Xiangyang Ji

GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation

CVPR 2025 1

Beyond Any-Shot Adaptation: Predicting Optimization Outcome for Robustness Gains without Extra Pay

arXiv 2025

Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces

CVPR 2025 1

UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image

CVPR 2025 1

Street Gaussians without 3D Object Tracker

arXiv 2024

Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning

arXiv 2024

Efficient Personalized Text-to-image Generation by Leveraging Textual Subspace

arXiv 2024

VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models

arXiv 2024

CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications

arXiv 2024

LLM-Empowered State Representation for Reinforcement Learning

arXiv 2024

Know2Vec: A Black-Box Proxy for Neural Network Retrieval

arXiv 2024

DiffusionRet: Generative Text-Video Retrieval with Diffusion Model

ICCV 2023 1

Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning

CVPR 2023 1

U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds

ICCV 2023 1

UATVR: Uncertainty-Adaptive Text-Video Retrieval

ICCV 2023 1

Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning

counterfactual-conservative-q-learning-for

Disjoint Masking with Joint Distillation for Efficient Masked Image Modeling

arXiv 2022

CCMB: A Large-scale Chinese Cross-modal Benchmark

arXiv 2022

Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection

ICCV 2023 1

CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement

arXiv 2022