Tianfei Zhou

papers

2,300

total citations

papers (21)

Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation

CVPR 2022arXiv

158

citations

Weakly Supervised 3D Object Detection from Lidar Point Cloud

ECCV 2020arXiv

116

citations

Cascaded Human-Object Interaction Recognition

CVPR 2020arXiv

104

citations

Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing

CVPR 2021arXiv

citations

CORE: Cooperative Reconstruction for Multi-Agent Perception

ICCV 2023arXiv

citations

Locality-Aware Inter- and Intra-Video Reconstruction for Self-Supervised Correspondence Learning

CVPR 2022arXiv

citations

Visual Abductive Reasoning

CVPR 2022arXiv

citations

Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation

CVPR 2021arXiv

citations

VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning

NEURIPS 2025arXiv

citations

Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation

NEURIPS 2023arXiv

citations

Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation

CVPR 2023arXiv

citations

Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training

AAAI 2024

citations

Learning Anchor Transformations for 3D Garment Animation

CVPR 2023arXiv

citations

Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection

CVPR 2025arXiv

citations

Prompt Tuning In a Compact Attribute Space

AAAI 2025

citations

CA2C: A Prior-Knowledge-Free Approach for Robust Label Noise Learning via Asymmetric Co-learning and Co-training

ICCV 2025

citations

Tianfei Zhou

papers (21)

Exploring Cross-Image Pixel Contrast for Semantic Segmentation

Rethinking Semantic Segmentation: A Prototype View

Video Object Segmentation with Episodic Graph Memory Networks

Deep Hierarchical Semantic Segmentation

Face Forensics in the Wild

Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation

Weakly Supervised 3D Object Detection from Lidar Point Cloud

Cascaded Human-Object Interaction Recognition

Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing

CORE: Cooperative Reconstruction for Multi-Agent Perception

Locality-Aware Inter- and Intra-Video Reconstruction for Self-Supervised Correspondence Learning

Visual Abductive Reasoning

Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation

VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning

Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation

Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation

Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training

Learning Anchor Transformations for 3D Garment Animation

Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection

Prompt Tuning In a Compact Attribute Space

CA2C: A Prior-Knowledge-Free Approach for Robust Label Noise Learning via Asymmetric Co-learning and Co-training

papers (21)

Exploring Cross-Image Pixel Contrast for Semantic Segmentation

Rethinking Semantic Segmentation: A Prototype View

Video Object Segmentation with Episodic Graph Memory Networks

Deep Hierarchical Semantic Segmentation

Face Forensics in the Wild

Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation

Weakly Supervised 3D Object Detection from Lidar Point Cloud

Cascaded Human-Object Interaction Recognition

Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing

CORE: Cooperative Reconstruction for Multi-Agent Perception

Locality-Aware Inter- and Intra-Video Reconstruction for Self-Supervised Correspondence Learning

Visual Abductive Reasoning

Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation

VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning

Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation

Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation

Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training

Learning Anchor Transformations for 3D Garment Animation

Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection

Prompt Tuning In a Compact Attribute Space

CA2C: A Prior-Knowledge-Free Approach for Robust Label Noise Learning via Asymmetric Co-learning and Co-training