conftrace_
← Authors

Xingyu Liu

31 papers · 2018–2026 · 10 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+11 more ↓ πŸŒ‰ Interdisciplinary Bridge 🌈 Renaissance Researcher (8) 🌍 Conference Polyglot (9) πŸƒ Academic Marathon (7) πŸ—ΊοΈ Taxonomy Completionist (52)
🧭 Keyword Pioneer 🐝 Cross-Pollinator (12) 🌈 Renaissance Researcher (8) πŸ”¬ Deep Specialist (10) πŸ‘₯ Mega-Team (85) πŸ“ˆ Trend Setter ⚑ Prolific Year (5) πŸ”₯ Unstoppable (8) πŸ—ƒοΈ Keyword Collector (131) πŸ’Ž Century Club (29) πŸš€ Conference Pioneer

Conferences

CVPR (9) ICCV (7) AAAI (3) ECCV (3) COLING (2) CORL (2) ICLR (2) ACL (1) EMNLP (1) ICML (1)

Top co-authors

Kris M. Kitani (5) Xiangyang Ji (4) Jingyu Wang (3) Ruida Zhang (3) Kris Kitani (3) Haifeng Sun (3) Jianxin Liao (3) Pengfei Ren (3) Qichen Fu (3) Deepak Pathak (3)

Keywords

3d vision (4) hand pose estimation (3) point cloud (3) action recognition (2) neural network (2) motion estimation (2) deep learning (2) reinforcement learning (2) 6d pose estimation (2) scene flow (2) keypoint detection (2) semantic segmentation (2) stereo vision (1) efficient training (1) embedding space (1) motion analysis (1) benchmark evaluation (1) 3d reconstruction (1) robotic manipulation (1) response generation (1)

Papers

Interleaved Latent Visual Reasoning with Selective Perceptual Modeling ACL 2026 Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports from Scratch with Agentic Framework AAAI 2026 Neural Topic Modeling via Contextual and Graph Information Fusion EMNLP 2025 Street Gaussians without 3D Object Tracker ICCV 2025 UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image CVPR 2025 Boosting the Dual-Stream Architecture in Ultra-High Resolution Segmentation with Resolution-Biased Uncertainty Estimation CVPR 2025 No Pains, More Gains: Recycling Sub-Salient Patches for Efficient High-Resolution Image Recognition CVPR 2025 Prior-aware Dynamic Temporal Modeling Framework for Sequential 3D Hand Pose Estimation ICCV 2025 Domain Shifting: A Generalized Solution for Heterogeneous Cross-Modality Person Re-Identification ECCV 2024 Jargon: A Suite of Language Models and Evaluation Tasks for French Specialized Domains COLING 2024 MedDialog-FR: A French Version of the MedDialog Corpus for Multi-label Classification and Response Generation Related to Women’s Intimate Health COLING 2024 Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer ICLR 2024 Differentiable Auxiliary Learning for Sketch Re-Identification AAAI 2024 Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation AAAI 2024 KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation CVPR 2024 Coarse-to-Fine Implicit Representation Learning for 3D Hand-Object Reconstruction from a Single RGB-D Image ECCV 2024 Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition ICCV 2023 Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation ICCV 2023 CATRE: Iterative Point Clouds Alignment for Category-Level Object Pose Refinement ECCV 2022 HERD: Continuous Human-to-Robot Evolution for Learning from Human Demonstration CORL 2022 Sequential Voting With Relational Box Fields for Active Object Detection CVPR 2022 Ego4D: Around the World in 3,000 Hours of Egocentric Video CVPR 2022 REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer ICML 2022 RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering ICCV 2021 V-MAO: Generative Modeling for Multi-Arm Manipulation of Articulated Objects CORL 2021 StereOBJ-1M: Large-Scale Stereo Image Dataset for 6D Object Pose Estimation ICCV 2021 KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects CVPR 2020 FlowNet3D: Learning Scene Flow in 3D Point Clouds CVPR 2019 MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences ICCV 2019 Learning Video Representations From Correspondence Proposals CVPR 2019 Efficient Sparse-Winograd Convolutional Neural Networks ICLR 2018