Weakly-supervised semantic segmentation under image tags supervision is a challenging task as it directly associates high-level semantic to low-level appearance. To bridge this gap, in this paper, we propose an iterative bottom-up and top-down framework which alternatively expands object regions and optimizes segmentation network. We start from initial localization produced by classification networks. While classification networks are only responsive to small and coarse discriminative object regions, we argue that, these regions contain significant common features about objects. So in the bottom-up step, we mine common object features from the initial localization and expand object regions with the mined features. To supplement non-discriminative regions, saliency maps are then considered under Bayesian framework to refine the object regions. Then in the top-down step, the refined object regions are used as supervision to train the segmentation network and to predict object masks. These object masks provide more accurate localization and contain more regions of object. Further, we take these object masks as initial localization and mine common object features from them. These processes are conducted iteratively to progressively produce fine object masks and optimize segmentation networks. Experimental results on Pascal VOC 2012 dataset demonstrate that the proposed method outperforms previous state-of-the-art methods by a large margin.
{"title":"Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features","authors":"Xiang Wang, Shaodi You, Xi Li, Huimin Ma","doi":"10.1109/CVPR.2018.00147","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00147","url":null,"abstract":"Weakly-supervised semantic segmentation under image tags supervision is a challenging task as it directly associates high-level semantic to low-level appearance. To bridge this gap, in this paper, we propose an iterative bottom-up and top-down framework which alternatively expands object regions and optimizes segmentation network. We start from initial localization produced by classification networks. While classification networks are only responsive to small and coarse discriminative object regions, we argue that, these regions contain significant common features about objects. So in the bottom-up step, we mine common object features from the initial localization and expand object regions with the mined features. To supplement non-discriminative regions, saliency maps are then considered under Bayesian framework to refine the object regions. Then in the top-down step, the refined object regions are used as supervision to train the segmentation network and to predict object masks. These object masks provide more accurate localization and contain more regions of object. Further, we take these object masks as initial localization and mine common object features from them. These processes are conducted iteratively to progressively produce fine object masks and optimize segmentation networks. Experimental results on Pascal VOC 2012 dataset demonstrate that the proposed method outperforms previous state-of-the-art methods by a large margin.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"455 1","pages":"1354-1362"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79750729","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}
Recent progress on salient object detection is beneficial from Fully Convolutional Neural Network (FCN). The saliency cues contained in multi-level convolutional features are complementary for detecting salient objects. How to integrate multi-level features becomes an open problem in saliency detection. In this paper, we propose a novel bi-directional message passing model to integrate multi-level features for salient object detection. At first, we adopt a Multi-scale Context-aware Feature Extraction Module (MCFEM) for multi-level feature maps to capture rich context information. Then a bi-directional structure is designed to pass messages between multi-level features, and a gate function is exploited to control the message passing rate. We use the features after message passing, which simultaneously encode semantic information and spatial details, to predict saliency maps. Finally, the predicted results are efficiently combined to generate the final saliency map. Quantitative and qualitative experiments on five benchmark datasets demonstrate that our proposed model performs favorably against the state-of-the-art methods under different evaluation metrics.
{"title":"A Bi-Directional Message Passing Model for Salient Object Detection","authors":"Lu Zhang, Ju Dai, Huchuan Lu, You He, G. Wang","doi":"10.1109/CVPR.2018.00187","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00187","url":null,"abstract":"Recent progress on salient object detection is beneficial from Fully Convolutional Neural Network (FCN). The saliency cues contained in multi-level convolutional features are complementary for detecting salient objects. How to integrate multi-level features becomes an open problem in saliency detection. In this paper, we propose a novel bi-directional message passing model to integrate multi-level features for salient object detection. At first, we adopt a Multi-scale Context-aware Feature Extraction Module (MCFEM) for multi-level feature maps to capture rich context information. Then a bi-directional structure is designed to pass messages between multi-level features, and a gate function is exploited to control the message passing rate. We use the features after message passing, which simultaneously encode semantic information and spatial details, to predict saliency maps. Finally, the predicted results are efficiently combined to generate the final saliency map. Quantitative and qualitative experiments on five benchmark datasets demonstrate that our proposed model performs favorably against the state-of-the-art methods under different evaluation metrics.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"11 1","pages":"1741-1750"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79855826","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}
Minimization of labeling effort for person re-identification in camera networks is an important problem as most of the existing popular methods are supervised and they require large amount of manual annotations, acquiring which is a tedious job. In this work, we focus on this labeling effort minimization problem and approach it as a subset selection task where the objective is to select an optimal subset of image-pairs for labeling without compromising performance. Towards this goal, our proposed scheme first represents any camera network (with k number of cameras) as an edge weighted complete k-partite graph where each vertex denotes a person and similarity scores between persons are used as edge-weights. Then in the second stage, our algorithm selects an optimal subset of pairs by solving a triangle free subgraph maximization problem on the k-partite graph. This sub-graph weight maximization problem is NP-hard (at least for k = 4) which means for large datasets the optimization problem becomes intractable. In order to make our framework scalable, we propose two polynomial time approximately-optimal algorithms. The first algorithm is a 1/2-approximation algorithm which runs in linear time in the number of edges. The second algorithm is a greedy algorithm with sub-quadratic (in number of edges) time-complexity. Experiments on three state-of-the-art datasets depict that the proposed approach requires on an average only 8-15% manually labeled pairs in order to achieve the performance when all the pairs are manually annotated.
{"title":"Exploiting Transitivity for Learning Person Re-identification Models on a Budget","authors":"Sourya Roy, S. Paul, N. Young, A. Roy-Chowdhury","doi":"10.1109/CVPR.2018.00738","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00738","url":null,"abstract":"Minimization of labeling effort for person re-identification in camera networks is an important problem as most of the existing popular methods are supervised and they require large amount of manual annotations, acquiring which is a tedious job. In this work, we focus on this labeling effort minimization problem and approach it as a subset selection task where the objective is to select an optimal subset of image-pairs for labeling without compromising performance. Towards this goal, our proposed scheme first represents any camera network (with k number of cameras) as an edge weighted complete k-partite graph where each vertex denotes a person and similarity scores between persons are used as edge-weights. Then in the second stage, our algorithm selects an optimal subset of pairs by solving a triangle free subgraph maximization problem on the k-partite graph. This sub-graph weight maximization problem is NP-hard (at least for k = 4) which means for large datasets the optimization problem becomes intractable. In order to make our framework scalable, we propose two polynomial time approximately-optimal algorithms. The first algorithm is a 1/2-approximation algorithm which runs in linear time in the number of edges. The second algorithm is a greedy algorithm with sub-quadratic (in number of edges) time-complexity. Experiments on three state-of-the-art datasets depict that the proposed approach requires on an average only 8-15% manually labeled pairs in order to achieve the performance when all the pairs are manually annotated.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"4 1","pages":"7064-7072"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84515106","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}
Hsien-Tzu Cheng, Chun-Hung Chao, Jin-Dong Dong, Hao-Kai Wen, Tyng-Luh Liu, Min Sun
Automatic saliency prediction in 360° videos is critical for viewpoint guidance applications (e.g., Facebook 360 Guide). We propose a spatial-temporal network which is (1) weakly-supervised trained and (2) tailor-made for 360° viewing sphere. Note that most existing methods are less scalable since they rely on annotated saliency map for training. Most importantly, they convert 360° sphere to 2D images (e.g., a single equirectangular image or multiple separate Normal Field-of-View (NFoV) images) which introduces distortion and image boundaries. In contrast, we propose a simple and effective Cube Padding (CP) technique as follows. Firstly, we render the 360° view on six faces of a cube using perspective projection. Thus, it introduces very little distortion. Then, we concatenate all six faces while utilizing the connectivity between faces on the cube for image padding (i.e., Cube Padding) in convolution, pooling, convolutional LSTM layers. In this way, CP introduces no image boundary while being applicable to almost all Convolutional Neural Network (CNN) structures. To evaluate our method, we propose Wild-360, a new 360° video saliency dataset, containing challenging videos with saliency heatmap annotations. In experiments, our method outperforms baseline methods in both speed and quality.
{"title":"Cube Padding for Weakly-Supervised Saliency Prediction in 360° Videos","authors":"Hsien-Tzu Cheng, Chun-Hung Chao, Jin-Dong Dong, Hao-Kai Wen, Tyng-Luh Liu, Min Sun","doi":"10.1109/CVPR.2018.00154","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00154","url":null,"abstract":"Automatic saliency prediction in 360° videos is critical for viewpoint guidance applications (e.g., Facebook 360 Guide). We propose a spatial-temporal network which is (1) weakly-supervised trained and (2) tailor-made for 360° viewing sphere. Note that most existing methods are less scalable since they rely on annotated saliency map for training. Most importantly, they convert 360° sphere to 2D images (e.g., a single equirectangular image or multiple separate Normal Field-of-View (NFoV) images) which introduces distortion and image boundaries. In contrast, we propose a simple and effective Cube Padding (CP) technique as follows. Firstly, we render the 360° view on six faces of a cube using perspective projection. Thus, it introduces very little distortion. Then, we concatenate all six faces while utilizing the connectivity between faces on the cube for image padding (i.e., Cube Padding) in convolution, pooling, convolutional LSTM layers. In this way, CP introduces no image boundary while being applicable to almost all Convolutional Neural Network (CNN) structures. To evaluate our method, we propose Wild-360, a new 360° video saliency dataset, containing challenging videos with saliency heatmap annotations. In experiments, our method outperforms baseline methods in both speed and quality.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"111 1","pages":"1420-1429"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80678844","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}
Yiping Chen, Jingkang Wang, Jonathan Li, Cewu Lu, Zhipeng Luo, Han Xue, Cheng Wang
Learning autonomous-driving policies is one of the most challenging but promising tasks for computer vision. Most researchers believe that future research and applications should combine cameras, video recorders and laser scanners to obtain comprehensive semantic understanding of real traffic. However, current approaches only learn from large-scale videos, due to the lack of benchmarks that consist of precise laser-scanner data. In this paper, we are the first to propose a LiDAR-Video dataset, which provides large-scale high-quality point clouds scanned by a Velodyne laser, videos recorded by a dashboard camera and standard drivers' behaviors. Extensive experiments demonstrate that extra depth information help networks to determine driving policies indeed.
{"title":"LiDAR-Video Driving Dataset: Learning Driving Policies Effectively","authors":"Yiping Chen, Jingkang Wang, Jonathan Li, Cewu Lu, Zhipeng Luo, Han Xue, Cheng Wang","doi":"10.1109/CVPR.2018.00615","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00615","url":null,"abstract":"Learning autonomous-driving policies is one of the most challenging but promising tasks for computer vision. Most researchers believe that future research and applications should combine cameras, video recorders and laser scanners to obtain comprehensive semantic understanding of real traffic. However, current approaches only learn from large-scale videos, due to the lack of benchmarks that consist of precise laser-scanner data. In this paper, we are the first to propose a LiDAR-Video dataset, which provides large-scale high-quality point clouds scanned by a Velodyne laser, videos recorded by a dashboard camera and standard drivers' behaviors. Extensive experiments demonstrate that extra depth information help networks to determine driving policies indeed.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"358 1","pages":"5870-5878"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76358036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present a robust method which compensates RS distortions in a single image using a set of image curves, basing on the knowledge that they correspond to 3D straight lines. Unlike in existing work, no a priori knowledge about the line directions (e.g. Manhattan World assumption) is required. We first formulate a parametric equation for the projection of a 3D straight line viewed by a moving rolling shutter camera under a uniform motion model. Then we propose a method which efficiently estimates ego angular velocity separately from pose parameters, using at least 4 image curves. Moreover, we propose for the first time a RANSAC-like strategy to select image curves which really correspond to 3D straight lines and reject those corresponding to actual curves in 3D world. A comparative experimental study with both synthetic and real data from famous benchmarks shows that the proposed method outperforms all the existing techniques from the state-of-the-art.
{"title":"A Robust Method for Strong Rolling Shutter Effects Correction Using Lines with Automatic Feature Selection","authors":"Yizhen Lao, Omar Ait-Aider","doi":"10.1109/CVPR.2018.00504","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00504","url":null,"abstract":"We present a robust method which compensates RS distortions in a single image using a set of image curves, basing on the knowledge that they correspond to 3D straight lines. Unlike in existing work, no a priori knowledge about the line directions (e.g. Manhattan World assumption) is required. We first formulate a parametric equation for the projection of a 3D straight line viewed by a moving rolling shutter camera under a uniform motion model. Then we propose a method which efficiently estimates ego angular velocity separately from pose parameters, using at least 4 image curves. Moreover, we propose for the first time a RANSAC-like strategy to select image curves which really correspond to 3D straight lines and reject those corresponding to actual curves in 3D world. A comparative experimental study with both synthetic and real data from famous benchmarks shows that the proposed method outperforms all the existing techniques from the state-of-the-art.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"50 1","pages":"4795-4803"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90838034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We propose methods of addressing two critical issues of pedestrian detection: (i) occlusion of target objects as false negative failure, and (ii) confusion with hard negative examples like vertical structures as false positive failure. Our solutions to these two problems are general and flexible enough to be applicable to any single-stage detection models. We implement our methods into four state-of-the-art single-stage models, including SqueezeDet+ [22], YOLOv2 [17], SSD [12], and DSSD [8]. We empirically validate that our approach indeed improves the performance of those four models on Caltech pedestrian [4] and CityPersons dataset [25]. Moreover, in some heavy occlusion settings, our approach achieves the best reported performance. Specifically, our two solutions are as follows. For better occlusion handling, we update the output tensors of single-stage models so that they include the prediction of part confidence scores, from which we compute a final occlusion-aware detection score. For reducing confusion with hard negative examples, we introduce average grid classifiers as post-refinement classifiers, trainable in an end-to-end fashion with little memory and time overhead (e.g. increase of 1-5 MB in memory and 1-2 ms in inference time).
{"title":"Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors","authors":"Junhyug Noh, Soochan Lee, Beomsu Kim, Gunhee Kim","doi":"10.1109/CVPR.2018.00107","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00107","url":null,"abstract":"We propose methods of addressing two critical issues of pedestrian detection: (i) occlusion of target objects as false negative failure, and (ii) confusion with hard negative examples like vertical structures as false positive failure. Our solutions to these two problems are general and flexible enough to be applicable to any single-stage detection models. We implement our methods into four state-of-the-art single-stage models, including SqueezeDet+ [22], YOLOv2 [17], SSD [12], and DSSD [8]. We empirically validate that our approach indeed improves the performance of those four models on Caltech pedestrian [4] and CityPersons dataset [25]. Moreover, in some heavy occlusion settings, our approach achieves the best reported performance. Specifically, our two solutions are as follows. For better occlusion handling, we update the output tensors of single-stage models so that they include the prediction of part confidence scores, from which we compute a final occlusion-aware detection score. For reducing confusion with hard negative examples, we introduce average grid classifiers as post-refinement classifiers, trainable in an end-to-end fashion with little memory and time overhead (e.g. increase of 1-5 MB in memory and 1-2 ms in inference time).","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"10 1","pages":"966-974"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90354310","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}
Most video-based action recognition approaches choose to extract features from the whole video to recognize actions. The cluttered background and non-action motions limit the performances of these methods, since they lack the explicit modeling of human body movements. With recent advances of human pose estimation, this work presents a novel method to recognize human action as the evolution of pose estimation maps. Instead of relying on the inaccurate human poses estimated from videos, we observe that pose estimation maps, the byproduct of pose estimation, preserve richer cues of human body to benefit action recognition. Specifically, the evolution of pose estimation maps can be decomposed as an evolution of heatmaps, e.g., probabilistic maps, and an evolution of estimated 2D human poses, which denote the changes of body shape and body pose, respectively. Considering the sparse property of heatmap, we develop spatial rank pooling to aggregate the evolution of heatmaps as a body shape evolution image. As body shape evolution image does not differentiate body parts, we design body guided sampling to aggregate the evolution of poses as a body pose evolution image. The complementary properties between both types of images are explored by deep convolutional neural networks to predict action label. Experiments on NTU RGB+D, UTD-MHAD and PennAction datasets verify the effectiveness of our method, which outperforms most state-of-the-art methods.
{"title":"Recognizing Human Actions as the Evolution of Pose Estimation Maps","authors":"Mengyuan Liu, Junsong Yuan","doi":"10.1109/CVPR.2018.00127","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00127","url":null,"abstract":"Most video-based action recognition approaches choose to extract features from the whole video to recognize actions. The cluttered background and non-action motions limit the performances of these methods, since they lack the explicit modeling of human body movements. With recent advances of human pose estimation, this work presents a novel method to recognize human action as the evolution of pose estimation maps. Instead of relying on the inaccurate human poses estimated from videos, we observe that pose estimation maps, the byproduct of pose estimation, preserve richer cues of human body to benefit action recognition. Specifically, the evolution of pose estimation maps can be decomposed as an evolution of heatmaps, e.g., probabilistic maps, and an evolution of estimated 2D human poses, which denote the changes of body shape and body pose, respectively. Considering the sparse property of heatmap, we develop spatial rank pooling to aggregate the evolution of heatmaps as a body shape evolution image. As body shape evolution image does not differentiate body parts, we design body guided sampling to aggregate the evolution of poses as a body pose evolution image. The complementary properties between both types of images are explored by deep convolutional neural networks to predict action label. Experiments on NTU RGB+D, UTD-MHAD and PennAction datasets verify the effectiveness of our method, which outperforms most state-of-the-art methods.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"11 1","pages":"1159-1168"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89947080","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}
Shenlong Wang, Simon Suo, Wei-Chiu Ma, A. Pokrovsky, R. Urtasun
Standard convolutional neural networks assume a grid structured input is available and exploit discrete convolutions as their fundamental building blocks. This limits their applicability to many real-world applications. In this paper we propose Parametric Continuous Convolution, a new learnable operator that operates over non-grid structured data. The key idea is to exploit parameterized kernel functions that span the full continuous vector space. This generalization allows us to learn over arbitrary data structures as long as their support relationship is computable. Our experiments show significant improvement over the state-of-the-art in point cloud segmentation of indoor and outdoor scenes, and lidar motion estimation of driving scenes.
{"title":"Deep Parametric Continuous Convolutional Neural Networks","authors":"Shenlong Wang, Simon Suo, Wei-Chiu Ma, A. Pokrovsky, R. Urtasun","doi":"10.1109/CVPR.2018.00274","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00274","url":null,"abstract":"Standard convolutional neural networks assume a grid structured input is available and exploit discrete convolutions as their fundamental building blocks. This limits their applicability to many real-world applications. In this paper we propose Parametric Continuous Convolution, a new learnable operator that operates over non-grid structured data. The key idea is to exploit parameterized kernel functions that span the full continuous vector space. This generalization allows us to learn over arbitrary data structures as long as their support relationship is computable. Our experiments show significant improvement over the state-of-the-art in point cloud segmentation of indoor and outdoor scenes, and lidar motion estimation of driving scenes.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"44 1","pages":"2589-2597"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87803998","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}
With the rise of misinformation spread via social media channels, enabled by the increasing automation and realism of image manipulation tools, image forensics is an increasingly relevant problem. Classic image forensic methods leverage low-level cues such as metadata, sensor noise fingerprints, and others that are easily fooled when the image is re-encoded upon upload to facebook, etc. This necessitates the use of higher-level physical and semantic cues that, once hard to estimate reliably in the wild, have become more effective due to the increasing power of computer vision. In particular, we detect manipulations introduced by artificial blurring of the image, which creates inconsistent photometric relationships between image intensity and various cues. We achieve 98% accuracy on the most challenging cases in a new dataset of blur manipulations, where the blur is geometrically correct and consistent with the scene's physical arrangement. Such manipulations are now easily generated, for instance, by smartphone cameras having hardware to measure depth, e.g. 'Portrait Mode' of the iPhone7Plus. We also demonstrate good performance on a challenge dataset evaluating a wider range of manipulations in imagery representing 'in the wild' conditions.
{"title":"Focus Manipulation Detection via Photometric Histogram Analysis","authors":"Can Chen, Scott McCloskey, Jingyi Yu","doi":"10.1109/CVPR.2018.00180","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00180","url":null,"abstract":"With the rise of misinformation spread via social media channels, enabled by the increasing automation and realism of image manipulation tools, image forensics is an increasingly relevant problem. Classic image forensic methods leverage low-level cues such as metadata, sensor noise fingerprints, and others that are easily fooled when the image is re-encoded upon upload to facebook, etc. This necessitates the use of higher-level physical and semantic cues that, once hard to estimate reliably in the wild, have become more effective due to the increasing power of computer vision. In particular, we detect manipulations introduced by artificial blurring of the image, which creates inconsistent photometric relationships between image intensity and various cues. We achieve 98% accuracy on the most challenging cases in a new dataset of blur manipulations, where the blur is geometrically correct and consistent with the scene's physical arrangement. Such manipulations are now easily generated, for instance, by smartphone cameras having hardware to measure depth, e.g. 'Portrait Mode' of the iPhone7Plus. We also demonstrate good performance on a challenge dataset evaluating a wider range of manipulations in imagery representing 'in the wild' conditions.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"95 1","pages":"1674-1682"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85718898","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：