检索结果-内蒙古大学图书馆

Frame attention networks for facial expression recognition in videos

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Meng, Debin Peng, Xiaojiang Wang, Kai Qiao, Yu Shenzhen Institutes of Advanced Technology Chinese Academy of Science Shenzhen China Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen China University of Chinese Academy of Sciences Beijing China

The video-based facial expression recognition aims to classify a given video into several basic emotions. How to integrate facial features of individual frames is crucial for this task. In this paper, we propose the Frame Attention Networks (FAN)1, to automatically highlight some discriminative frames in an end-to-end framework. The network takes a video with a variable number of face images as its input and produces a fixed-dimension representation. The whole network is composed of two modules. The feature embedding module is a deep Convolutional Neural Network (CNN) which embeds face images into feature vectors. The frame attention module learns multiple attention weights which are used to adaptively aggregate the feature vectors to form a single discriminative video representation. We conduct extensive experiments on CK+ and AFEW8.0 datasets. Our proposed FAN shows superior performance compared to other CNN based methods and achieves state-of-the-art performance on CK+. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

Building and registering parameterized 3D models of vessel trees for visualization during intervention

学校读者我要写书评

暂无评论

Building and registering parameterized 3D models of vessel t...

International Conference on pattern recognition

作者： G. Langs P. Radeva D. Rotger F. Carreras Insitute for Computer Graphics and Vision Graz University of Technology Graz Austria Pattern Recognition and Image Processing Group Vienna University of Technology Vienna Austria Computer Vision Center Universitat Autònoma de Barcelona Bellaterra Spain Hospital St. Pau Barcelona Spain

In this paper, we address the problem of multimodal registration of coronary vessels by developing a 3D parametrical model of vessel trees from computer tomography data and registering it to angiography images during intervention. Thus, the interventionist takes profit from 3D data otherwise only available before the intervention. This facilitates orientation in ambiguous radiographs, interactive visualization of all vessel structures to estimate their mutual position and navigation within the vessel system and ultimately reduces the radiation the patient and the physicians are exposed to. The model is build by exploring the branching vessel tree starting from a single position and successively expanding through the vessels guided by a local deformable surface. The result is a tree of cylindrical segments each adapted to the vessel walls that is registered to angiography images in a fast and robust way. Validation on 8 patients confirms the robustness of our method.

关键词： X-ray imaging Computed tomography Robustness Angiography Image segmentation Image reconstruction Distortion measurement Tree graphs Data visualization Radio navigation

Learning Attentive Pairwise Interaction for Fine-Grained Classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhuang, Peiqin Wang, Yali Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Fine-grained classification is a challenging problem, due to subtle differences among highly-confused categories. Most approaches address this difficulty by learning discriminative representation of individual input image. On the other hand, humans can effectively identify contrastive clues by comparing image pairs. Inspired by this fact, this paper proposes a simple but effective Attentive Pairwise Interaction Network (API-Net), which can progressively recognize a pair of fine-grained images by interaction. Specifically, API-Net first learns a mutual feature vector to capture semantic differences in the input pair. It then compares this mutual vector with individual vectors to generate gates for each input image. These distinct gate vectors inherit mutual context on semantic differences, which allow API-Net to attentively capture contrastive clues by pairwise interaction between two images. Additionally, we train API-Net in an end-to-end manner with a score ranking regularization, which can further generalize API-Net by taking feature priorities into account. We conduct extensive experiments on five popular benchmarks in fine-grained classification. API-Net outperforms the recent SOTA methods, i.e., CUB-200-2011 (90.0%), Aircraft (93.9%), Stanford Cars (95.3%), Stanford Dogs (90.3%), and NABirds (88.1%). Copyright © 2020, The Authors. All rights reserved.

关键词： Vectors

Smallbignet: Integrating core and contextual views for video classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xianhang Wang, Yali Zhou, Zhipeng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Temporal convolution has been widely used for video classification. However, it is performed on spatio-temporal contexts in a limited view, which often weakens its capacity of learning video representation. To alleviate this problem, we propose a concise and novel SmallBig network, with the cooperation of small and big views. For the current time step, the small view branch is used to learn the core semantics, while the big view branch is used to capture the contextual semantics. Unlike traditional temporal convolution, the big view branch can provide the small view branch with the most activated video features from a broader 3D receptive field. Via aggregating such big-view contexts, the small view branch can learn more robust and discriminative spatio-temporal representations for video classification. Furthermore, we propose to share convolution in the small and big view branch, which improves model compactness as well as alleviates overfitting. As a result, our SmallBigNet achieves a comparable model size like 2D CNNs, while boosting accuracy like 3D CNNs. We conduct extensive experiments on the large-scale video benchmarks, e.g., Kinetics400, Something-Something V1 and V2. Our SmallBig network outperforms a number of recent state-of-the-art approaches, in terms of accuracy and/or efficiency. The codes and models will be available on https://***/xhl-video/SmallBigNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

Enhanced quadratic video interpolation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Yihao Xie, Liangbin Siyao, Li Sun, Wenxiu Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China SenseTime Research

With the prosperity of digital video industry, video frame interpolation has arisen continuous attention in computer vision community and become a new upsurge in industry. Many learning-based methods have been proposed and achieved progressive results. Among them, a recent algorithm named quadratic video interpolation (QVI) achieves appealing performance. It exploits higher-order motion information (e.g. acceleration) and successfully models the estimation of interpolated flow. However, its produced intermediate frames still contain some unsatisfactory ghosting, artifacts and inaccurate motion, especially when large and complex motion occurs. In this work, we further improve the performance of QVI from three facets and propose an enhanced quadratic video interpolation (EQVI) model. In particular, we adopt a rectified quadratic flow prediction (RQFP) formulation with least squares method to estimate the motion more accurately. Complementary with image pixel-level blending, we introduce a residual contextual synthesis network (RCSN) to employ contextual information in high-dimensional feature space, which could help the model handle more complicated scenes and motion patterns. Moreover, to further boost the performance, we devise a novel multi-scale fusion network (MS-Fusion) which can be regarded as a learnable augmentation process. The proposed EQVI model won the first place in the AIM2020 Video Temporal Super-Resolution Challenge. Codes are available at https://***/lyh-18/EQVI. Copyright © 2020, The Authors. All rights reserved.

关键词： Least squares approximations

Med-DANet V2: A Flexible Dynamic Architecture for Efficient Medical Volumetric Segmentation

学校读者我要写书评

暂无评论

Med-DANet V2: A Flexible Dynamic Architecture for Efficient ...

IEEE Workshop on Applications of computer vision (WACV)

作者： Haoran Shen Yifu Zhang Wenxuan Wang Chen Chen Jing Liu Shanshan Song Jiangyun Li School of Automation and Electrical Engineering University of Science and Technology Beijing Center for Research in Computer Vision University of Central Florida National Lab of Pattern Recognition Institute of Automation Chinese Academy of Sciences

Recent works have shown that the computational efficiency of 3D medical image (e.g. CT and MRI) segmentation can be impressively improved by dynamic inference based on slice-wise complexity. As a pioneering work, a dynamic architecture network for medical volumetric segmentation (i.e. Med-DANet [44]) has achieved a favorable accuracy and efficiency trade-off by dynamically selecting a suitable 2D candidate model from the pre-defined model bank for different slices. However, the issues of incomplete data analysis, high training costs, and the two-stage pipeline in Med-DANet require further improvement. To this end, this paper further explores a unified formulation of the dynamic inference framework from the perspective of both the data itself and the model structure. For each slice of the input volume, our proposed method dynamically selects an important foreground region for segmentation based on the policy generated by our Decision Network and Crop Position Network. Besides, we propose to insert a stage-wise quantization selector to the employed segmentation model (e.g. U-Net) for dynamic architecture adapting. Extensive experiments on BraTS 2019 and 2020 show that our method achieves comparable or better performance than previous state-of-the-art methods with much less model complexity. Compared with previous methods Med-DANet and TransBTS with dynamic and static architecture respectively, our framework improves the model efficiency by up to nearly 4.1 and 17.3 times with comparable segmentation results on BraTS 2019. Code will be available at https://***/Rubics-Xuan/Med-DANet.

关键词：

Learning to predict context-adaptive convolution for semantic segmentation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Jianbo He, Junjun Ren, Jimmy S. Qiao, Yu Li, Hongsheng CUHK-SenseTime Joint Laboratory Chinese University of Hong Kong Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SenseTime Research

Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods [34] demonstrate that using global context for re-weighting feature channels can effectively improve the accuracy of semantic segmentation. However, the globally-sharing feature re-weighting vector might not be optimal for regions of different classes in the input image. In this paper, we propose a Context-adaptive Convolution Network (CaC-Net) to predict a spatially-varying feature weighting vector for each spatial location of the semantic feature maps. In CaC-Net, a set of context-adaptive convolution kernels are predicted from the global contextual information in a parameter-efficient manner. When used for convolution with the semantic feature maps, the predicted convolutional kernels can generate the spatially-varying feature weighting factors capturing both global and local contextual information. Comprehensive experimental results show that our CaC-Net achieves superior segmentation performance on three public datasets, PASCAL Context, PASCAL VOC 2012 and ADE20K. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

DegAE: A New Pretraining Paradigm for Low-Level vision

学校读者我要写书评

暂无评论

DegAE: A New Pretraining Paradigm for Low-Level Vision

Conference on computer vision and pattern recognition (CVPR)

作者： Yihao Liu Jingwen He Jinjin Gu Xiangtao Kong Yu Qiao Chao Dong Shanghai Artificial Intelligence Laboratory ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences The University of Sydney

Self-supervised pretraining has achieved remarkable success in high-level vision, but its application in low-level vision remains ambiguous and not well-established. What is the primitive intention of pretraining? What is the core problem of pretraining in low-level vision? In this paper, we aim to answer these essential questions and establish a new pretraining scheme for low-level vision. Specifically, we examine previous pretraining methods in both high-level and low-level vision, and categorize current low-level vision tasks into two groups based on the difficulty of data acqui-sition: low-cost and high-cost tasks. Existing literature has mainly focused on pretraining for low-cost tasks, where the observed performance improvement is often limited. However, we argue that pretraining is more significant for high-cost tasks, where data acquisition is more challenging. To learn a general low-level vision representation that can improve the performance of various tasks, we propose a new pretraining paradigm called degradation autoencoder (De-gAE). DegAE follows the philosophy of designing pretext task for self-supervised pretraining and is elaborately tai-lored to low-level vision. With DegAE pretraining, SwinIR achieves a 6.88dB performance gain on image dehaze task, while Uformer obtains 3.22dB and 0.54dB improvement on dehaze and derain tasks, respectively.

关键词：

Learning dynamical human-joint affinity for 3D pose estimation in videos

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Junhao Wang, Yali Zhou, Zhipeng Luan, Tianyu Wang, Zhe Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of California Irvine United States Shanghai AI Laboratory Shanghai China

Graph Convolution Network (GCN) has been successfully used for 3D human pose estimation in videos. However, it is often built on the fixed human-joint affinity, according to human skeleton. This may reduce adaptation capacity of GCN to tackle complex spatio-temporal pose variations in videos. To alleviate this problem, we propose a novel Dynamical Graph Network (DG-Net), which can dynamically identify human-joint affinity, and estimate 3D pose by adaptively learning spatial/temporal joint relations from videos. Different from traditional graph convolution, we introduce Dynamical Spatial/Temporal Graph convolution (DSG/DTG) to discover spatial/temporal human-joint affinity for each video exemplar, depending on spatial distance/temporal movement similarity between human joints in this video. Hence, they can effectively understand which joints are spatially closer and/or have consistent motion, for reducing depth ambiguity and/or motion uncertainty when lifting 2D pose to 3D pose. We conduct extensive experiments on three popular benchmarks, e.g., Human3.6M, HumanEva-I, and MPI-INF-3DHP, where DG-Net outperforms a number of recent SOTA approaches with fewer input frames and model size. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution