Jun Liu

109

Papers

400

Total Citations

Papers (109)

Learning Progressive Joint Propagation for Human Motion Prediction

LLaFS: When Large Language Models Meet Few-Shot Segmentation

Correlation Matching Transformation Transformers for UHD Image Restoration

6D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimation

Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation

LEAD: Exploring Logit Space Evolution for Model Selection

CoG-DQA: Chain-of-Guiding Learning with Large Language Models for Diagram Question Answering

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

VProChart: Answering Chart Question Through Visual Perception Alignment Agent and Programmatic Solution Reasoning

ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding

VA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention

Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs

CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Framework

Global-Semantic Alignment Distillation for Partial Multi-view Classification

Deconfound Semantic Shift and Incompleteness in Incremental Few-shot Semantic Segmentation

Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment

RMath: A Logic Reasoning-Focused Datasets Toward Mathematical Multistep Reasoning Tasks

Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models

MatchDet: A Collaborative Framework for Image Matching and Object Detection

DifAttack: Query-Efficient Black-Box Adversarial Attack via Disentangled Feature Space

LAFA: Multimodal Knowledge Graph Completion with Link Aware Fusion and Aggregation

Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection

Mixed Geometry Message and Trainable Convolutional Attention Network for Knowledge Graph Completion

MWSIS: Multimodal Weakly Supervised Instance Segmentation with 2D Box Annotations for Autonomous Driving

E-GPS: Explainable Geometry Problem Solving via Top-Down Solver and Bottom-Up Generator

Referring Expression Counting

LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content

LLMs are Good Action Recognizers

Action Detection via an Image Diffusion Process

LLMs are Good Sign Language Translators

Addressing Background Context Bias in Few-Shot Segmentation through Iterative Modulation

Network Tight Community Detection

Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification

UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers

NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis

Global Context-Aware Attention LSTM Networks for 3D Action Recognition

Deep Level Sets for Salient Object Detection

SSNet: Scale Selection Network for Online 3D Action Prediction

VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild

ZSTAD: Zero-Shot Temporal Activity Detection

Person30K: A Dual-Meta Generalization Network for Person Re-Identification

SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning Over Traffic Events

Rank-One Prior: Toward Real-Time Scene Recovery

Generalizable Person Re-Identification With Relevance-Aware Mixture of Experts

Interventional Video Grounding With Dual Contrastive Learning

UAV-Human: A Large Benchmark for Human Behavior Understanding With Unmanned Aerial Vehicles

Robust Image Forgery Detection Over Online Social Network Shared Images

Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding

Surface Representation for Point Clouds

En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning

Meta Agent Teaming Active Learning for Pose Estimation

Meta Compositional Referring Expression Segmentation

Continual Semantic Segmentation With Automatic Memory Sample Selection

A Characteristic Function-Based Method for Bottom-Up Human Pose Estimation

Unified Pose Sequence Modeling

Bi-Directional Feature Fusion Generative Adversarial Network for Ultra-High Resolution Pathological Image Virtual Re-Staining

DiffPose: Toward More Reliable 3D Pose Estimation

Uncertainty-Aware Unsupervised Image Deblurring With Deep Residual Prior

System-Status-Aware Adaptive Network for Online Streaming Video Understanding

Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling

Token Boosting for Robust Self-Supervised Visual Transformer Pre-Training

Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks

Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning

Else-Net: Elastic Semantic Network for Continual Action Recognition From Skeleton Data

Interaction via Bi-Directional Graph of Semantic Region Affinity for Scene Parsing

Learning Inner-Group Relations on Point Clouds

IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID

A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder

Motion Adaptive Pose Estimation From Compressed Videos

Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation

STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition

Learning Gabor Texture Features for Fine-Grained Recognition

Chaotic World: A Large and Challenging Benchmark for Human Behavior Understanding in Chaotic Events

Instance and Category Supervision are Alternate Learners for Continual Learning

MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition

Distribution-Aligned Diffusion for Human Mesh Recovery

Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation

Collaborative Learning of Gesture Recognition and 3D Hand Pose Estimation with Multi-Order Feature Analysis

Adaptive Computationally Efficient Network for Monocular 3D Hand Pose Estimation

HARD-Net: Hardness-AwaRe Discrimination Network for 3D Early Activity Prediction

OID: Outlier Identifying and Discarding in Blind Image Deblurring

Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition

GradAuto: Energy-Oriented Attack on Dynamic Neural Networks

tSF: Transformer-Based Semantic Filter for Few-Shot Learning

IGFormer: Interaction Graph Transformer for Skeleton-Based Human Interaction Recognition

Meta Spatio-Temporal Debiasing for Video Scene Graph Generation

Improving the Reliability for Confidence Estimation

ERA: Expert Retrieval and Assembly for Early Action Prediction

Heterogeneous Diversity Driven Active Learning for Multi-Object Tracking

Towards Explicit Geometry-Reflectance Collaboration for Generalized LiDAR Segmentation in Adverse Weather

An Image-like Diffusion Method for Human-Object Interaction Detection

Convex Combination Star Shape Prior for Data-driven Image Semantic Segmentation

LongDiff: Training-Free Long Video Generation in One Go

POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation

Hierarchical Divide-and-Conquer Grouping for Classification Adaptation of Pre-Trained Models

Boundary Probing for Input Privacy Protection When Using LMM Services

Blind Noisy Image Deblurring Using Residual Guidance Strategy

DiffIP: Representation Fingerprints for Robust IP Protection of Diffusion Models

Performing Defocus Deblurring by Modeling its Formation Process

Recognizing Actions from Robotic View for Natural Human-Robot Interaction

EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding

Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension

ResQ: A Residual Q Function-based Approach for Multi-Agent Reinforcement Learning Value Factorization

Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation

Heatmap Distribution Matching for Human Pose Estimation

Neural Lyapunov Control of Unknown Nonlinear Systems with Stability Guarantees

LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition

Joint Attribute and Model Generalization Learning for Privacy-Preserving Action Recognition

Greedy Orthogonal Pivoting Algorithm for Non-Negative Matrix Factorization