GitHub

HAIV-Lab/OSPCoOp_Imagenet-bg

To further test the robustness of the model against background interference, we propose an ImageNet background interference test set, ImageNet-Bg, based on the ImageNet validation set with 48,285 ...
IEEE

Molecular Code Index Modulation: Signaling, Detection, and Performance Analysis

Abstract: The Internet of Bio-Nano Things (IoBNT) is expected to play a pivotal role in the future healthcare systems. This paper proposes a molecular code index modulation (MCIM) scheme to achieve ...
GitHub

LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarks

LampMark is trained using CelebA-HQ and tested on CelebA-HQ and LFW. We do not own the datasets, and they can be downloaded from the official webpages. After splitting the image data following the ...
IEEE

MSP-O: A Two-Stage Mask Pretraining Method With Object Focus for Remote Sensing Object Detection

Abstract: Pretraining is showing fundamental importance in computer vision, to initialize the backbones of deep learning models with large natural image datasets, e.g., ImageNet. However, there is ...
The New York Times

The Street-Corner Sensors That Track Flooding in Real Time

Hundreds of sensors placed throughout New York City measure water as it rises, then send the data to an interactive map available to the public. By Cole del Charco Kelly Hayes, a co-owner of Gowanus ...