← Search

He Chen

13 accepted papers

2026

Regulating Rather than Constraining: Adaptive Guidance for Complex Spectral Reconstruction in Pansharpening

CVPR 2026

In remote sensing pansharpening, spectrally mixed regions, where the spectral interactions among adjacent land covers lead to highly inconsistent reconstruction patterns, remain the most challenging areas. Due to the complex spatial distribution and heterogeneous spectral characteristics of ground o

Cited by 0SourcecodeScholar
2026

UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes

CVPR 2026

Instruction-driven segmentation in remote sensing generates masks from guidance, offering great potential for accessible and generalizable applications. However, existing methods suffer from fragmented task formulations and limited instruction data, hindering effective understanding and generalizati

Cited by 0SourcecodeScholar
2025

Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation

IJCAI 2025

Embodied agents exhibit immense potential across a multitude of domains, making the assurance of their behavioral safety a fundamental prerequisite for their widespread deployment. However, existing research predominantly concentrates on the security of general large language models, lacking special

2024

Lower-level Duality Based Reformulation and Majorization Minimization Algorithm for Hyperparameter Optimization

AISTATS 2024poster

Hyperparameter tuning is an important task of machine learning, which can be formulated as a bilevel program (BLP). However, most existing algorithms are not applicable for BLP with non-smooth lower-level problems. To address this, we propose a single-level reformulation of the BLP based on lower-le…

Cited by 2SourcePDFScholar
2022

mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections

EMNLP 2022main

Large-scale pre-trained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstream tasks. This paper presents mPLUG, a new vision-language foundation model for both cross-modal understanding and gener…

2021

Fast Algorithms for Stackelberg Prediction Game with Least Squares Loss

ICML 2021spotlight

The Stackelberg prediction game (SPG) has been extensively used to model the interactions between the learner and data provider in the training process of various machine learning algorithms. Particularly, SPGs played prominent roles in cybersecurity applications, such as intrusion detection, bankin…

2021

Towards Efficient Graph Convolutional Networks for Point Cloud Handling

ICCV 2021poster

We aim at improving the computational efficiency of graph convolutional networks (GCNs) for learning on point clouds. The basic graph convolution that is composed of a K-nearest neighbor (KNN) search and a multilayer perceptron (MLP) is examined. By mathematically analyzing the operations there, two…

Cited by 34PDFScholar
2020

Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry

ECCV 2020poster

Epipolar constraints are at the core of feature matching and depth estimation in current multi-person multi-camera 3D human pose estimation methods. Despite the satisfactory performance of this formulation in sparser crowd scenes, its effectiveness is frequently challenged under denser crowd circums…

2015

A stackelberg game-based energy trading scheme for power beacon-assisted wireless-powered communication

ICASSP 2015accepted

This paper studies a power beacon-assisted wireless-powered communication network, consisting of one hybrid access point (AP), one information source, and multiple power beacons (PBs). The source has no embedded power supply, and thus, has to harvest RF energy from the AP in the downlink before tran…

Cited by 0SourceScholar