{"title":"Real-time distributed video analytics for privacy-aware person search","authors":"Bipin Gaikwad, A. Karmakar","doi":"10.2139/ssrn.4363661","DOIUrl":"https://doi.org/10.2139/ssrn.4363661","url":null,"abstract":"","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77004565","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}
{"title":"3DF-FCOS: Small object detection with 3D features based on FCOS","authors":"Xiaobao Yang, Yulong He, Junsheng Wu, Wei Sun, Tianyu Liu, Sugang Ma","doi":"10.2139/ssrn.4399361","DOIUrl":"https://doi.org/10.2139/ssrn.4399361","url":null,"abstract":"","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79545941","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}
Pub Date : 2023-05-03DOI: 10.48550/arXiv.2305.01979
Zhixi Cai, Shreya Ghosh, Tom Gedeon, Abhinav Dhall, Kalin Stefanov, Munawar Hayat
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.
{"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}
{"title":"Self-knowledge distillation based on knowledge transfer from soft to hard examples","authors":"Yueyue Tang, Ying Chen, Linbo Xie","doi":"10.2139/ssrn.4261729","DOIUrl":"https://doi.org/10.2139/ssrn.4261729","url":null,"abstract":"","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79910790","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}
. In this work, we show that neural networks aimed at solving various image restoration tasks can be successfully trained on fully synthetic data. In order to do so, we rely on a generative model of images, the scaling dead leaves model, which is obtained by superimposing disks whose size distribution is scale-invariant. Pairs of clean and corrupted synthetic images can then be obtained by a careful simulation of the degradation process. We show on various restoration tasks that such a synthetic training yields results that are only slightly inferior to those obtained when the training is performed on large natural image databases. This implies that, for restoration tasks, the geometric contents of natural images can be nailed down to only a simple generative model and a few parameters. This prior can then be used to train neural networks for specific modality, without having to rely on demanding campaigns of natural images acquisition. We demonstrate the feasibility of this approach on difficult restoration tasks, including the denoising of smartphone RAW images and the full development of low-light images.
{"title":"Fully synthetic training for image restoration tasks","authors":"Raphaël Achddou, Y. Gousseau, Saïd Ladjal","doi":"10.2139/ssrn.4176695","DOIUrl":"https://doi.org/10.2139/ssrn.4176695","url":null,"abstract":". In this work, we show that neural networks aimed at solving various image restoration tasks can be successfully trained on fully synthetic data. In order to do so, we rely on a generative model of images, the scaling dead leaves model, which is obtained by superimposing disks whose size distribution is scale-invariant. Pairs of clean and corrupted synthetic images can then be obtained by a careful simulation of the degradation process. We show on various restoration tasks that such a synthetic training yields results that are only slightly inferior to those obtained when the training is performed on large natural image databases. This implies that, for restoration tasks, the geometric contents of natural images can be nailed down to only a simple generative model and a few parameters. This prior can then be used to train neural networks for specific modality, without having to rely on demanding campaigns of natural images acquisition. We demonstrate the feasibility of this approach on difficult restoration tasks, including the denoising of smartphone RAW images and the full development of low-light images.","PeriodicalId":10549,"journal":{"name":"Comput. Vis. Image Underst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88386053","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：