Few-shot learning, which aims at extracting new concepts rapidly from extremely few examples of novel classes, has been featured into the meta-learning paradigm recently. Yet, the key challenge of how to learn a generalizable classifier with the capability of adapting to specific tasks with severely limited data still remains in this domain. To this end, we propose a Transductive Episodic-wise Adaptive Metric (TEAM) framework for few-shot learning, by integrating the meta-learning paradigm with both deep metric learning and transductive inference. With exploring the pairwise constraints and regularization prior within each task, we explicitly formulate the adaptation procedure into a standard semi-definite programming problem. By solving the problem with its closed-form solution on the fly with the setup of transduction, our approach efficiently tailors an episodic-wise metric for each task to adapt all features from a shared task-agnostic embedding space into a more discriminative task-specific metric space. Moreover, we further leverage an attention-based bi-directional similarity strategy for extracting the more robust relationship between queries and prototypes. Extensive experiments on three benchmark datasets show that our framework is superior to other existing approaches and achieves the state-of-the-art performance in the few-shot literature.
{"title":"Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning","authors":"Limeng Qiao, Yemin Shi, Jia Li, Yaowei Wang, Tiejun Huang, Yonghong Tian","doi":"10.1109/ICCV.2019.00370","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00370","url":null,"abstract":"Few-shot learning, which aims at extracting new concepts rapidly from extremely few examples of novel classes, has been featured into the meta-learning paradigm recently. Yet, the key challenge of how to learn a generalizable classifier with the capability of adapting to specific tasks with severely limited data still remains in this domain. To this end, we propose a Transductive Episodic-wise Adaptive Metric (TEAM) framework for few-shot learning, by integrating the meta-learning paradigm with both deep metric learning and transductive inference. With exploring the pairwise constraints and regularization prior within each task, we explicitly formulate the adaptation procedure into a standard semi-definite programming problem. By solving the problem with its closed-form solution on the fly with the setup of transduction, our approach efficiently tailors an episodic-wise metric for each task to adapt all features from a shared task-agnostic embedding space into a more discriminative task-specific metric space. Moreover, we further leverage an attention-based bi-directional similarity strategy for extracting the more robust relationship between queries and prototypes. Extensive experiments on three benchmark datasets show that our framework is superior to other existing approaches and achieves the state-of-the-art performance in the few-shot literature.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"77 1","pages":"3602-3611"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90576939","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}
Iro Armeni, Zhi-Yang He, JunYoung Gwak, A. Zamir, Martin Fischer, J. Malik, S. Savarese
A comprehensive semantic understanding of a scene is important for many applications - but in what space should diverse semantic information (e.g., objects, scene categories, material types, 3D shapes, etc.) be grounded and what should be its structure? Aspiring to have one unified structure that hosts diverse types of semantics, we follow the Scene Graph paradigm in 3D, generating a 3D Scene Graph. Given a 3D mesh and registered panoramic images, we construct a graph that spans the entire building and includes semantics on objects (e.g., class, material, shape and other attributes), rooms (e.g., function, illumination type, etc.) and cameras (e.g., location, etc.), as well as the relationships among these entities. However, this process is prohibitively labor heavy if done manually. To alleviate this we devise a semi-automatic framework that employs existing detection methods and enhances them using two main constraints: I. framing of query images sampled on panoramas to maximize the performance of 2D detectors, and II. multi-view consistency enforcement across 2D detections that originate in different camera locations.
{"title":"3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera","authors":"Iro Armeni, Zhi-Yang He, JunYoung Gwak, A. Zamir, Martin Fischer, J. Malik, S. Savarese","doi":"10.1109/ICCV.2019.00576","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00576","url":null,"abstract":"A comprehensive semantic understanding of a scene is important for many applications - but in what space should diverse semantic information (e.g., objects, scene categories, material types, 3D shapes, etc.) be grounded and what should be its structure? Aspiring to have one unified structure that hosts diverse types of semantics, we follow the Scene Graph paradigm in 3D, generating a 3D Scene Graph. Given a 3D mesh and registered panoramic images, we construct a graph that spans the entire building and includes semantics on objects (e.g., class, material, shape and other attributes), rooms (e.g., function, illumination type, etc.) and cameras (e.g., location, etc.), as well as the relationships among these entities. However, this process is prohibitively labor heavy if done manually. To alleviate this we devise a semi-automatic framework that employs existing detection methods and enhances them using two main constraints: I. framing of query images sampled on panoramas to maximize the performance of 2D detectors, and II. multi-view consistency enforcement across 2D detections that originate in different camera locations.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"5663-5672"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89199796","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}
Actor and action video segmentation from natural language query aims to selectively segment the actor and its action in a video based on an input textual description. Previous works mostly focus on learning simple correlation between two heterogeneous features of vision and language via dynamic convolution or fully convolutional classification. However, they ignore the linguistic variation of natural language query and have difficulty in modeling global visual context, which leads to unsatisfactory segmentation performance. To address these issues, we propose an asymmetric cross-guided attention network for actor and action video segmentation from natural language query. Specifically, we frame an asymmetric cross-guided attention network, which consists of vision guided language attention to reduce the linguistic variation of input query and language guided vision attention to incorporate query-focused global visual context simultaneously. Moreover, we adopt multi-resolution fusion scheme and weighted loss for foreground and background pixels to obtain further performance improvement. Extensive experiments on Actor-Action Dataset Sentences and J-HMDB Sentences show that our proposed approach notably outperforms state-of-the-art methods.
{"title":"Asymmetric Cross-Guided Attention Network for Actor and Action Video Segmentation From Natural Language Query","authors":"H. Wang, Cheng Deng, Junchi Yan, D. Tao","doi":"10.1109/ICCV.2019.00404","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00404","url":null,"abstract":"Actor and action video segmentation from natural language query aims to selectively segment the actor and its action in a video based on an input textual description. Previous works mostly focus on learning simple correlation between two heterogeneous features of vision and language via dynamic convolution or fully convolutional classification. However, they ignore the linguistic variation of natural language query and have difficulty in modeling global visual context, which leads to unsatisfactory segmentation performance. To address these issues, we propose an asymmetric cross-guided attention network for actor and action video segmentation from natural language query. Specifically, we frame an asymmetric cross-guided attention network, which consists of vision guided language attention to reduce the linguistic variation of input query and language guided vision attention to incorporate query-focused global visual context simultaneously. Moreover, we adopt multi-resolution fusion scheme and weighted loss for foreground and background pixels to obtain further performance improvement. Extensive experiments on Actor-Action Dataset Sentences and J-HMDB Sentences show that our proposed approach notably outperforms state-of-the-art methods.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"21 1","pages":"3938-3947"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84291464","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}
Shuai Shao, Zeming Li, Tianyuan Zhang, Chao Peng, Gang Yu, Xiangyu Zhang, Jing Li, Jian Sun
In this paper, we introduce a new large-scale object detection dataset, Objects365, which has 365 object categories over 600K training images. More than 10 million, high-quality bounding boxes are manually labeled through a three-step, carefully designed annotation pipeline. It is the largest object detection dataset (with full annotation) so far and establishes a more challenging benchmark for the community. Objects365 can serve as a better feature learning dataset for localization-sensitive tasks like object detection and semantic segmentation. The Objects365 pre-trained models significantly outperform ImageNet pre-trained models with 5.6 points gain (42 vs 36.4) based on the standard setting of 90K iterations on COCO benchmark. Even compared with much long training time like 540K iterations, our Objects365 pretrained model with 90K iterations still have 2.7 points gain (42 vs 39.3). Meanwhile, the finetuning time can be greatly reduced (up to 10 times) when reaching the same accuracy. Better generalization ability of Object365 has also been verified on CityPersons, VOC segmentation, and ADE tasks. The dataset as well as the pretrained-models have been released at www.objects365.org.
{"title":"Objects365: A Large-Scale, High-Quality Dataset for Object Detection","authors":"Shuai Shao, Zeming Li, Tianyuan Zhang, Chao Peng, Gang Yu, Xiangyu Zhang, Jing Li, Jian Sun","doi":"10.1109/ICCV.2019.00852","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00852","url":null,"abstract":"In this paper, we introduce a new large-scale object detection dataset, Objects365, which has 365 object categories over 600K training images. More than 10 million, high-quality bounding boxes are manually labeled through a three-step, carefully designed annotation pipeline. It is the largest object detection dataset (with full annotation) so far and establishes a more challenging benchmark for the community. Objects365 can serve as a better feature learning dataset for localization-sensitive tasks like object detection and semantic segmentation. The Objects365 pre-trained models significantly outperform ImageNet pre-trained models with 5.6 points gain (42 vs 36.4) based on the standard setting of 90K iterations on COCO benchmark. Even compared with much long training time like 540K iterations, our Objects365 pretrained model with 90K iterations still have 2.7 points gain (42 vs 39.3). Meanwhile, the finetuning time can be greatly reduced (up to 10 times) when reaching the same accuracy. Better generalization ability of Object365 has also been verified on CityPersons, VOC segmentation, and ADE tasks. The dataset as well as the pretrained-models have been released at www.objects365.org.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"12 1","pages":"8429-8438"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88385462","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}
Wu Wang, Weihong Zeng, Yue Huang, Xinghao Ding, J. Paisley
Hyperspectral image fusion (HIF) reconstructs high spatial resolution hyperspectral images from low spatial resolution hyperspectral images and high spatial resolution multispectral images. Previous works usually assume that the linear mapping between the point spread functions of the hyperspectral camera and the spectral response functions of the conventional camera is known. This is unrealistic in many scenarios. We propose a method for blind HIF problem based on deep learning, where the estimation of the observation model and fusion process are optimized iteratively and alternatingly during the super-resolution reconstruction. In addition, the proposed framework enforces simultaneous spatial and spectral accuracy. Using three public datasets, the experimental results demonstrate that the proposed algorithm outperforms existing blind and non-blind methods.
{"title":"Deep Blind Hyperspectral Image Fusion","authors":"Wu Wang, Weihong Zeng, Yue Huang, Xinghao Ding, J. Paisley","doi":"10.1109/ICCV.2019.00425","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00425","url":null,"abstract":"Hyperspectral image fusion (HIF) reconstructs high spatial resolution hyperspectral images from low spatial resolution hyperspectral images and high spatial resolution multispectral images. Previous works usually assume that the linear mapping between the point spread functions of the hyperspectral camera and the spectral response functions of the conventional camera is known. This is unrealistic in many scenarios. We propose a method for blind HIF problem based on deep learning, where the estimation of the observation model and fusion process are optimized iteratively and alternatingly during the super-resolution reconstruction. In addition, the proposed framework enforces simultaneous spatial and spectral accuracy. Using three public datasets, the experimental results demonstrate that the proposed algorithm outperforms existing blind and non-blind methods.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"14 1","pages":"4149-4158"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86615594","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}
Assaf Shocher, Shai Bagon, Phillip Isola, M. Irani
Generative Adversarial Networks (GANs) typically learn a distribution of images in a large image dataset, and are then able to generate new images from this distribution. However, each natural image has its own internal statistics, captured by its unique distribution of patches. In this paper we propose an ``Internal GAN'' (InGAN) -- an image-specific GAN -- which trains on a single input image and learns its internal distribution of patches. It is then able to synthesize a plethora of new natural images of significantly different sizes, shapes and aspect-ratios – all with the same internal patch-distribution (same ``DNA'') as the input image. In particular, despite large changes in global size/shape of the image, all elements inside the image maintain their local size/shape. InGAN is fully unsupervised, requiring no additional data other than the input image itself. Once trained on the input image, it can remap the input to any size or shape in a single feedforward pass, while preserving the same internal patch distribution. InGAN provides a unified framework for a variety of tasks, bridging the gap between textures and natural images.
{"title":"InGAN: Capturing and Retargeting the “DNA” of a Natural Image","authors":"Assaf Shocher, Shai Bagon, Phillip Isola, M. Irani","doi":"10.1109/ICCV.2019.00459","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00459","url":null,"abstract":"Generative Adversarial Networks (GANs) typically learn a distribution of images in a large image dataset, and are then able to generate new images from this distribution. However, each natural image has its own internal statistics, captured by its unique distribution of patches. In this paper we propose an ``Internal GAN'' (InGAN) -- an image-specific GAN -- which trains on a single input image and learns its internal distribution of patches. It is then able to synthesize a plethora of new natural images of significantly different sizes, shapes and aspect-ratios – all with the same internal patch-distribution (same ``DNA'') as the input image. In particular, despite large changes in global size/shape of the image, all elements inside the image maintain their local size/shape. InGAN is fully unsupervised, requiring no additional data other than the input image itself. Once trained on the input image, it can remap the input to any size or shape in a single feedforward pass, while preserving the same internal patch distribution. InGAN provides a unified framework for a variety of tasks, bridging the gap between textures and natural images.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"4491-4500"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86751169","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}
Despite promising performance achieved by deep con- volutional neural networks for non-occluded pedestrian de- tection, it remains a great challenge to detect partially oc- cluded pedestrians. Compared with non-occluded pedes- trian examples, it is generally more difficult to distinguish occluded pedestrian examples from background in featue space due to the missing of occluded parts. In this paper, we propose a discriminative feature transformation which en- forces feature separability of pedestrian and non-pedestrian examples to handle occlusions for pedestrian detection. Specifically, in feature space it makes pedestrian exam- ples approach the centroid of easily classified non-occluded pedestrian examples and pushes non-pedestrian examples close to the centroid of easily classified non-pedestrian ex- amples. Such a feature transformation partially compen- sates the missing contribution of occluded parts in feature space, therefore improving the performance for occluded pedestrian detection. We implement our approach in the Fast R-CNN framework by adding one transformation net- work branch. We validate the proposed approach on two widely used pedestrian detection datasets: Caltech and CityPersons. Experimental results show that our approach achieves promising performance for both non-occluded and occluded pedestrian detection.
{"title":"Discriminative Feature Transformation for Occluded Pedestrian Detection","authors":"Chunluan Zhou, Ming Yang, Junsong Yuan","doi":"10.1109/ICCV.2019.00965","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00965","url":null,"abstract":"Despite promising performance achieved by deep con- volutional neural networks for non-occluded pedestrian de- tection, it remains a great challenge to detect partially oc- cluded pedestrians. Compared with non-occluded pedes- trian examples, it is generally more difficult to distinguish occluded pedestrian examples from background in featue space due to the missing of occluded parts. In this paper, we propose a discriminative feature transformation which en- forces feature separability of pedestrian and non-pedestrian examples to handle occlusions for pedestrian detection. Specifically, in feature space it makes pedestrian exam- ples approach the centroid of easily classified non-occluded pedestrian examples and pushes non-pedestrian examples close to the centroid of easily classified non-pedestrian ex- amples. Such a feature transformation partially compen- sates the missing contribution of occluded parts in feature space, therefore improving the performance for occluded pedestrian detection. We implement our approach in the Fast R-CNN framework by adding one transformation net- work branch. We validate the proposed approach on two widely used pedestrian detection datasets: Caltech and CityPersons. Experimental results show that our approach achieves promising performance for both non-occluded and occluded pedestrian detection.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"327 1","pages":"9556-9565"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86778241","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}
Nitin Saini, E. Price, Rahul Tallamraju, R. Enficiaud, R. Ludwig, Igor Martinovic, Aamir Ahmad, Michael J. Black
Capturing human motion in natural scenarios means moving motion capture out of the lab and into the wild. Typical approaches rely on fixed, calibrated, cameras and reflective markers on the body, significantly limiting the motions that can be captured. To make motion capture truly unconstrained, we describe the first fully autonomous outdoor capture system based on flying vehicles. We use multiple micro-aerial-vehicles(MAVs), each equipped with a monocular RGB camera, an IMU, and a GPS receiver module. These detect the person, optimize their position, and localize themselves approximately. We then develop a markerless motion capture method that is suitable for this challenging scenario with a distant subject, viewed from above, with approximately calibrated and moving cameras. We combine multiple state-of-the-art 2D joint detectors with a 3D human body model and a powerful prior on human pose. We jointly optimize for 3D body pose and camera pose to robustly fit the 2D measurements. To our knowledge, this is the first successful demonstration of outdoor, full-body, markerless motion capture from autonomous flying vehicles.
{"title":"Markerless Outdoor Human Motion Capture Using Multiple Autonomous Micro Aerial Vehicles","authors":"Nitin Saini, E. Price, Rahul Tallamraju, R. Enficiaud, R. Ludwig, Igor Martinovic, Aamir Ahmad, Michael J. Black","doi":"10.1109/ICCV.2019.00091","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00091","url":null,"abstract":"Capturing human motion in natural scenarios means moving motion capture out of the lab and into the wild. Typical approaches rely on fixed, calibrated, cameras and reflective markers on the body, significantly limiting the motions that can be captured. To make motion capture truly unconstrained, we describe the first fully autonomous outdoor capture system based on flying vehicles. We use multiple micro-aerial-vehicles(MAVs), each equipped with a monocular RGB camera, an IMU, and a GPS receiver module. These detect the person, optimize their position, and localize themselves approximately. We then develop a markerless motion capture method that is suitable for this challenging scenario with a distant subject, viewed from above, with approximately calibrated and moving cameras. We combine multiple state-of-the-art 2D joint detectors with a 3D human body model and a powerful prior on human pose. We jointly optimize for 3D body pose and camera pose to robustly fit the 2D measurements. To our knowledge, this is the first successful demonstration of outdoor, full-body, markerless motion capture from autonomous flying vehicles.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"26 1","pages":"823-832"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87004476","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 research in 4D saliency detection is limited by the deficiency of a large-scale 4D light field dataset. To address this, we introduce a new dataset to assist the subsequent research in 4D light field saliency detection. To the best of our knowledge, this is to date the largest light field dataset in which the dataset provides 1465 all-focus images with human-labeled ground truth masks and the corresponding focal stacks for every light field image. To verify the effectiveness of the light field data, we first introduce a fusion framework which includes two CNN streams where the focal stacks and all-focus images serve as the input. The focal stack stream utilizes a recurrent attention mechanism to adaptively learn to integrate every slice in the focal stack, which benefits from the extracted features of the good slices. Then it is incorporated with the output map generated by the all-focus stream to make the saliency prediction. In addition, we introduce adversarial examples by adding noise intentionally into images to help train the deep network, which can improve the robustness of the proposed network. The noise is designed by users, which is imperceptible but can fool the CNNs to make the wrong prediction. Extensive experiments show the effectiveness and superiority of the proposed model on the popular evaluation metrics. The proposed method performs favorably compared with the existing 2D, 3D and 4D saliency detection methods on the proposed dataset and existing LFSD light field dataset. The code and results can be found at https://github.com/OIPLab-DUT/ ICCV2019_Deeplightfield_Saliency. Moreover, to facilitate research in this field, all images we collected are shared in a ready-to-use manner.
{"title":"Deep Learning for Light Field Saliency Detection","authors":"Tiantian Wang, Yongri Piao, Huchuan Lu, Xiao Li, Lihe Zhang","doi":"10.1109/ICCV.2019.00893","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00893","url":null,"abstract":"Recent research in 4D saliency detection is limited by the deficiency of a large-scale 4D light field dataset. To address this, we introduce a new dataset to assist the subsequent research in 4D light field saliency detection. To the best of our knowledge, this is to date the largest light field dataset in which the dataset provides 1465 all-focus images with human-labeled ground truth masks and the corresponding focal stacks for every light field image. To verify the effectiveness of the light field data, we first introduce a fusion framework which includes two CNN streams where the focal stacks and all-focus images serve as the input. The focal stack stream utilizes a recurrent attention mechanism to adaptively learn to integrate every slice in the focal stack, which benefits from the extracted features of the good slices. Then it is incorporated with the output map generated by the all-focus stream to make the saliency prediction. In addition, we introduce adversarial examples by adding noise intentionally into images to help train the deep network, which can improve the robustness of the proposed network. The noise is designed by users, which is imperceptible but can fool the CNNs to make the wrong prediction. Extensive experiments show the effectiveness and superiority of the proposed model on the popular evaluation metrics. The proposed method performs favorably compared with the existing 2D, 3D and 4D saliency detection methods on the proposed dataset and existing LFSD light field dataset. The code and results can be found at https://github.com/OIPLab-DUT/ ICCV2019_Deeplightfield_Saliency. Moreover, to facilitate research in this field, all images we collected are shared in a ready-to-use manner.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"22 1","pages":"8837-8847"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87386933","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}
The premise of training an accurate 3D human pose estimation network is the possession of huge amount of richly annotated training data. Nonetheless, manually obtaining rich and accurate annotations is, even not impossible, tedious and slow. In this paper, we propose to exploit monocular videos to complement the training dataset for the single-image 3D human pose estimation tasks. At the beginning, a baseline model is trained with a small set of annotations. By fixing some reliable estimations produced by the resulting model, our method automatically collects the annotations across the entire video as solving the 3D trajectory completion problem. Then, the baseline model is further trained with the collected annotations to learn the new poses. We evaluate our method on the broadly-adopted Human3.6M and MPI-INF-3DHP datasets. As illustrated in experiments, given only a small set of annotations, our method successfully makes the model to learn new poses from unlabelled monocular videos, promoting the accuracies of the baseline model by about 10%. By contrast with previous approaches, our method does not rely on either multi-view imagery or any explicit 2D keypoint annotations.
{"title":"On Boosting Single-Frame 3D Human Pose Estimation via Monocular Videos","authors":"Zhi Li, Xuan Wang, Fei Wang, Peilin Jiang","doi":"10.1109/ICCV.2019.00228","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00228","url":null,"abstract":"The premise of training an accurate 3D human pose estimation network is the possession of huge amount of richly annotated training data. Nonetheless, manually obtaining rich and accurate annotations is, even not impossible, tedious and slow. In this paper, we propose to exploit monocular videos to complement the training dataset for the single-image 3D human pose estimation tasks. At the beginning, a baseline model is trained with a small set of annotations. By fixing some reliable estimations produced by the resulting model, our method automatically collects the annotations across the entire video as solving the 3D trajectory completion problem. Then, the baseline model is further trained with the collected annotations to learn the new poses. We evaluate our method on the broadly-adopted Human3.6M and MPI-INF-3DHP datasets. As illustrated in experiments, given only a small set of annotations, our method successfully makes the model to learn new poses from unlabelled monocular videos, promoting the accuracies of the baseline model by about 10%. By contrast with previous approaches, our method does not rely on either multi-view imagery or any explicit 2D keypoint annotations.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"45 1","pages":"2192-2201"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87726684","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：