Remote Sensing

This dataset comprises radar-acquired signals from 15 subjects walking on a treadmill, aimed at exploring methodologies for non-contact vital sign detection under conditions of significant body movement. Each subject participated in four experimental sessions, where radar data were collected using two Continuous Wave (CW) radars positioned to capture signals from the front and back of the subject. The data includes both raw and demodulated signals synchronized with ground-truth data obtained from a BioPac system.

In recent years, the success of large-scale visionlanguage models (VLMs) such as CLIP has led to their increased usage in various computer vision tasks. These models enable zero-shot inference through carefully crafted instructional text prompts without task-specific supervision. However, the potential of VLMs for generalization tasks in remote sensing (RS) has not been fully realized. To address this research gap, we propose a novel image-conditioned prompt learning strategy called the Visual Attention Parameterized Prompts Learning Network (APPLeNet).

The detection of the collapse of landslides trigerred by intense natural hazards, such as earthquakes and rainfall, allows rapid response to hazards which turned into disasters. The use of remote sensing imagery is mostly considered to cover wide areas and assess even more rapidly the threats. Yet, since optical images are sensitive to cloud coverage, their use is limited in case of emergency response. The proposed dataset is thus multimodal and targets the early detection of landslides following the disastrous earthquake which occurred in Haiti in 2021.

Los Angeles-1： This dataset was also derived from the AVIRIS sensor with a 7.1-m spatial resolution. This image scene covers an area of 100 × 100 pixels, which has 205 spectral bands with the spectral wavelengths from 430 to 860 nm after bad bands are removed; 232 pixels are representing buildings are regarded as anomalies.