arXiv 2203.046432022-03-09cs.CV

3D Dense Face Alignment with Fused Features by Aggregating CNNs and GCNs

University of Liverpool（利物浦大学）；Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences（中国科学院宁波材料技术与工程研究所）；China Science IntelliCloud Technology Co., Ltd.（中国科学智能云科技有限公司）；Remark AI UK Limited（Remark AI英国有限公司）

Yanda Meng, Xu Chen, Dongxu Gao, Yitian Zhao, Xiaoyun Yang, Yihong Qiao, Xiaowei Huang, Yalin Zheng

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

In this paper, we propose a novel multi-level aggregation network to regress the coordinates of the vertices of a 3D face from a single 2D image in an end-to-end manner. This is achieved by seamlessly combining standard convolutional neural networks (CNNs) with Graph Convolution Networks (GCNs). By iteratively and hierarchically fusing the features across different layers and stages of the CNNs and GCNs, our approach can provide a dense face alignment and 3D face reconstruction simultaneously for the benefit of direct feature learning of 3D face mesh. Experiments on several challenging datasets demonstrate that our method outperforms state-of-the-art approaches on both 2D and 3D face alignment tasks.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

DMS-GCN: Dynamic Mutiscale Spatiotemporal Graph Convolutional Networks for Human Motion Prediction

School of Automation, Beijing Institute of Technology（北京理工大学自动化学院）

Human motion prediction is an important and challenging task in many computer vision application domains. Recent work concentrates on utilizing the timing processing ability of recurrent neural networks (RNNs) to achieve smooth and reliable results in short-term prediction. However, as evidenced by previous work, RNNs suffer from errors accumulation, leading to unreliable results. In this paper, we propose a simple feed-forward deep neural network for motion prediction, which takes into account temporal smoothness and spatial dependencies between human body joints. We design a Multi-scale Spat…

2021-12-20cs.CV

Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection

Dalian University of Technology（大连理工大学）；Tiwaki Co.Ltd（Tiwaki株式会社）

Fully convolutional neural networks (FCNs) have shown outstanding performance in many dense labeling problems. One key pillar of these successes is mining relevant information from features in convolutional layers. However, how to better aggregate multi-level convolutional feature maps for salient object detection is underexplored. In this work, we present Amulet, a generic aggregating multi-level convolutional feature framework for salient object detection. Our framework first integrates multi-level feature maps into multiple resolutions, which simultaneously incorporate coarse semantics and …

2017-08-07cs.CV

Action Recognition with Kernel-based Graph Convolutional Networks

Sorbonne University（索邦大学）；CNRS（法国国家科学研究中心）；LIP6（巴黎第六大学计算机实验室）

Learning graph convolutional networks (GCNs) is an emerging field which aims at generalizing deep learning to arbitrary non-regular domains. Most of the existing GCNs follow a neighborhood aggregation scheme, where the representation of a node is recursively obtained by aggregating its neighboring node representations using averaging or sorting operations. However, these operations are either ill-posed or weak to be discriminant or increase the number of training parameters and thereby the computational complexity and the risk of overfitting. In this paper, we introduce a novel GCN framework t…

2020-12-28cs.CV

S2RC-GCN：一种用于高光谱图像复杂土地覆盖分类的空间-光谱可靠对比图卷积网络

S2RC-GCN: A Spatial-Spectral Reliable Contrastive Graph Convolutional Network for Complex Land Cover Classification Using Hyperspectral Images

School of Computer China University of Geosciences Wuhan, China；School of Geography；Information Engineering China University of Geosciences Wuhan, China；School of Management Wuhan University of Science

本文提出S2RC-GCN框架，融合1D/2D编码器提取的光谱-空间特征并引入可靠对比图卷积，在江夏高分五号复杂土地覆盖数据集上取得最佳分类性能。

2024-04-01cs.CV

GmCN: Graph Mask Convolutional Network

Anhui University（安徽大学）

Graph Convolutional Networks (GCNs) have shown very powerful for graph data representation and learning tasks. Existing GCNs usually conduct feature aggregation on a fixed neighborhood graph in which each node computes its representation by aggregating the feature representations of all its neighbors which is biased by its own representation. However, this fixed aggregation strategy is not guaranteed to be optimal for GCN based graph learning and also can be affected by some graph structure noises, such as incorrect or undesired edge connections. To address these issues, we propose a novel Gra…

2019-11-20cs.CVcs.LGcs.SI

Mul-GAD: a semi-supervised graph anomaly detection framework via aggregating multi-view information

Hainan University（海南大学）

Anomaly detection is defined as discovering patterns that do not conform to the expected behavior. Previously, anomaly detection was mostly conducted using traditional shallow learning techniques, but with little improvement. As the emergence of graph neural networks (GNN), graph anomaly detection has been greatly developed. However, recent studies have shown that GNN-based methods encounter challenge, in that no graph anomaly detection algorithm can perform generalization on most datasets. To bridge the tap, we propose a multi-view fusion approach for graph anomaly detection (Mul-GAD). The vi…

2022-12-11cs.AIcs.CV

更多相关论文收起更多论文

GCN-LASE: Towards Adequately Incorporating Link Attributes in Graph Convolutional Networks

Yuanpei College, Peking University（北京大学元培学院）；Key Laboratory of Machine Perception, Ministry of Education, Peking University（北京大学教育部机器感知重点实验室）

Graph Convolutional Networks (GCNs) have proved to be a most powerful architecture in aggregating local neighborhood information for individual graph nodes. Low-rank proximities and node features are successfully leveraged in existing GCNs, however, attributes that graph links may carry are commonly ignored, as almost all of these models simplify graph links into binary or scalar values describing node connectedness. In our paper instead, links are reverted to hypostatic relationships between entities with descriptional attributes. We propose GCN-LASE (GCN with Link Attributes and Sampling Est…

2019-05-30cs.CVcs.LGcs.SI

Pose-Guided Graph Convolutional Networks for Skeleton-Based Action Recognition

Korea University（高丽大学）

Graph convolutional networks (GCNs), which can model the human body skeletons as spatial and temporal graphs, have shown remarkable potential in skeleton-based action recognition. However, in the existing GCN-based methods, graph-structured representation of the human skeleton makes it difficult to be fused with other modalities, especially in the early stages. This may limit their scalability and performance in action recognition tasks. In addition, the pose information, which naturally contains informative and discriminative clues for action recognition, is rarely explored together with skel…

2022-10-10cs.CVeess.IVeess.SP

上下文引导的特征融合网络语义对齐

Context-Guided Semantic Alignment for Feature Fusion Networks

Department of Embedded Systems Engineering, Incheon National University（仁川国立大学嵌入式系统工程系）

提出轻量级语义对齐模块FINE，通过跨层级注意力机制利用高层上下文指导低层特征融合，并引入对齐感知令牌采样降低计算复杂度，提升目标检测精度。

2026-08-27cs.CV

GeoSpark: Sparking up Point Cloud Segmentation with Geometry Clue

University of Cambridge（剑桥大学）；HKUST(GuangZhou)（香港科技大学（广州））

Current point cloud segmentation architectures suffer from limited long-range feature modeling, as they mostly rely on aggregating information with local neighborhoods. Furthermore, in order to learn point features at multiple scales, most methods utilize a data-agnostic sampling approach to decrease the number of points after each stage. Such sampling methods, however, often discard points for small objects in the early stages, leading to inadequate feature learning. We believe these issues are can be mitigated by introducing explicit geometry clues as guidance. To this end, we propose GeoSpa…

2023-03-14cs.CV

CHITNet：用于红外与可见光图像融合的互补到和谐信息传递网络

CHITNet: A Complementary to Harmonious Information Transfer Network for Infrared and Visible Image Fusion

Kunming University of Science and Technology（昆明理工大学）

本文提出CHITNet，通过互信息传递、和谐信息获取和结构信息保持三个模块，将红外与可见光图像的互补信息转化为和谐信息，实现高质量图像融合，并在视觉与定量评估中优于现有方法。

2024-10-22cs.CV

SyncTrack4D: 多视频4D高斯点云的跨视频运动对齐与视频同步

SyncTrack4D: Cross-Video Motion Alignment and Video Synchronization for Multi-Video 4D Gaussian Splatting

University of Maryland, College Park（马里兰大学学院公园分校）；Dolby Laboratories（杜比实验室）

SyncTrack4D通过跨视频运动对齐和4D高斯点云重建，实现多视频不同步问题的高精度同步与高保真重建。

2025-12-03cs.CV

Progressive Multi-scale Consistent Network for Multi-class Fundus Lesion Segmentation

Nankai University（南开大学）

Effectively integrating multi-scale information is of considerable significance for the challenging multi-class segmentation of fundus lesions because different lesions vary significantly in scales and shapes. Several methods have been proposed to successfully handle the multi-scale object segmentation. However, two issues are not considered in previous studies. The first is the lack of interaction between adjacent feature levels, and this will lead to the deviation of high-level features from low-level features and the loss of detailed cues. The second is the conflict between the low-level an…

2022-05-31cs.CVeess.IV

MeSD：用于VideoLLM的多证据自蒸馏

MeSD: Multi-Evidence Self-Distillation for VideoLLM

UCAS（中国科学院大学）；Xingchen AGI Lab, China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd（星辰AGI实验室，中国电信人工智能科技（北京）有限公司）；BJTU（北京交通大学）；BUAA（北京航空航天大学）；ZJU（浙江大学）

MeSD提出多证据自蒸馏框架，通过三个共享参数的证据条件教师和验证引导优化，为VideoLLM提供密集token级监督，在多个视频基准上超越强化学习和自蒸馏基线。

2026-10-06cs.AIcs.CV