Dahun Kim

papers

785

total citations

papers (12)

Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering

NEURIPS 2021arXiv

206

citations

Video Panoptic Segmentation

CVPR 2020arXiv

196

citations

Region-Aware Pretraining for Open-Vocabulary Object Detection With Vision Transformers

CVPR 2023arXiv

113

citations

Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities

CVPR 2024arXiv

citations

Region-centric Image-Language Pretraining for Open-Vocabulary Detection

ECCV 2024arXiv

citations

VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models

CVPR 2025arXiv

citations

Context-Adaptive Multi-Prompt Embedding with Large Language Models for Vision-Language Alignment

COLM 2025arXiv

citations

Rotationally-Temporally Consistent Novel View Synthesis of Human Performance Video

ECCV 2020

citations

Dahun Kim

papers (12)

Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering

Video Panoptic Segmentation

Region-Aware Pretraining for Open-Vocabulary Object Detection With Vision Transformers

CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation

TubeFormer-DeepLab: Video Mask Transformer

Contrastive Feature Masking Open-Vocabulary Vision Transformer

Learning To Associate Every Segment for Video Panoptic Segmentation

Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities

Region-centric Image-Language Pretraining for Open-Vocabulary Detection

VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models

Context-Adaptive Multi-Prompt Embedding with Large Language Models for Vision-Language Alignment

Rotationally-Temporally Consistent Novel View Synthesis of Human Performance Video

papers (12)

Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering

Video Panoptic Segmentation

Region-Aware Pretraining for Open-Vocabulary Object Detection With Vision Transformers

CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation

TubeFormer-DeepLab: Video Mask Transformer

Contrastive Feature Masking Open-Vocabulary Vision Transformer

Learning To Associate Every Segment for Video Panoptic Segmentation

Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities

Region-centric Image-Language Pretraining for Open-Vocabulary Detection

VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models

Context-Adaptive Multi-Prompt Embedding with Large Language Models for Vision-Language Alignment

Rotationally-Temporally Consistent Novel View Synthesis of Human Performance Video