Picture for Yinjie Lei

Yinjie Lei

Recent Advances in Multi-modal 3D Scene Understanding: A Comprehensive Survey and Evaluation

Oct 24, 2023
Figure 1 for Recent Advances in Multi-modal 3D Scene Understanding: A Comprehensive Survey and Evaluation
Figure 2 for Recent Advances in Multi-modal 3D Scene Understanding: A Comprehensive Survey and Evaluation
Figure 3 for Recent Advances in Multi-modal 3D Scene Understanding: A Comprehensive Survey and Evaluation
Figure 4 for Recent Advances in Multi-modal 3D Scene Understanding: A Comprehensive Survey and Evaluation
Viaarxiv icon

Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning

Add code
Sep 06, 2023
Figure 1 for Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning
Figure 2 for Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning
Figure 3 for Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning
Figure 4 for Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning
Viaarxiv icon

Unsupervised Domain Adaptation via Domain-Adaptive Diffusion

Aug 26, 2023
Figure 1 for Unsupervised Domain Adaptation via Domain-Adaptive Diffusion
Figure 2 for Unsupervised Domain Adaptation via Domain-Adaptive Diffusion
Figure 3 for Unsupervised Domain Adaptation via Domain-Adaptive Diffusion
Figure 4 for Unsupervised Domain Adaptation via Domain-Adaptive Diffusion
Viaarxiv icon

Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches

Add code
Aug 13, 2023
Figure 1 for Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches
Figure 2 for Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches
Figure 3 for Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches
Figure 4 for Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches
Viaarxiv icon

End-to-End 3D Dense Captioning with Vote2Cap-DETR

Add code
Jan 06, 2023
Figure 1 for End-to-End 3D Dense Captioning with Vote2Cap-DETR
Figure 2 for End-to-End 3D Dense Captioning with Vote2Cap-DETR
Figure 3 for End-to-End 3D Dense Captioning with Vote2Cap-DETR
Figure 4 for End-to-End 3D Dense Captioning with Vote2Cap-DETR
Viaarxiv icon

ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation

Add code
Dec 12, 2022
Figure 1 for ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation
Figure 2 for ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation
Figure 3 for ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation
Figure 4 for ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation
Viaarxiv icon

Pretrained Language Encoders are Natural Tagging Frameworks for Aspect Sentiment Triplet Extraction

Aug 20, 2022
Figure 1 for Pretrained Language Encoders are Natural Tagging Frameworks for Aspect Sentiment Triplet Extraction
Figure 2 for Pretrained Language Encoders are Natural Tagging Frameworks for Aspect Sentiment Triplet Extraction
Figure 3 for Pretrained Language Encoders are Natural Tagging Frameworks for Aspect Sentiment Triplet Extraction
Figure 4 for Pretrained Language Encoders are Natural Tagging Frameworks for Aspect Sentiment Triplet Extraction
Viaarxiv icon

Semantic-Aware Domain Generalized Segmentation

Add code
Apr 02, 2022
Figure 1 for Semantic-Aware Domain Generalized Segmentation
Figure 2 for Semantic-Aware Domain Generalized Segmentation
Figure 3 for Semantic-Aware Domain Generalized Segmentation
Figure 4 for Semantic-Aware Domain Generalized Segmentation
Viaarxiv icon

Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds

Add code
Mar 31, 2022
Figure 1 for Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds
Figure 2 for Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds
Figure 3 for Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds
Figure 4 for Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds
Viaarxiv icon

Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision

Jan 09, 2022
Figure 1 for Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision
Figure 2 for Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision
Figure 3 for Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision
Figure 4 for Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision
Viaarxiv icon