Shu Liu

43

Papers

758

Total Citations

Papers (43)

LISA: Reasoning Segmentation via Large Language Model

MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders

Establishing Best Practices in Building Rigorous Agentic Benchmarks

Path Aggregation Network for Instance Segmentation

Amodal Instance Segmentation With KINS Dataset

Associatively Segmenting Instances and Semantics in Point Clouds

PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation

DSGN: Deep Stereo Geometry Network for 3D Object Detection

3DSSD: Point-Based 3D Single Stage Object Detector

Distilling Knowledge via Knowledge Review

Semi-Supervised Semantic Segmentation With Directional Context-Aware Consistency

Jigsaw Clustering for Unsupervised Visual Representation Learning

Self-Supervised 3D Mesh Reconstruction From Single Images

Improving Calibration for Long-Tailed Recognition

EfficientNeRF Efficient Neural Radiance Fields

Generalized Few-Shot Semantic Segmentation

Stratified Transformer for 3D Point Cloud Segmentation

Rethinking Out-of-Distribution (OOD) Detection: Masked Image Modeling Is All You Need

Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields

Hierarchical Dense Correlation Distillation for Few-Shot Segmentation

Contour Box: Rejecting Object Proposals Without Explicit Closed Contours

Box Aggregation for Proposal Decimation: Last Mile of Object Detection

Semantic Segmentation With Object Clique Potential

SGN: Sequential Grouping Networks for Instance Segmentation

STD: Sparse-to-Dense 3D Object Detector for Point Cloud

Fast and Practical Neural Architecture Search

Fast Point R-CNN

Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation

Guided Point Contrastive Learning for Semi-Supervised Point Cloud Semantic Segmentation

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition

Deep Structured Instance Graph for Distilling Object Detectors

Video Instance Segmentation With a Propose-Reduce Paradigm

Learnable Boundary Guided Adversarial Training

Parametric Contrastive Learning

Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation

Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection

CN: Channel Normalization For Point Cloud Recognition

Dive Deeper Into Box for Object Detection

DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

HRegNet: A Hierarchical Network for Large-Scale Outdoor LiDAR Point Cloud Registration

Prompt Highlighter: Interactive Control for Multi-Modal LLMs

Multi-Scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation

Sequential Context Encoding for Duplicate Removal