Suchergebnisse - grouping and shape analysis; Recognition: detection

Sparse Instance Activation for Real-Time Instance Segmentation von Cheng, Tianheng, Wang, Xinggang, Chen, Shaoyu, Zhang, Wenqiang, Zhang, Qian, Huang, Chang, Zhang, Zhaoxiang, Liu, Wenyu

“… Previously, most instance segmentation methods heavily rely on object detection and perform mask prediction based on bounding boxes or dense centers …”
Volltext

E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation von Zhang, Tao, Wei, Shiqing, Ji, Shunping

“… Contour-based instance segmentation methods have developed rapidly recently but feature rough and hand-crafted front-end contour initialization, which …”
Volltext

Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity von Wang, Weiyao, Feiszli, Matt, Wang, Heng, Malik, Jitendra, Tran, Du

“… Open-world instance segmentation is the task of grouping pixels into object instances without any pre-determined taxonomy …”
Volltext

Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers von Ke, Tsung-Wei, Hwang, Jyh-Jing, Guo, Yunhui, Wang, Xudong, Yu, Stella X.

“… Unsupervised semantic segmentation aims to discover groupings within and across images that capture object-and view-invariance of a category without external supervision …”
Volltext

CDGNet: Class Distribution Guided Network for Human Parsing von Liu, Kunliang, Choi, Ouk, Wang, Jianming, Hwang, Wonjun

“… The objective of human parsing is to partition a human in an image into constituent parts. This task involves labeling each pixel of the human image according …”
Volltext

GAT-CADNet: Graph Attention Network for Panoptic Symbol Spotting in CAD Drawings von Zheng, Zhaohua, Li, Jianfang, Zhu, Lingjie, Li, Honghua, Petzold, Frank, Tan, Ping

“… Our key contributions are three-fold: 1) the instance symbol spotting task is formulated as a subgraph detection problem and solved by predicting the adjacency matrix; 2 …”
Volltext

Medial Spectral Coordinates for 3D Shape Analysis von Rezanejad, Morteza, Khodadad, Mohammad, Mahyar, Hamidreza, Lombaert, Herve, Gruninger, Michael, Walther, Dirk, Siddiqi, Kaleem

“… In recent years there has been a resurgence of interest in our community in the shape analysis of 3D objects repre-sented by surface meshes, their voxelized interiors, or surface point clouds …”
Volltext

Neural Recognition of Dashed Curves with Gestalt Law of Continuity von Liu, Hanyuan, Li, Chengze, Liu, Xueting, Wong, Tien-Tsin

“… Dashed curve is a frequently used curve form and is widely used in various drawing and illustration applications. While humans can intuitively recognize dashed …”
Volltext

Masked-attention Mask Transformer for Universal Image Segmentation von Cheng, Bowen, Misra, Ishan, Schwing, Alexander G., Kirillov, Alexander, Girdhar, Rohit

“… (50.1 AP on COCO) and semantic segmentation (57.7 mIoU onADE20K) …”
Volltext

PatchFormer: An Efficient Point Transformer with Patch Attention von Zhang, Cheng, Wan, Haocheng, Shen, Xinyi, Wu, Zizhao

“… ) to adaptively learn a much smaller set of bases upon which the attention maps are computed. By a weighted summation upon these bases, PAT not only captures the global shape context but also achieves linear complexity to input size …”
Volltext

Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation von Park, Wonhui, Jin, Dongkwon, Kim, Chang-Su

“… Novel contour descriptors, called eigencontours, based on low-rank approximation are proposed in this paper. First, we construct a contour matrix containing …”
Volltext

SeeThroughNet: Resurrection of Auxiliary Loss by Preserving Class Probability Information von Han, Dasol, Yoo, Jaewook, Oh, Dokwan

“… Auxiliary loss is additional loss besides the main branch loss to help optimize the learning process of neural networks. In order to calculate the auxiliary …”
Volltext

RBGNet: Ray-based Grouping for 3D Object Detection von Wang, Haiyang, Shi, Shaoshuai, Yang, Ze, Fang, Rongyao, Qian, Qi, Li, Hongsheng, Schiele, Bernt, Wang, Liwei

“… In order to learn better representations of object shape to enhance cluster features for predicting 3D boxes, we propose a ray-based feature grouping module, which aggregates the point-wise features …”
Volltext

EDTER: Edge Detection with Transformer von Pu, Mengyang, Huang, Yaping, Liu, Yuming, Guan, Qingji, Ling, Haibin

“… Convolutional neural networks have made significant progresses in edge detection by progressively exploring the context and semantic features …”
Volltext

Detecting Camouflaged Object in Frequency Domain von Zhong, Yijie, Li, Bo, Tang, Lv, Kuang, Senyun, Wu, Shuang, Ding, Shouhong

“… Camouflaged object detection (COD) aims to identify objects that are perfectly embedded in their environment, which has various downstream applications in fields such as medicine, art, and agriculture …”
Volltext

Multimodal Token Fusion for Vision Transformers von Wang, Yikai, Chen, Xinghao, Cao, Lele, Huang, Wenbing, Sun, Fuchun, Wang, Yunhe

“… Many adaptations of transformers have emerged to address the single-modal vision tasks, where self-attention modules are stacked to handle input sources like …”
Volltext

A Keypoint-based Global Association Network for Lane Detection von Wang, Jinsheng, Ma, Yinchao, Huang, Shaofei, Hui, Tianrui, Wang, Fei, Qian, Chen, Zhang, Tianzhu

“… Lane detection is a challenging task that requires predicting complex topology shapes of lane lines and distinguishing different types of lanes simultaneously …”
Volltext

Dense Learning based Semi-Supervised Object Detection von Chen, Binghui, Li, Pengyu, Chen, Xiang, Wang, Biao, Zhang, Lei, Hua, Xian-Sheng

“… Semi-supervised object detection (SSOD) aims to facilitate the training and deployment of object detectors with the help of a large amount of unlabeled data …”
Volltext

BASNet: Boundary-Aware Salient Object Detection von Qin, Xuebin, Zhang, Zichen, Huang, Chenyang, Gao, Chao, Dehghan, Masood, Jagersand, Martin

“… Deep Convolutional Neural Networks have been adopted for salient object detection and achieved the state-of-the-art performance …”
Volltext

Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection von Pang, Youwei, Zhao, Xiaoqi, Xiang, Tian-Zhu, Zhang, Lihe, Lu, Huchuan

“… The recently proposed camouflaged object detection (COD) attempts to segment objects that are visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios …”
Volltext