Comput. Vis. Image Underst.最新文献

Real-time distributed video analytics for privacy-aware person search 实时分布式视频分析的隐私意识的人的搜索

Comput. Vis. Image Underst. Pub Date : 2023-09-01 DOI: 10.2139/ssrn.4363661

Bipin Gaikwad, A. Karmakar

引用次数: 0

PAGML: Precise Alignment Guided Metric Learning for sketch-based 3D shape retrieval PAGML:用于基于草图的三维形状检索的精确对齐引导度量学习

Comput. Vis. Image Underst. Pub Date : 2023-08-01 DOI: 10.2139/ssrn.4370100

Shaojin Bai, Jing Bai, Hao-Yu Xu, Jiwen Tuo, Min Liu

引用次数: 0

Unpaired sonar image denoising with simultaneous contrastive learning 同时对比学习的非配对声纳图像去噪

Comput. Vis. Image Underst. Pub Date : 2023-07-01 DOI: 10.2139/ssrn.4327715

Bo-Jun Zhao, Qiang Zhou, Lijun Huang, Qiang Zhang

引用次数: 0

3DF-FCOS: Small object detection with 3D features based on FCOS 3DF-FCOS:基于FCOS的具有3D特征的小目标检测

Comput. Vis. Image Underst. Pub Date : 2023-07-01 DOI: 10.2139/ssrn.4399361

Xiaobao Yang, Yulong He, Junsheng Wu, Wei Sun, Tianyu Liu, Sugang Ma

引用次数: 0

Robust Teacher: Self-correcting pseudo-label-guided semi-supervised learning for object detection 鲁棒教师:用于目标检测的自校正伪标签引导半监督学习

Comput. Vis. Image Underst. Pub Date : 2023-07-01 DOI: 10.2139/ssrn.4327717

Shijie Li, Junmin Liu, Weilin Shen, Jianyong Sun, Chengli Tan

引用次数: 0

Memory-efficient multi-scale residual dense network for single image rain removal 基于多尺度残差密集网络的单幅图像去雨

Comput. Vis. Image Underst. Pub Date : 2023-07-01 DOI: 10.2139/ssrn.4327723

Ziyang Zheng, Zhixiang Chen, Shuqi Wang, Wenpeng Wang, Hui Wang

引用次数: 1

Adversarial anchor-guided feature refinement for adversarial defense 针对对抗防御的对抗性锚制导特征细化

Comput. Vis. Image Underst. Pub Date : 2023-06-01 DOI: 10.2139/ssrn.4350314

Hakmin Lee, Yonghyun Ro

引用次数: 0

"Glitch in the Matrix!": A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization “黑客帝国中的故障!”内容驱动的视听伪造检测与定位的大规模基准

Comput. Vis. Image Underst. Pub Date : 2023-05-03 DOI: 10.48550/arXiv.2305.01979

Zhixi Cai, Shreya Ghosh, Tom Gedeon, Abhinav Dhall, Kalin Stefanov, Munawar Hayat

{"title":"\"Glitch in the Matrix!\": A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization","authors":"Zhixi Cai, Shreya Ghosh, Tom Gedeon, Abhinav Dhall, Kalin Stefanov, Munawar Hayat","doi":"10.48550/arXiv.2305.01979","DOIUrl":"https://doi.org/10.48550/arXiv.2305.01979","url":null,"abstract":"Most deepfake detection methods focus on detecting spatial and/or spatio-temporal changes in facial attributes and are centered around the binary classification task of detecting whether a video is real or fake. This is because available benchmark datasets contain mostly visual-only modifications present in the entirety of the video. However, a sophisticated deepfake may include small segments of audio or audio-visual manipulations that can completely change the meaning of the video content. To addresses this gap, we propose and benchmark a new dataset, Localized Audio Visual DeepFake (LAV-DF), consisting of strategic content-driven audio, visual and audio-visual manipulations. The proposed baseline method, Boundary Aware Temporal Forgery Detection (BA-TFD), is a 3D Convolutional Neural Network-based architecture which effectively captures multimodal manipulations. We further improve (i.e. BA-TFD+) the baseline method by replacing the backbone with a Multiscale Vision Transformer and guide the training process with contrastive, frame classification, boundary matching and multimodal boundary matching loss functions. The quantitative analysis demonstrates the superiority of BA-TFD+ on temporal forgery localization and deepfake detection tasks using several benchmark datasets including our newly proposed dataset. The dataset, models and code are available at https://github.com/ControlNet/LAV-DF.","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73587194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Self-knowledge distillation based on knowledge transfer from soft to hard examples 基于软实例到硬实例知识转移的自我知识升华

Comput. Vis. Image Underst. Pub Date : 2023-05-01 DOI: 10.2139/ssrn.4261729

Yueyue Tang, Ying Chen, Linbo Xie

引用次数: 0

Fully synthetic training for image restoration tasks 完全合成训练图像恢复任务

Comput. Vis. Image Underst. Pub Date : 2023-05-01 DOI: 10.2139/ssrn.4176695

Raphaël Achddou, Y. Gousseau, Saïd Ladjal

引用次数: 1