Chen Feng

papers

1,510

total citations

papers (22)

Learning Distilled Collaboration Graph for Multi-Agent Perception

NEURIPS 2021arXiv

354

citations

VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion

CVPR 2023arXiv

349

citations

LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood

CVPR 2020arXiv

170

citations

P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds

CVPR 2020arXiv

169

citations

Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting

CVPR 2022arXiv

125

citations

Towards Homogeneous Lexical Tone Decoding from Heterogeneous Intracranial Recordings

ICLR 2025arXiv

citations

PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks

AAAI 2025arXiv

citations

Self-Supervised Spatial Reasoning on Multi-View Line Drawings

CVPR 2022arXiv

citations

Adversarial Exploitation of Data Diversity Improves Visual Localization

ICCV 2025arXiv

citations

Chen Feng

papers (22)

Learning Distilled Collaboration Graph for Multi-Agent Perception

VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion

LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood

P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds

Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting

Fooling LiDAR Perception via Adversarial Trajectory Perturbation

Regularizing Neural Networks via Minimizing Hyperspherical Energy

Among Us: Adversarially Robust Collaborative Perception by Consensus

Egocentric Prediction of Action Target in 3D

CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos

DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization

SPARE3D: A Dataset for SPAtial REasoning on Three-View Line Drawings

Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset

MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset

LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition

LUWA Dataset: Learning Lithic Use-Wear Analysis on Microscopic Images

Extrapolated Urban View Synthesis Benchmark

GARF: Learning Generalizable 3D Reassembly for Real-World Fractures

Towards Homogeneous Lexical Tone Decoding from Heterogeneous Intracranial Recordings

PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks

Self-Supervised Spatial Reasoning on Multi-View Line Drawings

Adversarial Exploitation of Data Diversity Improves Visual Localization

papers (22)

Learning Distilled Collaboration Graph for Multi-Agent Perception

VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion

LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood

P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds

Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting

Fooling LiDAR Perception via Adversarial Trajectory Perturbation

Regularizing Neural Networks via Minimizing Hyperspherical Energy

Among Us: Adversarially Robust Collaborative Perception by Consensus

Egocentric Prediction of Action Target in 3D

CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos

DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization

SPARE3D: A Dataset for SPAtial REasoning on Three-View Line Drawings

Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset

MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset

LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition

LUWA Dataset: Learning Lithic Use-Wear Analysis on Microscopic Images

Extrapolated Urban View Synthesis Benchmark

GARF: Learning Generalizable 3D Reassembly for Real-World Fractures

Towards Homogeneous Lexical Tone Decoding from Heterogeneous Intracranial Recordings

PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks

Self-Supervised Spatial Reasoning on Multi-View Line Drawings

Adversarial Exploitation of Data Diversity Improves Visual Localization