Shilong Liu

Affiliations

Tsinghua University

papers

5,795

total citations

papers (16)

Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

ECCV 2024arXiv

3,440

citations

DN-DETR: Accelerate DETR Training by Introducing Query DeNoising

CVPR 2022arXiv

1,000

citations

Mask DINO: Towards a Unified Transformer-Based Framework for Object Detection and Segmentation

CVPR 2023arXiv

542

citations

Shilong Liu

Affiliations

papers (16)

Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

DN-DETR: Accelerate DETR Training by Introducing Query DeNoising

Mask DINO: Towards a Unified Transformer-Based Framework for Object Detection and Segmentation

A Simple Framework for Open-Vocabulary Segmentation and Detection

LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models

Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR

T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

MP-Former: Mask-Piloted Transformer for Image Segmentation

Detection Transformer with Stable Matching

Visual In-Context Prompting

Unsupervised Part Segmentation Through Disentangling Appearance and Shape

Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought

Neural Interactive Keypoint Detection

PREIM3D: 3D Consistent Precise Image Attribute Editing From a Single Image

InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image

DFA3D: 3D Deformable Attention For 2D-to-3D Feature Lifting

papers (16)

Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

DN-DETR: Accelerate DETR Training by Introducing Query DeNoising

Mask DINO: Towards a Unified Transformer-Based Framework for Object Detection and Segmentation

A Simple Framework for Open-Vocabulary Segmentation and Detection

LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models

Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR

T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

MP-Former: Mask-Piloted Transformer for Image Segmentation

Detection Transformer with Stable Matching

Visual In-Context Prompting

Unsupervised Part Segmentation Through Disentangling Appearance and Shape

Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought

Neural Interactive Keypoint Detection

PREIM3D: 3D Consistent Precise Image Attribute Editing From a Single Image

InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image

DFA3D: 3D Deformable Attention For 2D-to-3D Feature Lifting