Yi-Hsuan Tsai

papers

1,392

total citations

papers (28)

Weakly-Supervised Semantic Segmentation via Sub-Category Exploration

CVPR 2020arXiv

298

citations

Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector

ECCV 2020arXiv

248

citations

Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes

CVPR 2024arXiv

citations

Delving into Motion-Aware Matching for Monocular 3D Object Tracking

ICCV 2023arXiv

citations

Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting

CVPR 2025arXiv

citations

3D-PL: Domain Adaptive Depth Estimation with 3D-Aware Pseudo-Labeling

ECCV 2022arXiv

citations

360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning

NEURIPS 2022arXiv

citations

MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

ICCV 2025arXiv

citations

Self-Training Room Layout via Geometry-aware Ray-casting

ECCV 2024

citations

Colorization of Depth Map via Disentanglement

ECCV 2020

citations

What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning

ICCV 2025arXiv

citations

Learning Phase Mask for Privacy-Preserving Passive Depth Estimation

ECCV 2022

citations

BiFuse: Monocular 360 Depth Estimation via Bi-Projection Fusion

CVPR 2020

citations

Learning To Learn Across Diverse Data Biases in Deep Face Recognition

CVPR 2022

citations

LED2-Net: Monocular 360deg Layout Estimation via Differentiable Depth Rendering

CVPR 2021

citations

Yi-Hsuan Tsai

papers (28)

Weakly-Supervised Semantic Segmentation via Sub-Category Exploration

Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector

Multimodal Prompting With Missing Modalities for Visual Recognition

MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation

Domain Adaptive Semantic Segmentation Using Weak Labels

Learning Cross-Modal Contrastive Features for Video Domain Adaptation

Object Detection with a Unified Label Space from Multiple Datasets

End-to-end Multi-modal Video Temporal Grounding

On Generalizing Beyond Domains in Cross-Domain Continual Learning

Text-Driven Image Editing via Learnable Regions

Cross-Domain Similarity Learning for Face Recognition in Unseen Domains

Learning Semantic Segmentation from Multiple Datasets with Label Shifts

Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection

Towards Interpretable Deep Networks for Monocular Depth Estimation

PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection

Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes

Delving into Motion-Aware Matching for Monocular 3D Object Tracking

Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting

3D-PL: Domain Adaptive Depth Estimation with 3D-Aware Pseudo-Labeling

360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning

MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

Self-Training Room Layout via Geometry-aware Ray-casting

Colorization of Depth Map via Disentanglement

What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning

Learning Phase Mask for Privacy-Preserving Passive Depth Estimation

BiFuse: Monocular 360 Depth Estimation via Bi-Projection Fusion

Learning To Learn Across Diverse Data Biases in Deep Face Recognition

LED2-Net: Monocular 360deg Layout Estimation via Differentiable Depth Rendering

papers (28)

Weakly-Supervised Semantic Segmentation via Sub-Category Exploration

Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector

Multimodal Prompting With Missing Modalities for Visual Recognition

MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation

Domain Adaptive Semantic Segmentation Using Weak Labels

Learning Cross-Modal Contrastive Features for Video Domain Adaptation

Object Detection with a Unified Label Space from Multiple Datasets

End-to-end Multi-modal Video Temporal Grounding

On Generalizing Beyond Domains in Cross-Domain Continual Learning

Text-Driven Image Editing via Learnable Regions

Cross-Domain Similarity Learning for Face Recognition in Unseen Domains

Learning Semantic Segmentation from Multiple Datasets with Label Shifts

Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection

Towards Interpretable Deep Networks for Monocular Depth Estimation

PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection

Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes

Delving into Motion-Aware Matching for Monocular 3D Object Tracking

Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting

3D-PL: Domain Adaptive Depth Estimation with 3D-Aware Pseudo-Labeling

360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning

MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

Self-Training Room Layout via Geometry-aware Ray-casting

Colorization of Depth Map via Disentanglement

What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning

Learning Phase Mask for Privacy-Preserving Passive Depth Estimation

BiFuse: Monocular 360 Depth Estimation via Bi-Projection Fusion

Learning To Learn Across Diverse Data Biases in Deep Face Recognition

LED2-Net: Monocular 360deg Layout Estimation via Differentiable Depth Rendering