Liang Zhang

Affiliations

College of Ecology, Lanzhou UniversityETH Zurich

papers

392

total citations

papers (24)

Free-Form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud

ICCV 2021arXiv

108

citations

On Vocabulary Reliance in Scene Text Recognition

CVPR 2020arXiv

citations

Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

NEURIPS 2025arXiv

citations

Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment

AAAI 2024arXiv

citations

DPZero: Private Fine-Tuning of Language Models without Backpropagation

ICML 2024arXiv

citations

Learning From Pixel-Level Noisy Label: A New Perspective for Light Field Saliency Detection

CVPR 2022arXiv

citations

Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization

NEURIPS 2022arXiv

citations

DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition

ECCV 2024arXiv

citations

TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models

ICCV 2023arXiv

citations

On the Crucial Role of Initialization for Matrix Factorization

ICLR 2025arXiv

citations

FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation

ICCV 2023arXiv

citations

Language Model Guided Interpretable Video Action Reasoning

CVPR 2024arXiv

citations

Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation

NEURIPS 2023arXiv

citations

PoLAR: Polar-Decomposed Low-Rank Adapter Representation

NEURIPS 2025arXiv

citations

Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization

NEURIPS 2023arXiv

citations

Explore and Tell: Embodied Visual Captioning in 3D Environments

ICCV 2023arXiv

citations

Enhance Sketch Recognition’s Explainability via Semantic Component-Level Parsing

AAAI 2024arXiv

citations

Adversarial Contrastive Graph Augmentation with Counterfactual Regularization

AAAI 2025

citations

How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks?

NEURIPS 2020

citations

3D Spatial Multimodal Knowledge Accumulation for Scene Graph Prediction in Point Cloud

CVPR 2023

citations

Real-Time Vanishing Point Detector Integrating Under-Parameterized RANSAC and Hough Transform

ICCV 2021

citations

Liang Zhang

Affiliations

papers (24)

Free-Form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud

On Vocabulary Reliance in Scene Text Recognition

Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment

DPZero: Private Fine-Tuning of Language Models without Backpropagation

Learning From Pixel-Level Noisy Label: A New Perspective for Light Field Saliency Detection

Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization

DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition

TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models

On the Crucial Role of Initialization for Matrix Factorization

FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation

Language Model Guided Interpretable Video Action Reasoning

Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation

PoLAR: Polar-Decomposed Low-Rank Adapter Representation

Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization

Explore and Tell: Embodied Visual Captioning in 3D Environments

Enhance Sketch Recognition’s Explainability via Semantic Component-Level Parsing

Adversarial Contrastive Graph Augmentation with Counterfactual Regularization

How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks?

3D Spatial Multimodal Knowledge Accumulation for Scene Graph Prediction in Point Cloud

Merging Mechanisms for Ads and Organic Items in E-commerce Platforms

Multi-Lingual Acquisition on Multimodal Pre-training for Cross-modal Retrieval

UE4-NeRF:Neural Radiance Field for Real-Time Rendering of Large-Scale Scene

Real-Time Vanishing Point Detector Integrating Under-Parameterized RANSAC and Hough Transform

papers (24)

Free-Form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud

On Vocabulary Reliance in Scene Text Recognition

Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment

DPZero: Private Fine-Tuning of Language Models without Backpropagation

Learning From Pixel-Level Noisy Label: A New Perspective for Light Field Saliency Detection

Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization

DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition

TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models

On the Crucial Role of Initialization for Matrix Factorization

FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation

Language Model Guided Interpretable Video Action Reasoning

Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation

PoLAR: Polar-Decomposed Low-Rank Adapter Representation

Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization

Explore and Tell: Embodied Visual Captioning in 3D Environments

Enhance Sketch Recognition’s Explainability via Semantic Component-Level Parsing

Adversarial Contrastive Graph Augmentation with Counterfactual Regularization

How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks?

3D Spatial Multimodal Knowledge Accumulation for Scene Graph Prediction in Point Cloud

Merging Mechanisms for Ads and Organic Items in E-commerce Platforms

Multi-Lingual Acquisition on Multimodal Pre-training for Cross-modal Retrieval

UE4-NeRF:Neural Radiance Field for Real-Time Rendering of Large-Scale Scene

Real-Time Vanishing Point Detector Integrating Under-Parameterized RANSAC and Hough Transform