口头报告
建议PPT尺寸：16:9
会议图片素材下载：
LOGO.png，PRCV2022.png
标注⭐的论文为最佳论文候选
论文ID：CMT系统中的Paper ID
| 口头报告1：文字识别与文本理解 | |||
| 时间：12月25日
14:20-15:20 地点：分会场1 |
|||
| 时间 | 论文ID | 报告题目 | 报告人 |
| 14:20-14:32 | 44 | Handwritten Mathematical Expression Recognition via GCAttention-Based Encoder and Bidirectional Mutual Learning Transformer | Han, Xiaoxiang*; Liu, Qiaohong; Han, Ziqi; Lin, Yuanjie; Xu, Naiyue |
| 14:32-14:44 | 270 | TMCR: A Twin Matching Networks for Chinese Scene Text Retrieval | Peng, Zhiheng; Shao, Ming; Xia, Siyu* |
| 14:44-14:56 | 394 | Efficient License Plate Recognition via Parallel Position-aware Attention | Wang, Tianxiang; Wang, Wenzhong*; Li, Chenglong; Tang, Jin |
| 14:56-15:08 | 407⭐ | Anchor-Free Location Refinement Network for Small License Plate Detection | Li, Zhen-Jia*; Chen, Song-Lu; Qi, Liu; Chen, Feng; Yin, Xu-Cheng |
| 15:08-15:20 | 505 | Math Word Problem Generation with Memory Retrieval | Wang, Xiaowei; QIN, Wei; Hu, Zhenzhen*; Wang, Lei; Lan, Yunshi; Hong, Richang |
| 口头报告2：生物特征识别与安全 | |||
| 时间：12月25日
14:10-15:10 地点：分会场2 |
|||
| 时间 | 论文ID | 报告题目 | 报告人 |
| 14:10-14:22 | 230⭐ | Rider Re-identification Based on Pyramid Attention | Li, Jiaze; Liu, Bin* |
| 14:22-14:34 | 300⭐ | Weighted Graph Based Feature Representation for Finger-Vein Recognition | Ye, Ziyun; Zhao, Zihao; Wen, Mengna; Yang, Jinfeng* |
| 14:34-14:46 | 369 | Self-Supervised Face Anti-Spoofing via Anti-Contrastive Learning | Cao, Jiajiong; Liu, Yufan*; Ding, Jingting; Li, Liang |
| 14:46-15:58 | 403⭐ | Attributes based Visible-Infrared Person Re-identification | Zheng, Aihua; Feng, Mengya; Pan, Peng; Jiang, Bo; Luo, Bin* |
| 15:58-15:10 | 430 | Part-based Multi-Scale Attention Network for Text-based Person Search | Wang, Yubin; Qi, Ding; zhao , cairong* |
| 口头报告3：高分与遥感目标分析 | |||
| 时间：12月25日
14:20-15:20 地点：分会场3 |
|||
| 时间 | 论文ID | 报告题目 | 报告人 |
| 14:20-14:32 | 96 | High Spatial Resolution Remote Sensing Imagery Classification Based on Markov Random Field Model Integrating Granularity and Semantic Features | Wang, Jun*; Dai, Qinling; Wang, Leiguang; Zhao, Yili; Fu, Haoyu H; Zhang, Yue |
| 14:32-14:44 | 172⭐ | SUDANet:A Siamese UNet with Dense Attention Mechanism for Remote Sensing Image Change Detection | Sun, Chengzhe*; Du , Chun; Wu, Jiangjiang; Chen, Hao |
| 14:44-14:56 | 297 | Feature Difference Enhancement Fusion for Remote Sensing Image Change Detection | Hu, Renjie*; Pei, Gensheng; Peng, Pai; Chen, Tao; Yao, Yazhou |
| 14:56-15:08 | 443⭐ | Hyperspectral and Multispectral Image Fusion Based on Unsupervised Feature Mixing and Reconstruction Network | Zhang, Rui; Fu, Peng*; Geng, Leilei; Sun, Quansen |
| 15:08-15:20 | 592 | Transmission tower detection algorithm based on feature-enhanced convolutional network in remote sensing image | zhengpeng, zhang*; Xie, Xinyu; chenggen, song; dong, dai; lijing, bu |
| 口头报告4：视觉分析与理解 | |||
| 时间：12月25日
14:20-15:20 地点：分会场4 |
|||
| 时间 | 论文ID | 报告题目 | 报告人 |
| 14:20-14:32 | 196⭐ | FOV Recognizer: Telling the Field of View of Movie Shots | Jin, Xin; Fan, Chenyu; Wang, Biao; Bo, Yihang*; Pan, Xinzhe; Jia, Zihan; Zhuo, Ya; Zhang , Runqi; Cui, Shuai |
| 14:32-14:44 | 289⭐ | Harnessing Multi-Semantic Hypergraph for Few-Shot Learning | Chen, Hao; Li, Linyan; Xia, Zhenping; Lyu, Fan; Zhao, Liuqing; Huang, Kaizhu; Feng, Wei; Hu, Fuyuan* |
| 14:44-14:56 | 495⭐ | YFormer: a New Transformer Architecture for Video-query Based Video Moment Retrieval | Huo, Shuwei; Zhou, Yuan*; Wang, Haiyang |
| 14:56-15:08 | 587⭐ | JoinTW: A Joint Image-to-Image Translation and Watermarking Method | Zhao, Xiaohan*; Wang, Yunhong; Yang, Ruijie; Guo, Yuanfang |
| 15:08-15:20 | 620⭐ | CLIP Meets Video Captioning: Concept-Aware Representation Learning Does Matter | Yang, Bang; Zhang, Tong; Zou, Yuexian* |
| 口头报告5：机器学习方法与建模 | |||
| 时间：12月26日
14:10–15:10 地点：分会场1 |
|||
| 时间 | 论文ID | 报告题目 | 报告人 |
| 14:10-14:22 | 194 | Enhancing Transferability of Adversarial Examples with Spatial Momentum | Wang, Guoqiu; Yan, Huanqian; Wei, Xingxing* |
| 14:22-14:34 | 286 | Adaptive Open Set Recognition with Multi-Modal Joint Metric Learning | Fu, Yimin*; Liu, Zhunga; Yang, Yanbo; Xu, Linfeng; Lan, Hua |
| 14:34-14:46 | 399⭐ | Every Corporation Owns Its Structure: Corporate Credit Ratings via Graph Neural Networks | Feng, Bojing*; Xu, Haonan; Xue, Wenfang |
| 14:46-14:58 | 553 | General High-Pass Convolution: A Novel Convolutional Layer for Image Manipulation Detection | Tang, Zecheng; Liu, Yang* |
| 14:58-15:10 | 573 | BiTMulV: Bidirectional-Decoding based Transformer With Multi-View Visual Representation for Image Captioning | Yu, Qiankun*; Wang, Xuekui; Wang, Dong; Chu, Xu; Liu, Bing; Liu, Peng |
| 口头报告6：人体与交通场景理解 | |||
| 时间：12月26日
14:10–15:10 地点：分会场2 |
|||
| 时间 | 论文ID | 报告题目 | 报告人 |
| 14:10-14:22 | 99 | A Single-pathway Biomimetic Model for Potential Collision Prediction | zhang, song; lei, guodong; Liang, Xuefeng* |
| 14:22-14:34 | 158 | Locally Geometry-Aware Improvements of LOP for Efficient Skeleton Extraction | Fang, Xianyong*; Hu, Lingzhi; Ye, Fan; Wang, Linbo |
| 14:34-14:46 | 175 | Dual-rank attention module for fine-grained vehicle model recognition | Cai, Wen; Zhu, Wenjia; Cheng, Bo; Xu, Longdao; Yu, Ye*; Lu, Qiang; Jia, Wei |
| 14:46-14:58 | 346⭐ | KITPose: Keypoint-Interactive Transformer for Animal Pose Estimation | Rao, Jiyong; Song, Xiaoning; Xu, Tianyang*; Feng, Zhenhua |
| 14:58-15:10 | 367 | Stochastic Navigation Command Matching for Imitation Learning of a Driving Policy | Meng, Xiangning*; Xue, Jianru; Zhao, Kang; Li, Gengxin; Wu, Mengsen |
| 口头报告7：医学图像分析 | |||
| 时间：12月26日
14:10–15:10 地点：分会场3 |
|||
| 时间 | 论文ID | 报告题目 | 报告人 |
| 14:10-14:22 | 109⭐ | DIT-NET: Joint Deformable Network and Intra-class Transfer GAN for cross-domain 3D Neonatal Brain MRI segmentation | Li, Bo*; You, Xinge; Peng, Qinmu; Jing, Wang; Yang, Chuanwu |
| 14:22-14:34 | 152⭐ | Multi-Scale Multi-Target Domain Adaptation for Angle Closure Classification | Qiu, Zhen; Zhang, Yifan; Li, Fei; Zhang, Xiulan; Xu, Yanwu; Tan, Mingkui* |
| 14:34-14:46 | 182⭐ | Automatic glottis segmentation method based on lightweight U-net | Huang, Xiangyu; Deng, Junjie; Wang, Xi; Zhuang, Peiyun; Huang, Lianfen; Zhao, Caidan* |
| 14:46-14:58 | 489⭐ | Semi-supervised Medical Image Segmentation with Semantic Distance Distribution Consistency Learning | Liu, Linhu*; Tian, Jiang; shi, zhongchao; Fan, Jianping |
| 14:58-15:10 | 507⭐ | MultiGAN: multi-domain image translation from OCT to OCTA | Pan, Bing; Ji, Zexuan*; Chen, Qiang |
| 口头报告8：目标检测与跟踪 | |||
| 时间：12月26日
14:10–15:10 地点：分会场4 |
|||
| 时间 | 论文ID | 报告题目 | 报告人 |
| 14:10-14:22 | 240 | Few-Shot Object Detection Based On Latent Knowledge Representation | Cao, Yifeng*; Duan, Lijuan; Liu, Zhaoying; wang, wenjian; Liang, Fangfang |
| 14:22-14:34 | 280 | PolyTracker: Progressive Contour Regression for Multiple Object Tracking and Segmentation | Shen, Sanjing*; Feng, Hao; Zhou, Wengang ; Li, Houqiang |
| 14:34-14:46 | 319 | Instance-wise contrastive learning for multi-object tracking | Luo, Qiyu; Xu, Chunyan* |
| 14:46-14:58 | 397 | Enhanced Spatial Awareness For Deep Interactive Image Segmentation | Li, Haochen*; Ni, Jinlong; Li, Zhicheng; Qian, Yuxiang; Wang, Tao |
| 14:58-15:10 | 425 | Dual Attention-guided Network for Anchor-free Apple Instance Segmentation in Complex Environments | Pei, Yunshen; Ding, Yi; Zhu, Xuesen; Yan, Liuyang; Cheng, Keyang* |
