Trustworthy AI: From principles to practices
The rapid development of Artificial Intelligence (AI) technology has enabled the deployment
of various systems based on it. However, many current AI systems are found vulnerable to …
of various systems based on it. However, many current AI systems are found vulnerable to …
Explainability of deep vision-based autonomous driving systems: Review and challenges
This survey reviews explainability methods for vision-based self-driving systems trained with
behavior cloning. The concept of explainability has several facets and the need for …
behavior cloning. The concept of explainability has several facets and the need for …
Laion-5b: An open large-scale dataset for training next generation image-text models
C Schuhmann, R Beaumont, R Vencu… - Advances in …, 2022 - proceedings.neurips.cc
Groundbreaking language-vision architectures like CLIP and DALL-E proved the utility of
training on large amounts of noisy image-text data, without relying on expensive accurate …
training on large amounts of noisy image-text data, without relying on expensive accurate …
Countering malicious deepfakes: Survey, battleground, and horizon
The creation or manipulation of facial appearance through deep generative approaches,
known as DeepFake, have achieved significant progress and promoted a wide range of …
known as DeepFake, have achieved significant progress and promoted a wide range of …
Coming down to earth: Satellite-to-street view synthesis for geo-localization
The goal of cross-view image based geo-localization is to determine the location of a given
street view image by matching it against a collection of geo-tagged satellite images. This …
street view image by matching it against a collection of geo-tagged satellite images. This …
UAV-satellite view synthesis for cross-view geo-localization
The goal of cross-view image matching based on geo-localization is to determine the
location of a given ground-view image (front view) by matching it with a group of satellite …
location of a given ground-view image (front view) by matching it with a group of satellite …
Openforensics: Large-scale challenging dataset for multi-face forgery detection and segmentation in-the-wild
The proliferation of deepfake media is raising concerns among the public and relevant
authorities. It has become essential to develop countermeasures against forged faces in …
authorities. It has become essential to develop countermeasures against forged faces in …
Attribute-preserving face dataset anonymization via latent code optimization
This work addresses the problem of anonymizing the identity of faces in a dataset of images,
such that the privacy of those depicted is not violated, while at the same time the dataset is …
such that the privacy of those depicted is not violated, while at the same time the dataset is …
Personalized and invertible face de-identification by disentangled identity information manipulation
J Cao, B Liu, Y Wen, R **e… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
The popularization of intelligent devices including smartphones and surveillance cameras
results in more serious privacy issues. De-identification is regarded as an effective tool for …
results in more serious privacy issues. De-identification is regarded as an effective tool for …
F-TPE: Flexible thumbnail-preserving encryption based on multi-pixel sum-preserving encryption
People are accustomed to utilizing mobile phones to capture images and uploading them to
the cloud due to various incomparable advantages such as saving the storage space on the …
the cloud due to various incomparable advantages such as saving the storage space on the …