activity
20172024
most citedLearning Open-World Object Proposals without Learning to Classify

7 citations · 15 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

16 papers · 1 filter

cs.CV2024

Learning Visual Grounding from Generative Vision and Language Model

Shijie Wang, Dahun Kim, Ali Taalimi +2

Visual grounding tasks aim to localize image regions based on natural language references. In this work, we explore whether generative VLMs predominantly trained on image-text data…

cs.CV2024

3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation

Zihao Xiao, Longlong Jing, Shangxuan Wu +9

3D panoptic segmentation is a challenging perception task, especially in autonomous driving. It aims to predict both semantic and instance annotations for 3D points in a scene. Alt…

cs.CV2023

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

Dahun Kim, Anelia Angelova, Weicheng Kuo

We present a new open-vocabulary detection approach based on region-centric image-language pretraining to bridge the gap between image-level pretraining and open-vocabulary object…

cs.CV2023

Contrastive Feature Masking Open-Vocabulary Vision Transformer

Dahun Kim, Anelia Angelova, Weicheng Kuo

We present Contrastive Feature Masking Vision Transformer (CFM-ViT) - an image-text pretraining methodology that achieves simultaneous learning of image- and region-level represent…

cs.CV202310 cited

DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model

Xiuye Gu, Yin Cui, Jonathan Huang +8

Observing the close relationship among panoptic, semantic and instance segmentation tasks, we propose to train a universal multi-dataset multi-task segmentation model: DaTaSeg.We u…

cs.CV2023

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

Dahun Kim, Anelia Angelova, Weicheng Kuo

We present Region-aware Open-vocabulary Vision Transformers (RO-ViT) - a contrastive image-text pretraining recipe to bridge the gap between image-level pretraining and open-vocabu…