Daizong Liu

14

Papers

19

Total Citations

Papers (14)

Hiding Imperceptible Noise in Curvature-Aware Patches for 3D Point Cloud Attack

Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network

Imperceptible 3D Point Cloud Attacks on Lattice-based Barycentric Coordinates

Explicitly Perceiving and Preserving the Local Geometric Structures for 3D Point Cloud Attack

Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language

MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation

Context-Aware Biaffine Localizing Network for Temporal Sentence Grounding

You Can Ground Earlier Than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos

Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection

3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack

Dual Learning with Dynamic Knowledge Distillation for Partially Relevant Video Retrieval

Seeing is Not Believing: Adversarial Natural Object Optimization for Hard-Label 3D Scene Attacks

Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks

LLM-assisted Entropy-based Adaptive Distillation for Unsupervised Fine-grained Visual Representation Learning