activity
20242026
most citedCross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing

7 citations · 7 across the 9 of their papers we have counts for

collaborators

9 papers

cs.LG2026

Measuring Structured Predictability in Neural Training Dynamics: A Cross-Regime Study

Fanqi Wang, Weisheng Tang, Hairong Qi

Modern deep networks are trained through long update trajectories, yet their temporal organization remains less systematically characterized than architectures, losses, or optimize…

cs.CV2026

ExPLoRe: Expert Patch-Level Loss Routing for Multi-Objective Masked Image Modeling

Konstantinos Georgiou, Maofeng Tang, Hairong Qi

Multi-objective masked image modeling (MIM) combines complementary learning signals (token distillation, CLS alignment, and pixel reconstruction) but existing methods weight these…

cs.CV2026

Sat3R: Satellite DSM Reconstruction via RPC-Aware Depth Fine-tuning

Qiaoyi Yang, Chaoyi Zhou, Xi Liu +9

Accurate Digital Surface Model (DSM) reconstruction from satellite imagery is critical for applications such as disaster response, urban planning, and large-scale geographic mappin…

cs.CV2026

Looking into a Pixel by Nonlinear Unmixing -- A Generative Approach

Maofeng Tang, Hairong Qi

Due to the large footprint of pixels in remote sensing imagery, hyperspectral unmixing (HU) has become an important and necessary procedure in hyperspectral image analysis. Traditi…

cs.CV2026

MEDiC: Multi-objective Exploration of Distillation from CLIP

Konstantinos Georgiou, Maofeng Tang, Hairong Qi

Masked image modeling (MIM) methods typically operate in either raw pixel space (reconstructing masked patches) or latent feature space (aligning with a pre-trained teacher). We pr…

cs.CV2026

FujiView: Multimodal Late-Fusion for Predicting Scenic Visibility

Bryceton Bible, Shah Md Nehal Hasnaeen, Hairong Qi

Visibility of natural landmarks such as Mount Fuji is a defining factor in both tourism planning and visitor experience, yet it remains difficult to predict due to rapidly changing…