ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Hongyuan Zhu

Hongyuan Zhu

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 11:22 PM AMS

13

papers

227

total citations

papers (13)

CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow

End-to-End 3D Dense Captioning With Vote2Cap-DETR

Contributing Dimension Structure of Deep Feature for Coreset Selection

Object-level Correlation for Few-Shot Segmentation

Deep Unsupervised Hashing via External Guidance

PrefAce: Face-Centric Pretraining with Self-Structure Aware Distillation

Learning Cross-Modal Retrieval With Noisy Labels

Detecting Open World Objects via Partial Attribute Assignment

Zero-Shot Point Cloud Segmentation by Semantic-Visual Aware Synthesis

Balancing Privacy and Performance: A Many-in-One Approach for Image Anonymization

LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding Reasoning and Planning

Rethinking Image Super Resolution From Long-Tailed Distribution Learning Perspective

RONO: Robust Discriminative Learning With Noisy Labels for 2D-3D Cross-Modal Retrieval