Jie Liu

34

Papers

249

Total Citations

Papers (34)

Improving Video Generation with Human Feedback

A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning

CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution

AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis

Sketch and Refine: Towards Fast and Accurate Lane Detection

Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models

Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks

CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation

Hierarchical Aligned Multimodal Learning for NER on Tweet Posts

Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing

E4: Energy-Efficient DNN Inference for Edge Video Analytics via Early Exiting and DVFS

PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field Reconstruction

Probabilistic Prototype Calibration of Vision-language Models for Generalized Few-shot Semantic Segmentation

K-hop Hypergraph Neural Network: A Comprehensive Aggregation Approach

LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition

Test-time Adaptation for Foundation Medical Segmentation Model Without Parametric Updates

AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual Learning

Q-PART: Quasi-Periodic Adaptive Regression with Test-time Training for Pediatric Left Ventricular Ejection Fraction Regression

Residual Feature Aggregation Network for Image Super-Resolution

Inception Convolution With Efficient Dilation Search

Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation

SimT: Handling Open-Set Noise for Domain Adaptive Semantic Segmentation

Adjustment and Alignment for Unbiased Open Set Domain Adaptation

Few-Shot Semantic Segmentation With Cyclic Memory Network

Dynamic Context-Sensitive Filtering Network for Video Salient Object Detection

CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection

Robust Object Modeling for Visual Tracking

Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape

Asymmetric Two-Stream Architecture for Accurate RGB-D Saliency Detection

Unknown-Oriented Learning for Open Set Domain Adaptation

Scale-Aware Graph Neural Network for Few-Shot Semantic Segmentation

DAMPER: A Dual-Stage Medical Report Generation Framework with Coarse-Grained MeSH Alignment and Fine-Grained Hypergraph Matching

Both Supply and Precision: Sample Debias and Ranking Consistency Joint Learning for Large Scale Pre-Ranking System

SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient