While great progress has been made in stereo computation over the last decades, large textureless regions remain challenging. Segment-based methods can tackle this problem properly, but their performances are sensitive to the segmentation results. In this paper, we alleviate the sensitivity by generating multiple proposals on absolute and relative disparities from multi-segmentations. These proposals supply rich descriptions of surface structures. Especially, the relative disparity between distant pixels can encode the large structure, which is critical to handle the large textureless regions. The proposals are coordinated by point-wise competition and pairwise collaboration within a MRF model. During inference, a dynamic programming is performed in different directions with various step sizes, so the long-range connections are better preserved. In the experiments, we carefully analyzed the effectiveness of the major components. Results on the 2014 Middlebury and KITTI 2015 stereo benchmark show that our method is comparable to state-of-the-art.
{"title":"Coordinating Multiple Disparity Proposals for Stereo Computation","authors":"Ang Li, Dapeng Chen, Yuanliu Liu, Zejian Yuan","doi":"10.1109/CVPR.2016.436","DOIUrl":"https://doi.org/10.1109/CVPR.2016.436","url":null,"abstract":"While great progress has been made in stereo computation over the last decades, large textureless regions remain challenging. Segment-based methods can tackle this problem properly, but their performances are sensitive to the segmentation results. In this paper, we alleviate the sensitivity by generating multiple proposals on absolute and relative disparities from multi-segmentations. These proposals supply rich descriptions of surface structures. Especially, the relative disparity between distant pixels can encode the large structure, which is critical to handle the large textureless regions. The proposals are coordinated by point-wise competition and pairwise collaboration within a MRF model. During inference, a dynamic programming is performed in different directions with various step sizes, so the long-range connections are better preserved. In the experiments, we carefully analyzed the effectiveness of the major components. Results on the 2014 Middlebury and KITTI 2015 stereo benchmark show that our method is comparable to state-of-the-art.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"310 1","pages":"4022-4030"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76454874","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}
Sarah Rastegar, M. Baghshah, H. Rabiee, Seyed Mohsen Shojaee
Deep learning has received much attention as of the most powerful approaches for multimodal representation learning in recent years. An ideal model for multimodal data can reason about missing modalities using the available ones, and usually provides more information when multiple modalities are being considered. All the previous deep models contain separate modality-specific networks and find a shared representation on top of those networks. Therefore, they only consider high level interactions between modalities to find a joint representation for them. In this paper, we propose a multimodal deep learning framework (MDLCW) that exploits the cross weights between representation of modalities, and try to gradually learn interactions of the modalities in a deep network manner (from low to high level interactions). Moreover, we theoretically show that considering these interactions provide more intra-modality information, and introduce a multi-stage pre-training method that is based on the properties of multi-modal data. In the proposed framework, as opposed to the existing deep methods for multi-modal data, we try to reconstruct the representation of each modality at a given level, with representation of other modalities in the previous layer. Extensive experimental results show that the proposed model outperforms state-of-the-art information retrieval methods for both image and text queries on the PASCAL-sentence and SUN-Attribute databases.
{"title":"MDL-CW: A Multimodal Deep Learning Framework with CrossWeights","authors":"Sarah Rastegar, M. Baghshah, H. Rabiee, Seyed Mohsen Shojaee","doi":"10.1109/CVPR.2016.285","DOIUrl":"https://doi.org/10.1109/CVPR.2016.285","url":null,"abstract":"Deep learning has received much attention as of the most powerful approaches for multimodal representation learning in recent years. An ideal model for multimodal data can reason about missing modalities using the available ones, and usually provides more information when multiple modalities are being considered. All the previous deep models contain separate modality-specific networks and find a shared representation on top of those networks. Therefore, they only consider high level interactions between modalities to find a joint representation for them. In this paper, we propose a multimodal deep learning framework (MDLCW) that exploits the cross weights between representation of modalities, and try to gradually learn interactions of the modalities in a deep network manner (from low to high level interactions). Moreover, we theoretically show that considering these interactions provide more intra-modality information, and introduce a multi-stage pre-training method that is based on the properties of multi-modal data. In the proposed framework, as opposed to the existing deep methods for multi-modal data, we try to reconstruct the representation of each modality at a given level, with representation of other modalities in the previous layer. Extensive experimental results show that the proposed model outperforms state-of-the-art information retrieval methods for both image and text queries on the PASCAL-sentence and SUN-Attribute databases.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"48 1","pages":"2601-2609"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79252352","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}
Roozbeh Mottaghi, Hannaneh Hajishirzi, Ali Farhadi
With the recent progress in visual recognition, we have already started to see a surge of vision related real-world applications. These applications, unlike general scene understanding, are task oriented and require specific information from visual data. Considering the current growth in new sensory devices, feature designs, feature learning methods, and algorithms, the search in the space of features and models becomes combinatorial. In this paper, we propose a novel cost-sensitive task-oriented recognition method that is based on a combination of linguistic semantics and visual cues. Our task-oriented framework is able to generalize to unseen tasks for which there is no training data and outperforms state-of-the-art cost-based recognition baselines on our new task-based dataset.
{"title":"A Task-Oriented Approach for Cost-Sensitive Recognition","authors":"Roozbeh Mottaghi, Hannaneh Hajishirzi, Ali Farhadi","doi":"10.1109/CVPR.2016.242","DOIUrl":"https://doi.org/10.1109/CVPR.2016.242","url":null,"abstract":"With the recent progress in visual recognition, we have already started to see a surge of vision related real-world applications. These applications, unlike general scene understanding, are task oriented and require specific information from visual data. Considering the current growth in new sensory devices, feature designs, feature learning methods, and algorithms, the search in the space of features and models becomes combinatorial. In this paper, we propose a novel cost-sensitive task-oriented recognition method that is based on a combination of linguistic semantics and visual cues. Our task-oriented framework is able to generalize to unseen tasks for which there is no training data and outperforms state-of-the-art cost-based recognition baselines on our new task-based dataset.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"19 1","pages":"2203-2211"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76953810","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}
Xueyang Fu, Delu Zeng, Yue Huang, Xiao-Ping Zhang, Xinghao Ding
We propose a weighted variational model to estimate both the reflectance and the illumination from an observed image. We show that, though it is widely adopted for ease of modeling, the log-transformed image for this task is not ideal. Based on the previous investigation of the logarithmic transformation, a new weighted variational model is proposed for better prior representation, which is imposed in the regularization terms. Different from conventional variational models, the proposed model can preserve the estimated reflectance with more details. Moreover, the proposed model can suppress noise to some extent. An alternating minimization scheme is adopted to solve the proposed model. Experimental results demonstrate the effectiveness of the proposed model with its algorithm. Compared with other variational methods, the proposed method yields comparable or better results on both subjective and objective assessments.
{"title":"A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation","authors":"Xueyang Fu, Delu Zeng, Yue Huang, Xiao-Ping Zhang, Xinghao Ding","doi":"10.1109/CVPR.2016.304","DOIUrl":"https://doi.org/10.1109/CVPR.2016.304","url":null,"abstract":"We propose a weighted variational model to estimate both the reflectance and the illumination from an observed image. We show that, though it is widely adopted for ease of modeling, the log-transformed image for this task is not ideal. Based on the previous investigation of the logarithmic transformation, a new weighted variational model is proposed for better prior representation, which is imposed in the regularization terms. Different from conventional variational models, the proposed model can preserve the estimated reflectance with more details. Moreover, the proposed model can suppress noise to some extent. An alternating minimization scheme is adopted to solve the proposed model. Experimental results demonstrate the effectiveness of the proposed model with its algorithm. Compared with other variational methods, the proposed method yields comparable or better results on both subjective and objective assessments.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"115 1","pages":"2782-2790"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73417073","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}
Justus Thies, M. Zollhöfer, M. Stamminger, C. Theobalt, M. Nießner
We present a novel approach for real-time facial reenactment of a monocular target video sequence (e.g., Youtube video). The source sequence is also a monocular video stream, captured live with a commodity webcam. Our goal is to animate the facial expressions of the target video by a source actor and re-render the manipulated output video in a photo-realistic fashion. To this end, we first address the under-constrained problem of facial identity recovery from monocular video by non-rigid model-based bundling. At run time, we track facial expressions of both source and target video using a dense photometric consistency measure. Reenactment is then achieved by fast and efficient deformation transfer between source and target. The mouth interior that best matches the re-targeted expression is retrieved from the target sequence and warped to produce an accurate fit. Finally, we convincingly re-render the synthesized target face on top of the corresponding video stream such that it seamlessly blends with the real-world illumination. We demonstrate our method in a live setup, where Youtube videos are reenacted in real time.
{"title":"Face2Face: Real-Time Face Capture and Reenactment of RGB Videos","authors":"Justus Thies, M. Zollhöfer, M. Stamminger, C. Theobalt, M. Nießner","doi":"10.1145/3292039","DOIUrl":"https://doi.org/10.1145/3292039","url":null,"abstract":"We present a novel approach for real-time facial reenactment of a monocular target video sequence (e.g., Youtube video). The source sequence is also a monocular video stream, captured live with a commodity webcam. Our goal is to animate the facial expressions of the target video by a source actor and re-render the manipulated output video in a photo-realistic fashion. To this end, we first address the under-constrained problem of facial identity recovery from monocular video by non-rigid model-based bundling. At run time, we track facial expressions of both source and target video using a dense photometric consistency measure. Reenactment is then achieved by fast and efficient deformation transfer between source and target. The mouth interior that best matches the re-targeted expression is retrieved from the target sequence and warped to produce an accurate fit. Finally, we convincingly re-render the synthesized target face on top of the corresponding video stream such that it seamlessly blends with the real-world illumination. We demonstrate our method in a live setup, where Youtube videos are reenacted in real time.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"15 1","pages":"2387-2395"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72617275","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}
Lluís Castrejón, Y. Aytar, Carl Vondrick, H. Pirsiavash, A. Torralba
People can recognize scenes across many different modalities beyond natural images. In this paper, we investigate how to learn cross-modal scene representations that transfer across modalities. To study this problem, we introduce a new cross-modal scene dataset. While convolutional neural networks can categorize cross-modal scenes well, they also learn an intermediate representation not aligned across modalities, which is undesirable for crossmodal transfer applications. We present methods to regularize cross-modal convolutional neural networks so that they have a shared representation that is agnostic of the modality. Our experiments suggest that our scene representation can help transfer representations across modalities for retrieval. Moreover, our visualizations suggest that units emerge in the shared representation that tend to activate on consistent concepts independently of the modality.
{"title":"Learning Aligned Cross-Modal Representations from Weakly Aligned Data","authors":"Lluís Castrejón, Y. Aytar, Carl Vondrick, H. Pirsiavash, A. Torralba","doi":"10.1109/CVPR.2016.321","DOIUrl":"https://doi.org/10.1109/CVPR.2016.321","url":null,"abstract":"People can recognize scenes across many different modalities beyond natural images. In this paper, we investigate how to learn cross-modal scene representations that transfer across modalities. To study this problem, we introduce a new cross-modal scene dataset. While convolutional neural networks can categorize cross-modal scenes well, they also learn an intermediate representation not aligned across modalities, which is undesirable for crossmodal transfer applications. We present methods to regularize cross-modal convolutional neural networks so that they have a shared representation that is agnostic of the modality. Our experiments suggest that our scene representation can help transfer representations across modalities for retrieval. Moreover, our visualizations suggest that units emerge in the shared representation that tend to activate on consistent concepts independently of the modality.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"33 1","pages":"2940-2949"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74545112","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}
This paper presents a novel deep architecture, called neural regression forest (NRF), for depth estimation from a single image. NRF combines random forests and convolutional neural networks (CNNs). Scanning windows extracted from the image represent samples which are passed down the trees of NRF for predicting their depth. At every tree node, the sample is filtered with a CNN associated with that node. Results of the convolutional filtering are passed to left and right children nodes, i.e., corresponding CNNs, with a Bernoulli probability, until the leaves, where depth estimations are made. CNNs at every node are designed to have fewer parameters than seen in recent work, but their stacked processing along a path in the tree effectively amounts to a deeper CNN. NRF allows for parallelizable training of all "shallow" CNNs, and efficient enforcing of smoothness in depth estimation results. Our evaluation on the benchmark Make3D and NYUv2 datasets demonstrates that NRF outperforms the state of the art, and gracefully handles gradually decreasing training datasets.
{"title":"Monocular Depth Estimation Using Neural Regression Forest","authors":"Anirban Roy, S. Todorovic","doi":"10.1109/CVPR.2016.594","DOIUrl":"https://doi.org/10.1109/CVPR.2016.594","url":null,"abstract":"This paper presents a novel deep architecture, called neural regression forest (NRF), for depth estimation from a single image. NRF combines random forests and convolutional neural networks (CNNs). Scanning windows extracted from the image represent samples which are passed down the trees of NRF for predicting their depth. At every tree node, the sample is filtered with a CNN associated with that node. Results of the convolutional filtering are passed to left and right children nodes, i.e., corresponding CNNs, with a Bernoulli probability, until the leaves, where depth estimations are made. CNNs at every node are designed to have fewer parameters than seen in recent work, but their stacked processing along a path in the tree effectively amounts to a deeper CNN. NRF allows for parallelizable training of all \"shallow\" CNNs, and efficient enforcing of smoothness in depth estimation results. Our evaluation on the benchmark Make3D and NYUv2 datasets demonstrates that NRF outperforms the state of the art, and gracefully handles gradually decreasing training datasets.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"9 1","pages":"5506-5514"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90184610","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}
This paper presents a novel scene text detection algorithm, Canny Text Detector, which takes advantage of the similarity between image edge and text for effective text localization with improved recall rate. As closely related edge pixels construct the structural information of an object, we observe that cohesive characters compose a meaningful word/sentence sharing similar properties such as spatial location, size, color, and stroke width regardless of language. However, prevalent scene text detection approaches have not fully utilized such similarity, but mostly rely on the characters classified with high confidence, leading to low recall rate. By exploiting the similarity, our approach can quickly and robustly localize a variety of texts. Inspired by the original Canny edge detector, our algorithm makes use of double threshold and hysteresis tracking to detect texts of low confidence. Experimental results on public datasets demonstrate that our algorithm outperforms the state-of the-art scene text detection methods in terms of detection rate.
{"title":"Canny Text Detector: Fast and Robust Scene Text Localization Algorithm","authors":"Hojin Cho, Myung-Chul Sung, Bongjin Jun","doi":"10.1109/CVPR.2016.388","DOIUrl":"https://doi.org/10.1109/CVPR.2016.388","url":null,"abstract":"This paper presents a novel scene text detection algorithm, Canny Text Detector, which takes advantage of the similarity between image edge and text for effective text localization with improved recall rate. As closely related edge pixels construct the structural information of an object, we observe that cohesive characters compose a meaningful word/sentence sharing similar properties such as spatial location, size, color, and stroke width regardless of language. However, prevalent scene text detection approaches have not fully utilized such similarity, but mostly rely on the characters classified with high confidence, leading to low recall rate. By exploiting the similarity, our approach can quickly and robustly localize a variety of texts. Inspired by the original Canny edge detector, our algorithm makes use of double threshold and hysteresis tracking to detect texts of low confidence. Experimental results on public datasets demonstrate that our algorithm outperforms the state-of the-art scene text detection methods in terms of detection rate.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"441 1","pages":"3566-3573"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87562459","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}
Aiming at automatically discovering the common objects contained in a set of relevant images and segmenting them as foreground simultaneously, object co-segmentation has become an active research topic in recent years. Although a number of approaches have been proposed to address this problem, many of them are designed with the misleading assumption, unscalable prior, or low flexibility and thus still suffer from certain limitations, which reduces their capability in the real-world scenarios. To alleviate these limitations, we propose a novel two-stage co-segmentation framework, which introduces the weak background prior to establish a globally close-loop graph to represent the common object and union background separately. Then a novel graph optimized-flexible manifold ranking algorithm is proposed to flexibly optimize the graph connection and node labels to co-segment the common objects. Experiments on three image datasets demonstrate that our method outperforms other state-of-the-art methods.
{"title":"Object Co-segmentation via Graph Optimized-Flexible Manifold Ranking","authors":"Rong Quan, Junwei Han, Dingwen Zhang, F. Nie","doi":"10.1109/CVPR.2016.81","DOIUrl":"https://doi.org/10.1109/CVPR.2016.81","url":null,"abstract":"Aiming at automatically discovering the common objects contained in a set of relevant images and segmenting them as foreground simultaneously, object co-segmentation has become an active research topic in recent years. Although a number of approaches have been proposed to address this problem, many of them are designed with the misleading assumption, unscalable prior, or low flexibility and thus still suffer from certain limitations, which reduces their capability in the real-world scenarios. To alleviate these limitations, we propose a novel two-stage co-segmentation framework, which introduces the weak background prior to establish a globally close-loop graph to represent the common object and union background separately. Then a novel graph optimized-flexible manifold ranking algorithm is proposed to flexibly optimize the graph connection and node labels to co-segment the common objects. Experiments on three image datasets demonstrate that our method outperforms other state-of-the-art methods.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"59 1","pages":"687-695"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84865108","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}
Si Liu, Tianzhu Zhang, Xiaochun Cao, Changsheng Xu
In this paper, we propose a novel structural correlation filter (SCF) model for robust visual tracking. The proposed SCF model takes part-based tracking strategies into account in a correlation filter tracker, and exploits circular shifts of all parts for their motion modeling to preserve target object structure. Compared with existing correlation filter trackers, our proposed tracker has several advantages: (1) Due to the part strategy, the learned structural correlation filters are less sensitive to partial occlusion, and have computational efficiency and robustness. (2) The learned filters are able to not only distinguish the parts from the background as the traditional correlation filters, but also exploit the intrinsic relationship among local parts via spatial constraints to preserve object structure. (3) The learned correlation filters not only make most parts share similar motion, but also tolerate outlier parts that have different motion. Both qualitative and quantitative evaluations on challenging benchmark image sequences demonstrate that the proposed SCF tracking algorithm performs favorably against several state-of-the-art methods.
{"title":"Structural Correlation Filter for Robust Visual Tracking","authors":"Si Liu, Tianzhu Zhang, Xiaochun Cao, Changsheng Xu","doi":"10.1109/CVPR.2016.467","DOIUrl":"https://doi.org/10.1109/CVPR.2016.467","url":null,"abstract":"In this paper, we propose a novel structural correlation filter (SCF) model for robust visual tracking. The proposed SCF model takes part-based tracking strategies into account in a correlation filter tracker, and exploits circular shifts of all parts for their motion modeling to preserve target object structure. Compared with existing correlation filter trackers, our proposed tracker has several advantages: (1) Due to the part strategy, the learned structural correlation filters are less sensitive to partial occlusion, and have computational efficiency and robustness. (2) The learned filters are able to not only distinguish the parts from the background as the traditional correlation filters, but also exploit the intrinsic relationship among local parts via spatial constraints to preserve object structure. (3) The learned correlation filters not only make most parts share similar motion, but also tolerate outlier parts that have different motion. Both qualitative and quantitative evaluations on challenging benchmark image sequences demonstrate that the proposed SCF tracking algorithm performs favorably against several state-of-the-art methods.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"535 ","pages":"4312-4320"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91450065","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：