Zhe Liu

34

Papers

595

Total Citations

Papers (34)

EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection

Attribute-Missing Graph Clustering Network

Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification

SEED: A Simple and Effective 3D DETR in Point Clouds

DVSAI: Diverse View-Shared Anchors Based Incomplete Multi-View Clustering

LONG3R: Long Sequence Streaming 3D Reconstruction

Contextual Bandits for Unbounded Context Distributions

OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection

Planning from Imagination: Episodic Simulation and Episodic Memory for Vision-and-Language Navigation

MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices

Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement

Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Rates

Describe, Adapt and Combine: Empowering CLIP Encoders for Open-set 3D Object Retrieval

A Simple Vision Transformer for Weakly Semi-supervised 3D Object Detection

Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learning

RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration

RLSAC: Reinforcement Learning Enhanced Sample Consensus for End-to-End Robust Estimation

Globally Optimal and Efficient Vanishing Point Estimation in Atlanta World

What Matters for 3D Scene Flow Network

Boosting Image Restoration via Priors from Pre-trained Models

Mamba4D: Efficient 4D Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models

Improving Integrated Gradient-based Transferable Adversarial Examples by Refining the Integration Path

FLAME: Learning to Navigate with Multimodal LLM in Urban Environments

Hawkes-Enhanced Spatial-Temporal Hypergraph Contrastive Learning Based on Criminal Correlations

RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection

DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Iterative Diffusion-Based Refinement

Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning

PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimization

Learning To Identify Correct 2D-2D Line Correspondences on Sphere

Quasi-Globally Optimal and Efficient Vanishing Point Estimation in Manhattan World

LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis

Learning Icosahedral Spherical Probability Map Based on Bingham Mixture Model for Vanishing Point Estimation

Hilbert Distillation for Cross-Dimensionality Networks

Query-based Temporal Fusion with Explicit Motion for 3D Object Detection