed to simultaneously generate all segmentation functions over the images so that they both align with local segmentation cues in each particular image, and agree with each other under network transportation. This formulation allows us to extract segmentations even with no training data, but can also exploit such data when available. The collective effect of the joint processing using functional maps leads to accurate information sharing among images and yields superior segmentation results, as shown on the iCoseg, MSRC, and PASCAL data sets.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"17 1","pages":"849-856"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82180219","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}
Vicente Ordonez, Jia Deng, Yejin Choi, A. Berg, Tamara L. Berg
Entry level categories - the labels people will use to name an object - were originally defined and studied by psychologists in the 1980s. In this paper we study entry-level categories at a large scale and learn the first models for predicting entry-level categories for images. Our models combine visual recognition predictions with proxies for word "naturalness" mined from the enormous amounts of text on the web. We demonstrate the usefulness of our models for predicting nouns (entry-level words) associated with images by people. We also learn mappings between concepts predicted by existing visual recognition systems and entry-level concepts that could be useful for improving human-focused applications such as natural language image description or retrieval.
{"title":"From Large Scale Image Categorization to Entry-Level Categories","authors":"Vicente Ordonez, Jia Deng, Yejin Choi, A. Berg, Tamara L. Berg","doi":"10.1109/ICCV.2013.344","DOIUrl":"https://doi.org/10.1109/ICCV.2013.344","url":null,"abstract":"Entry level categories - the labels people will use to name an object - were originally defined and studied by psychologists in the 1980s. In this paper we study entry-level categories at a large scale and learn the first models for predicting entry-level categories for images. Our models combine visual recognition predictions with proxies for word \"naturalness\" mined from the enormous amounts of text on the web. We demonstrate the usefulness of our models for predicting nouns (entry-level words) associated with images by people. We also learn mappings between concepts predicted by existing visual recognition systems and entry-level concepts that could be useful for improving human-focused applications such as natural language image description or retrieval.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"1 1","pages":"2768-2775"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82448227","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：