Monocular face reconstruction is a challenging task in computer vision, which aims to recover 3D face geometry from a single RGB face image. Recently, deep learning based methods have achieved great improvements on monocular face reconstruction. However, for deep learning-based methods to reach optimal performance, it is paramount to have large-scale training images with ground-truth 3D face geometry, which is generally difficult for human to annotate. To tackle this problem, we propose a semi-supervised monocular reconstruction method, which jointly optimizes a shape-preserved domain-transfer CycleGAN and a shape estimation network. The framework is semi-supervised trained with 3D rendered images with ground-truth shapes and in-the-wild face images without any extra annotation. The CycleGAN network transforms all realistic images to have the rendered style and is end-to-end trained within the overall framework. This is the key difference compared with existing CycleGAN-based learning methods, which just used CycleGAN as a separate training sample generator. Novel landmark consistency loss and edge-aware shape estimation loss are proposed for our two networks to jointly solve the challenging face reconstruction problem. Extensive experiments on public face reconstruction datasets demonstrate the effectiveness of our overall method as well as the individual components.
{"title":"Semi-Supervised Monocular 3D Face Reconstruction With End-to-End Shape-Preserved Domain Transfer","authors":"Jingtan Piao, C. Qian, Hongsheng Li","doi":"10.1109/ICCV.2019.00949","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00949","url":null,"abstract":"Monocular face reconstruction is a challenging task in computer vision, which aims to recover 3D face geometry from a single RGB face image. Recently, deep learning based methods have achieved great improvements on monocular face reconstruction. However, for deep learning-based methods to reach optimal performance, it is paramount to have large-scale training images with ground-truth 3D face geometry, which is generally difficult for human to annotate. To tackle this problem, we propose a semi-supervised monocular reconstruction method, which jointly optimizes a shape-preserved domain-transfer CycleGAN and a shape estimation network. The framework is semi-supervised trained with 3D rendered images with ground-truth shapes and in-the-wild face images without any extra annotation. The CycleGAN network transforms all realistic images to have the rendered style and is end-to-end trained within the overall framework. This is the key difference compared with existing CycleGAN-based learning methods, which just used CycleGAN as a separate training sample generator. Novel landmark consistency loss and edge-aware shape estimation loss are proposed for our two networks to jointly solve the challenging face reconstruction problem. Extensive experiments on public face reconstruction datasets demonstrate the effectiveness of our overall method as well as the individual components.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"11 1","pages":"9397-9406"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89790340","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}
Recognizing actions from limited preliminary video observations has seen considerable recent progress. Typically, however, such progress has been had without explicitly modeling fine-grained motion evolution as a potentially valuable information source. In this study, we address this task by investigating how action patterns evolve over time in a spatial feature space. There are three key components to our system. First, we work with intermediate-layer ConvNet features, which allow for abstraction from raw data, while retaining spatial layout, which is sacrificed in approaches that rely on vectorized global representations. Second, instead of propagating features per se, we propagate their residuals across time, which allows for a compact representation that reduces redundancy while retaining essential information about evolution over time. Third, we employ a Kalman filter to combat error build-up and unify across prediction start times. Extensive experimental results on the JHMDB21, UCF101 and BIT datasets show that our approach leads to a new state-of-the-art in action prediction.
{"title":"Spatiotemporal Feature Residual Propagation for Action Prediction","authors":"He Zhao, Richard P. Wildes","doi":"10.1109/ICCV.2019.00710","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00710","url":null,"abstract":"Recognizing actions from limited preliminary video observations has seen considerable recent progress. Typically, however, such progress has been had without explicitly modeling fine-grained motion evolution as a potentially valuable information source. In this study, we address this task by investigating how action patterns evolve over time in a spatial feature space. There are three key components to our system. First, we work with intermediate-layer ConvNet features, which allow for abstraction from raw data, while retaining spatial layout, which is sacrificed in approaches that rely on vectorized global representations. Second, instead of propagating features per se, we propagate their residuals across time, which allows for a compact representation that reduces redundancy while retaining essential information about evolution over time. Third, we employ a Kalman filter to combat error build-up and unify across prediction start times. Extensive experimental results on the JHMDB21, UCF101 and BIT datasets show that our approach leads to a new state-of-the-art in action prediction.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"40 1","pages":"7002-7011"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90274479","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}
Attribution is the problem of finding which parts of an image are the most responsible for the output of a deep neural network. An important family of attribution methods is based on measuring the effect of perturbations applied to the input image, either via exhaustive search or by finding representative perturbations via optimization. In this paper, we discuss some of the shortcomings of existing approaches to perturbation analysis and address them by introducing the concept of extremal perturbations, which are theoretically grounded and interpretable. We also introduce a number of technical innovations to compute these extremal perturbations, including a new area constraint and a parametric family of smooth perturbations, which allow us to remove all tunable weighing factors from the optimization problem. We analyze the effect of perturbations as a function of their area, demonstrating excellent sensitivity to the spatial properties of the network under stimulation. We also extend perturbation analysis to the intermediate layers of a deep neural network. This application allows us to show how compactly an image can be represented (in terms of the number of channels it requires). We also demonstrate that the consistency with which images of a given class rely on the same intermediate channel correlates well with class accuracy.
{"title":"Understanding Deep Networks via Extremal Perturbations and Smooth Masks","authors":"Ruth Fong, Mandela Patrick, A. Vedaldi","doi":"10.1109/ICCV.2019.00304","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00304","url":null,"abstract":"Attribution is the problem of finding which parts of an image are the most responsible for the output of a deep neural network. An important family of attribution methods is based on measuring the effect of perturbations applied to the input image, either via exhaustive search or by finding representative perturbations via optimization. In this paper, we discuss some of the shortcomings of existing approaches to perturbation analysis and address them by introducing the concept of extremal perturbations, which are theoretically grounded and interpretable. We also introduce a number of technical innovations to compute these extremal perturbations, including a new area constraint and a parametric family of smooth perturbations, which allow us to remove all tunable weighing factors from the optimization problem. We analyze the effect of perturbations as a function of their area, demonstrating excellent sensitivity to the spatial properties of the network under stimulation. We also extend perturbation analysis to the intermediate layers of a deep neural network. This application allows us to show how compactly an image can be represented (in terms of the number of channels it requires). We also demonstrate that the consistency with which images of a given class rely on the same intermediate channel correlates well with class accuracy.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"40 1","pages":"2950-2958"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78098778","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}
Heatmap regression-based models have significantly advanced the progress of facial landmark detection. However, the lack of structural constraints always generates inaccurate heatmaps resulting in poor landmark detection performance. While hierarchical structure modeling methods have been proposed to tackle this issue, they all heavily rely on manually designed tree structures. The designed hierarchical structure is likely to be completely corrupted due to the missing or inaccurate prediction of landmarks. To the best of our knowledge, in the context of deep learning, no work before has investigated how to automatically model proper structures for facial landmarks, by discovering their inherent relations. In this paper, we propose a novel Hierarchical Structured Landmark Ensemble (HSLE) model for learning robust facial landmark detection, by using it as the structural constraints. Different from existing approaches of manually designing structures, our proposed HSLE model is constructed automatically via discovering the most robust patterns so HSLE has the ability to robustly depict both local and holistic landmark structures simultaneously. Our proposed HSLE can be readily plugged into any existing facial landmark detection baselines for further performance improvement. Extensive experimental results demonstrate our approach significantly outperforms the baseline by a large margin to achieve a state-of-the-art performance.
{"title":"Learning Robust Facial Landmark Detection via Hierarchical Structured Ensemble","authors":"Xu Zou, Sheng Zhong, Luxin Yan, Xiangyu Zhao, Jiahuan Zhou, Ying Wu","doi":"10.1109/ICCV.2019.00023","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00023","url":null,"abstract":"Heatmap regression-based models have significantly advanced the progress of facial landmark detection. However, the lack of structural constraints always generates inaccurate heatmaps resulting in poor landmark detection performance. While hierarchical structure modeling methods have been proposed to tackle this issue, they all heavily rely on manually designed tree structures. The designed hierarchical structure is likely to be completely corrupted due to the missing or inaccurate prediction of landmarks. To the best of our knowledge, in the context of deep learning, no work before has investigated how to automatically model proper structures for facial landmarks, by discovering their inherent relations. In this paper, we propose a novel Hierarchical Structured Landmark Ensemble (HSLE) model for learning robust facial landmark detection, by using it as the structural constraints. Different from existing approaches of manually designing structures, our proposed HSLE model is constructed automatically via discovering the most robust patterns so HSLE has the ability to robustly depict both local and holistic landmark structures simultaneously. Our proposed HSLE can be readily plugged into any existing facial landmark detection baselines for further performance improvement. Extensive experimental results demonstrate our approach significantly outperforms the baseline by a large margin to achieve a state-of-the-art performance.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"141-150"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78522419","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 16.2-million frame (50-hour) multimodal dataset of two-person face-to-face spontaneous conversations. Our dataset features synchronized body and finger motion as well as audio data. To the best of our knowledge, it represents the largest motion capture and audio dataset of natural conversations to date. The statistical analysis verifies strong intraperson and interperson covariance of arm, hand, and speech features, potentially enabling new directions on data-driven social behavior analysis, prediction, and synthesis. As an illustration, we propose a novel real-time finger motion synthesis method: a temporal neural network innovatively trained with an inverse kinematics (IK) loss, which adds skeletal structural information to the generative model. Our qualitative user study shows that the finger motion generated by our method is perceived as natural and conversation enhancing, while the quantitative ablation study demonstrates the effectiveness of IK loss.
{"title":"Talking With Hands 16.2M: A Large-Scale Dataset of Synchronized Body-Finger Motion and Audio for Conversational Motion Analysis and Synthesis","authors":"Gilwoo Lee, Zhiwei Deng, Shugao Ma, Takaaki Shiratori, S. Srinivasa, Yaser Sheikh","doi":"10.1109/ICCV.2019.00085","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00085","url":null,"abstract":"We present a 16.2-million frame (50-hour) multimodal dataset of two-person face-to-face spontaneous conversations. Our dataset features synchronized body and finger motion as well as audio data. To the best of our knowledge, it represents the largest motion capture and audio dataset of natural conversations to date. The statistical analysis verifies strong intraperson and interperson covariance of arm, hand, and speech features, potentially enabling new directions on data-driven social behavior analysis, prediction, and synthesis. As an illustration, we propose a novel real-time finger motion synthesis method: a temporal neural network innovatively trained with an inverse kinematics (IK) loss, which adds skeletal structural information to the generative model. Our qualitative user study shows that the finger motion generated by our method is perceived as natural and conversation enhancing, while the quantitative ablation study demonstrates the effectiveness of IK loss.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"14 1","pages":"763-772"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75228908","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}
Stray light (flare) is formed inside cameras by internal reflections between optical elements. We point out a flare effect of significant magnitude and implication to snapshot hyperspectral imagers. Recent technologies enable placing interference-based filters on individual pixels in imaging sensors. These filters have narrow transmission bands around custom wavelengths and high transmission efficiency. Cameras using arrays of such filters are compact, robust and fast. However, as opposed to traditional broad-band filters, which often absorb unwanted light, narrow band-pass interference filters reflect non-transmitted light. This is a source of very significant flare which biases hyperspectral measurements. The bias in any pixel depends on spectral content in other pixels. We present a theoretical image formation model for this effect, and quantify it through simulations and experiments. In addition, we test deflaring of signals affected by such flare.
{"title":"Flare in Interference-Based Hyperspectral Cameras","authors":"Eden Sassoon, T. Treibitz, Y. Schechner","doi":"10.1109/ICCV.2019.01027","DOIUrl":"https://doi.org/10.1109/ICCV.2019.01027","url":null,"abstract":"Stray light (flare) is formed inside cameras by internal reflections between optical elements. We point out a flare effect of significant magnitude and implication to snapshot hyperspectral imagers. Recent technologies enable placing interference-based filters on individual pixels in imaging sensors. These filters have narrow transmission bands around custom wavelengths and high transmission efficiency. Cameras using arrays of such filters are compact, robust and fast. However, as opposed to traditional broad-band filters, which often absorb unwanted light, narrow band-pass interference filters reflect non-transmitted light. This is a source of very significant flare which biases hyperspectral measurements. The bias in any pixel depends on spectral content in other pixels. We present a theoretical image formation model for this effect, and quantify it through simulations and experiments. In addition, we test deflaring of signals affected by such flare.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"15 1","pages":"10173-10181"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75269860","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}
Single-frame object detectors perform well on videos sometimes, even without temporal context. However, challenges such as occlusion, motion blur, and rare poses of objects are hard to resolve without temporal awareness. Thus, there is a strong need to improve video object detection by considering long-range temporal dependencies. In this paper, we present a light-weight modification to a single-frame detector that accounts for arbitrary long dependencies in a video. It improves the accuracy of a single-frame detector significantly with negligible compute overhead. The key component of our approach is a novel temporal relation module, operating on object proposals, that learns the similarities between proposals from different frames and selects proposals from past and/or future to support current proposals. Our final “causal" model, without any offline post-processing steps, runs at a similar speed as a single-frame detector and achieves state-of-the-art video object detection on ImageNet VID dataset.
{"title":"Leveraging Long-Range Temporal Relationships Between Proposals for Video Object Detection","authors":"Mykhailo Shvets, Wei Liu, A. Berg","doi":"10.1109/ICCV.2019.00985","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00985","url":null,"abstract":"Single-frame object detectors perform well on videos sometimes, even without temporal context. However, challenges such as occlusion, motion blur, and rare poses of objects are hard to resolve without temporal awareness. Thus, there is a strong need to improve video object detection by considering long-range temporal dependencies. In this paper, we present a light-weight modification to a single-frame detector that accounts for arbitrary long dependencies in a video. It improves the accuracy of a single-frame detector significantly with negligible compute overhead. The key component of our approach is a novel temporal relation module, operating on object proposals, that learns the similarities between proposals from different frames and selects proposals from past and/or future to support current proposals. Our final “causal\" model, without any offline post-processing steps, runs at a similar speed as a single-frame detector and achieves state-of-the-art video object detection on ImageNet VID dataset.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"31 1","pages":"9755-9763"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75711059","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}
Current state-of-the-art approaches for lip reading are based on sequence-to-sequence architectures that are designed for natural machine translation and audio speech recognition. Hence, these methods do not fully exploit the characteristics of the lip dynamics, causing two main drawbacks. First, the short-range temporal dependencies, which are critical to the mapping from lip images to visemes, receives no extra attention. Second, local spatial information is discarded in the existing sequence models due to the use of global average pooling (GAP). To well solve these drawbacks, we propose a Temporal Focal block to sufficiently describe short-range dependencies and a Spatio-Temporal Fusion Module (STFM) to maintain the local spatial information and to reduce the feature dimensions as well. From the experiment results, it is demonstrated that our method achieves comparable performance with the state-of-the-art approach using much less training data and much lighter Convolutional Feature Extractor. The training time is reduced by 12 days due to the convolutional structure and the local self-attention mechanism.
{"title":"Spatio-Temporal Fusion Based Convolutional Sequence Learning for Lip Reading","authors":"Xingxuan Zhang, Feng Cheng, Shilin Wang","doi":"10.1109/ICCV.2019.00080","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00080","url":null,"abstract":"Current state-of-the-art approaches for lip reading are based on sequence-to-sequence architectures that are designed for natural machine translation and audio speech recognition. Hence, these methods do not fully exploit the characteristics of the lip dynamics, causing two main drawbacks. First, the short-range temporal dependencies, which are critical to the mapping from lip images to visemes, receives no extra attention. Second, local spatial information is discarded in the existing sequence models due to the use of global average pooling (GAP). To well solve these drawbacks, we propose a Temporal Focal block to sufficiently describe short-range dependencies and a Spatio-Temporal Fusion Module (STFM) to maintain the local spatial information and to reduce the feature dimensions as well. From the experiment results, it is demonstrated that our method achieves comparable performance with the state-of-the-art approach using much less training data and much lighter Convolutional Feature Extractor. The training time is reduced by 12 days due to the convolutional structure and the local self-attention mechanism.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"71 1","pages":"713-722"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74700988","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}
Zheng Tang, M. Naphade, Stan Birchfield, Jonathan Tremblay, William Hodge, Ratnesh Kumar, Shuo Wang, Xiaodong Yang
In comparison with person re-identification (ReID), which has been widely studied in the research community, vehicle ReID has received less attention. Vehicle ReID is challenging due to 1) high intra-class variability (caused by the dependency of shape and appearance on viewpoint), and 2) small inter-class variability (caused by the similarity in shape and appearance between vehicles produced by different manufacturers). To address these challenges, we propose a Pose-Aware Multi-Task Re-Identification (PAMTRI) framework. This approach includes two innovations compared with previous methods. First, it overcomes viewpoint-dependency by explicitly reasoning about vehicle pose and shape via keypoints, heatmaps and segments from pose estimation. Second, it jointly classifies semantic vehicle attributes (colors and types) while performing ReID, through multi-task learning with the embedded pose representations. Since manually labeling images with detailed pose and attribute information is prohibitive, we create a large-scale highly randomized synthetic dataset with automatically annotated vehicle attributes for training. Extensive experiments validate the effectiveness of each proposed component, showing that PAMTRI achieves significant improvement over state-of-the-art on two mainstream vehicle ReID benchmarks: VeRi and CityFlow-ReID.
{"title":"PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data","authors":"Zheng Tang, M. Naphade, Stan Birchfield, Jonathan Tremblay, William Hodge, Ratnesh Kumar, Shuo Wang, Xiaodong Yang","doi":"10.1109/ICCV.2019.00030","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00030","url":null,"abstract":"In comparison with person re-identification (ReID), which has been widely studied in the research community, vehicle ReID has received less attention. Vehicle ReID is challenging due to 1) high intra-class variability (caused by the dependency of shape and appearance on viewpoint), and 2) small inter-class variability (caused by the similarity in shape and appearance between vehicles produced by different manufacturers). To address these challenges, we propose a Pose-Aware Multi-Task Re-Identification (PAMTRI) framework. This approach includes two innovations compared with previous methods. First, it overcomes viewpoint-dependency by explicitly reasoning about vehicle pose and shape via keypoints, heatmaps and segments from pose estimation. Second, it jointly classifies semantic vehicle attributes (colors and types) while performing ReID, through multi-task learning with the embedded pose representations. Since manually labeling images with detailed pose and attribute information is prohibitive, we create a large-scale highly randomized synthetic dataset with automatically annotated vehicle attributes for training. Extensive experiments validate the effectiveness of each proposed component, showing that PAMTRI achieves significant improvement over state-of-the-art on two mainstream vehicle ReID benchmarks: VeRi and CityFlow-ReID.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"37 1","pages":"211-220"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73719911","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：