某机构ICCV 2023论文速览
从图像分割、目标检测等经典问题，到数据表示和“机器遗忘”等理论课题，某机构研究人员在ICCV上发表的论文展示了他们在计算机视觉领域工作的多样性。
会议：ICCV 2023
按主题分类的某机构ICCV 2023论文
三维数据处理
- 3-DHAL3D：用于细粒度三维部件标签的分层主动学习
- Fenggen Yu, Yiming Qian, Francisca Gil Ureta, Brian Jackson, Eric Bennett, Richard Zhang
- ImGeoNet：用于多视角三维目标检测的图像诱导几何感知体素表示
- Tao Tu, Shun-Po Chuang, Yu-Lun Liu, Cheng Sun, Ke Zhang, Donna Roy, Cheng-Hao Kuo, Min Sun
动作识别
- SkeleTR：面向开放环境的基于骨架的动作识别
- Haodong Duan, Mingze Xu, Bing Shuai, Davide Modolo, Zhuowen Tu, Joe Tighe, Alessandro Bergamo
数据表示
- 意义的线性空间：视觉-语言模型中的组合结构
- Matthew Trager, Pramuditha Perera, Luca Zancato, Alessandro Achille, Parminder Bhatia, Stefano Soatto
- 用于时空表示学习的运动引导掩码
- David Fan, Jue Wang, Leo Liao, Yi Zhu, Vimal Bhat, Hector Santos, Rohith Mysore Vijaya Kumar, Xinyu (Arthur) Li
配音视频生成
- SIDGAN：基于平移不变学习的高分辨率配音视频生成
- Urwa Muaz, Wondong Jang, Rohun Tripathi, santhosh Mani, Wenbin Ouyang, Ravi Teja Gadde, Baris Gecer, Sergio Elizondo, Reza Madad, Naveen Nair
地理空间基础模型
- 通过持续预训练构建地理空间基础模型
- Matias Mendieta, Boran Han, Xingjian Shi, Yi Zhu, Chen Chen
图神经网络
- 学习图神经网络的自适应邻域
- Avi Saha, Oscar Mendez, Chris Russell, Richard Bowden
图像检索
- FashionNTM：基于级联记忆的多轮时尚图像检索
- Anwesan Pal, Sahil Wadhwa, Ayush Jaiswal, Xu Zhang, Yue Wu, Rakesh Chada, Pradeep Natarajan, Henrik I. Christensen
图像分割
- 基于形状先验的由粗到细的非模态分割
- Jianxiong Gao, Xuelin Qian, Yikai Wang, Tianjun Xiao, Tong He, Zheng Zhang, Yanwei Fu
- LD-ZNet：一种基于潜在扩散的文本引导图像分割方法
- Koutilya PNVR, Bharat Singh, Pallabi Ghosh, Behjat Siddiquie, David Jacobs
- 从具有目标中心表示的学习监督信号重新思考非模态视频分割
- Ke Fan, Jingshi Lei, Xuelin Qian, Miaopeng Yu, Tianjun Xiao, Tong He, Zheng Zhang, Yanwei Fu
信息提取
- DocTr：用于文档结构化信息提取的文档转换器
- Haofu Liao, Aruni RoyChowdhury, Weijian Li, Ankan Bansal, Yuting Zhang, Zhuowen Tu, Ravi Kumar Satzoda, R. Manmatha, Vijay Mahadevan
机器遗忘
- SAFE：基于分片图的机器遗忘
- Yonatan Dukler, Ben Bowman, Alessandro Achille, Aditya Golatkar, Ashwin Swaminathan, Stefano Soatto
目标检测
- 基于Transformer的领域自适应检测中的双向对齐
- Liqiang He, Wei Wang, Albert Chen, Min Sun, Cheng-Hao Kuo, Sinisa Todorovic
- 视频中的无监督开放词汇目标定位
- Ke Fan, Zechen Bai, Tianjun Xiao, Dominik Zietlow, Max Horn, Zixu Zhao, Carl-Johann Simon-Gabriel, Mike Zheng Shou, Francesco Locatello, Bernt Schiele, Thomas Brox, Zheng Zhang, Yanwei Fu, Tong He
多目标追踪
- 以目标为中心的多目标追踪
- Zixu Zhao, Jiaze Wang, Max Horn, Yizhuo Ding, Tong He, Zechen Bai, Dominik Zietlow, Carl-Johann Simon-Gabriel, Bing Shuai, Zhuowen Tu, Thomas Brox, Bernt Schiele, Yanwei Fu, Francesco Locatello, Zheng Zhang, Tianjun Xiao
场景文本识别
- CLIPTER：在场景文本识别中审视更宏观的图景
- Aviad Aberdam, David Haim Bensaid, Alona Golts, Roy Ganz, Oren Nuriel, Royee Tichauer, Shai Mazor, Ron Litman
- 构建既能“看”又能“读”的模型
- Roy Ganz, Oren Nuriel, Aviad Aberdam, Yair Kittenplon, Shai Mazor, Ron Litman
迁移学习
- PADCLIP：用于无监督领域自适应的CLIP自适应去偏伪标记
- Zhengfeng Lai, Sol Vesdapunt, Ning Zhou, Jun Wu, Cong Phuoc Huynh, Xuelu Li, Kah Kuen Fu, Chen-Nee Chuah
视频检索
- 基于文本条件特征对齐的音频增强型文本到视频检索
- Sarah Ibrahimi, Xiaohang Sun, Pichao Wang, Amanmeet Garg, Ashutosh Sanan, Mohamed Omar
视频分割
- MEGA：面向电影级视频分割的多模态对齐聚合与蒸馏
- Najmeh Sadoughi, Xinyu (Arthur) Li, Avijit Vajpayee, David Fan, Bing Shuai, Hector Santos, Vimal Bhat, Rohith Mysore Vijaya Kumar
研究领域: 计算机视觉
标签: 目标检测, 图像分割, 数据表示, ICCVFINISHED
