Bin Liu

papers

1,392

total citations

papers (25)

ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation

ICCV 2021arXiv

citations

Diverse Semantic Image Synthesis via Probability Distribution Modeling

CVPR 2021arXiv

citations

Parametric Instance Classification for Unsupervised Visual Feature learning

NEURIPS 2020arXiv

citations

Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification

ECCV 2022arXiv

citations

TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection

AAAI 2024arXiv

citations

Density-Aware Graph for Deep Semi-Supervised Visual Recognition

CVPR 2020arXiv

citations

Unifying Multi-Modal Uncertainty Modeling and Semantic Alignment for Text-to-Image Person Re-identification

AAAI 2024

citations

Improve Unsupervised Pretraining for Few-Label Transfer

ICCV 2021arXiv

citations

VRA: Variational Rectified Activation for Out-of-distribution Detection

NEURIPS 2023arXiv

citations

Towards More Unified In-context Visual Understanding

CVPR 2024arXiv

citations

ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning

NEURIPS 2023arXiv

citations

Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation

AAAI 2024arXiv

citations

A Reduction-based Framework for Sequential Decision Making with Delayed Feedback

NEURIPS 2023arXiv

citations

OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition

ICML 2025arXiv

citations

UNICL-SAM: Uncertainty-Driven In-Context Segmentation with Part Prototype Discovery

CVPR 2025

citations

Rethinking Masked Data Reconstruction Pretraining for Strong 3D Action Representation Learning

AAAI 2025

citations

Batch Selection for Multi-Label Classification Guided by Uncertainty and Dynamic Label Correlations

AAAI 2025arXiv

citations

Collaborative Consortium of Foundation Models for Open-World Few-Shot Learning

AAAI 2024

citations

Enhancing Semi-supervised Domain Adaptation via Effective Target Labeling

AAAI 2024

citations

Training-free Open-Vocabulary Semantic Segmentation via Diverse Prototype Construction and Sub-region Matching

AAAI 2025

citations

FE-CLIP: Frequency Enhanced CLIP Model for Zero-Shot Anomaly Detection and Segmentation

ICCV 2025

citations

Bridging the Sky and Ground: Towards View-Invariant Feature Learning for Aerial-Ground Person Re-Identification

ICCV 2025

citations

Bin Liu

papers (25)

Negative Margin Matters: Understanding Margin in Few-shot Classification

Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer

BBDM: Image-to-Image Translation With Brownian Bridge Diffusion Models

ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation

Diverse Semantic Image Synthesis via Probability Distribution Modeling

Parametric Instance Classification for Unsupervised Visual Feature learning

Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification

TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection

Density-Aware Graph for Deep Semi-Supervised Visual Recognition

Unifying Multi-Modal Uncertainty Modeling and Semantic Alignment for Text-to-Image Person Re-identification

Improve Unsupervised Pretraining for Few-Label Transfer

VRA: Variational Rectified Activation for Out-of-distribution Detection

Towards More Unified In-context Visual Understanding

ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning

Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation

A Reduction-based Framework for Sequential Decision Making with Delayed Feedback

OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition

UNICL-SAM: Uncertainty-Driven In-Context Segmentation with Part Prototype Discovery

Rethinking Masked Data Reconstruction Pretraining for Strong 3D Action Representation Learning

Batch Selection for Multi-Label Classification Guided by Uncertainty and Dynamic Label Correlations

Collaborative Consortium of Foundation Models for Open-World Few-Shot Learning

Enhancing Semi-supervised Domain Adaptation via Effective Target Labeling

Training-free Open-Vocabulary Semantic Segmentation via Diverse Prototype Construction and Sub-region Matching

FE-CLIP: Frequency Enhanced CLIP Model for Zero-Shot Anomaly Detection and Segmentation

Bridging the Sky and Ground: Towards View-Invariant Feature Learning for Aerial-Ground Person Re-Identification

papers (25)

Negative Margin Matters: Understanding Margin in Few-shot Classification

Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer

BBDM: Image-to-Image Translation With Brownian Bridge Diffusion Models

ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation

Diverse Semantic Image Synthesis via Probability Distribution Modeling

Parametric Instance Classification for Unsupervised Visual Feature learning

Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification

TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection

Density-Aware Graph for Deep Semi-Supervised Visual Recognition

Unifying Multi-Modal Uncertainty Modeling and Semantic Alignment for Text-to-Image Person Re-identification

Improve Unsupervised Pretraining for Few-Label Transfer

VRA: Variational Rectified Activation for Out-of-distribution Detection

Towards More Unified In-context Visual Understanding

ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning

Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation

A Reduction-based Framework for Sequential Decision Making with Delayed Feedback

OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition

UNICL-SAM: Uncertainty-Driven In-Context Segmentation with Part Prototype Discovery

Rethinking Masked Data Reconstruction Pretraining for Strong 3D Action Representation Learning

Batch Selection for Multi-Label Classification Guided by Uncertainty and Dynamic Label Correlations

Collaborative Consortium of Foundation Models for Open-World Few-Shot Learning

Enhancing Semi-supervised Domain Adaptation via Effective Target Labeling

Training-free Open-Vocabulary Semantic Segmentation via Diverse Prototype Construction and Sub-region Matching

FE-CLIP: Frequency Enhanced CLIP Model for Zero-Shot Anomaly Detection and Segmentation

Bridging the Sky and Ground: Towards View-Invariant Feature Learning for Aerial-Ground Person Re-Identification