Xueqing Deng

papers

487

total citations

papers (11)

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

NEURIPS 2023arXiv

212

citations

Randomized Autoregressive Visual Generation

ICCV 2025arXiv

citations

MaskBit: Embedding-free Image Generation via Bit Tokens

ICLR 2025arXiv

citations

NightLab: A Dual-Level Architecture With Hardness Detection for Segmentation at Night

CVPR 2022arXiv

citations

COCONut: Modernizing COCO Segmentation

CVPR 2024arXiv

citations

DistPro: Searching a Fast Knowledge Distillation Process via Meta Optimization

ECCV 2022arXiv

citations

ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation

CVPR 2025arXiv

citations

Leveraging Panoptic Scene Graph for Evaluating Fine-Grained Text-to-Image Generation

ICCV 2025

citations

Xueqing Deng

papers (11)

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

Randomized Autoregressive Visual Generation

MaskBit: Embedding-free Image Generation via Bit Tokens

NightLab: A Dual-Level Architecture With Hardness Detection for Segmentation at Night

COCONut: Modernizing COCO Segmentation

DistPro: Searching a Fast Knowledge Distillation Process via Meta Optimization

ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation

MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval

Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences

WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception

Leveraging Panoptic Scene Graph for Evaluating Fine-Grained Text-to-Image Generation

papers (11)

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

Randomized Autoregressive Visual Generation

MaskBit: Embedding-free Image Generation via Bit Tokens

NightLab: A Dual-Level Architecture With Hardness Detection for Segmentation at Night

COCONut: Modernizing COCO Segmentation

DistPro: Searching a Fast Knowledge Distillation Process via Meta Optimization

ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation

MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval

Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences

WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception

Leveraging Panoptic Scene Graph for Evaluating Fine-Grained Text-to-Image Generation