Yuxin Peng

24

Papers

155

Total Citations

Papers (24)

FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models

DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding

Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification

EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing

FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval

STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding

Selective Visual Prompting in Vision Mamba

PosterO: Structuring Layout Trees to Enable Language Models in Generalized Content-Aware Layout Generation

ConMo: Controllable Motion Disentanglement and Recomposition for Zero-Shot Motion Transfer

Open-Vocabulary HOI Detection with Interaction-aware Prompt and Concept Calibration

UPP: Unified Point-Level Prompting for Robust Point Cloud Analysis

DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification

DKC: Differentiated Knowledge Consolidation for Cloth-Hybrid Lifelong Person Re-identification

Comprehensive Visual Grounding for Video Description

DART: Dual-Modal Adaptive Online Prompting and Knowledge Retention for Test-Time Adaptation

Continual Vision-Language Retrieval via Dynamic Knowledge Rectification

FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment

FineSports: A Multi-person Hierarchical Sports Video Dataset for Fine-grained Action Understanding

FCS: Feature Calibration and Separation for Non-Exemplar Class Incremental Learning

SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting

Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification

TRKT: Weakly Supervised Dynamic Scene Graph Generation with Temporal-enhanced Relation-aware Knowledge Transferring

Semantic-Aware Human Object Interaction Image Generation

Hierarchical Event Memory for Accurate and Low-latency Online Video Temporal Grounding