The Flow has not summarised this story yet — read it at arXiv Computer Vision.
arXiv:2606. 18661v1 Announce Type: cross Abstract: Intelligent landslide hazard interpretation is critical for disaster prevention, yet current paradigms struggle to simultaneously extract visual features and high-level geoscientific semantics, while general-purpose vision-language models (VLMs) suffer from perceptual limitations and domain hallucinations in complex geological scenarios.
Intelligent landslide hazard interpretation is critical for disaster prevention, yet current paradigms struggle to simultaneously extract visual features and high-level geoscientific semantics, while general-purpose vision-language models (VLMs) suffer from perceptual limitations and domain hallucinations in complex geological scenarios. To address these challenges, we propose an instruction-driven agentic framework comprising three components.
arXiv:2609.13332v1 Announce Type: new Abstract: Automated landslide segmentation on Mars is one of the important tasks for understanding its surface processes, and all will aid in future space explor...
arXiv:2601. 03569v3 Announce Type: replace Abstract: Local Intrinsic Dimensionality (LID) has shown strong potential for anomaly detection in high-dimensional data, including landslide failure detection in granular media, where early and accurate identification of failure zones is crucial for effective geohazard mitigation.
The paper introduces a Local-Geo and Spatial Context Fusion (LGSCF) strategy that combines point-based geo-environmental features with surrounding spatial context using a feature-wise modulation mechanism. Applied to nine CNN models over a 2644 km² area in Taiwan, LGSCF consistently outperforms baseline models, achieving F1-scores up to 87.09% and AUC values up to 0.9472. The resulting susceptibility maps more accurately concentrate known landslides in high-risk zones with fewer misclassifications.
Newly triggered landslides rarely carry immediate annotations, so cross-domain transferability determines the value of landslide mapping for emergency response and regional risk assessment. Vision foundation models have strengthened representational transfer, yet on unseen regions, events, and data sources they still generate high-confidence false alarms.