Alert button
Picture for Zehuan Yuan

Zehuan Yuan

Alert button

UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces

Dec 25, 2023
Jiannan Wu, Yi Jiang, Bin Yan, Huchuan Lu, Zehuan Yuan, Ping Luo

Viaarxiv icon

General Object Foundation Model for Images and Videos at Scale

Dec 14, 2023
Junfeng Wu, Yi Jiang, Qihao Liu, Zehuan Yuan, Xiang Bai, Song Bai

Viaarxiv icon

Recognize Any Regions

Nov 02, 2023
Haosen Yang, Chuofan Ma, Bin Wen, Yi Jiang, Zehuan Yuan, Xiatian Zhu

Viaarxiv icon

CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection

Oct 25, 2023
Chuofan Ma, Yi Jiang, Xin Wen, Zehuan Yuan, Xiaojuan Qi

Figure 1 for CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection
Figure 2 for CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection
Figure 3 for CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection
Figure 4 for CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection
Viaarxiv icon

EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE

Aug 23, 2023
Junyi Chen, Longteng Guo, Jia Sun, Shuai Shao, Zehuan Yuan, Liang Lin, Dongyu Zhang

Figure 1 for EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE
Figure 2 for EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE
Figure 3 for EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE
Figure 4 for EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE
Viaarxiv icon

Exploring Transformers for Open-world Instance Segmentation

Aug 08, 2023
Jiannan Wu, Yi Jiang, Bin Yan, Huchuan Lu, Zehuan Yuan, Ping Luo

Figure 1 for Exploring Transformers for Open-world Instance Segmentation
Figure 2 for Exploring Transformers for Open-world Instance Segmentation
Figure 3 for Exploring Transformers for Open-world Instance Segmentation
Figure 4 for Exploring Transformers for Open-world Instance Segmentation
Viaarxiv icon

ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst

May 25, 2023
Zijia Zhao, Longteng Guo, Tongtian Yue, Sihan Chen, Shuai Shao, Xinxin Zhu, Zehuan Yuan, Jing Liu

Figure 1 for ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
Figure 2 for ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
Figure 3 for ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
Figure 4 for ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
Viaarxiv icon

EGC: Image Generation and Classification via a Diffusion Energy-Based Model

Apr 13, 2023
Qiushan Guo, Chuofan Ma, Yi Jiang, Zehuan Yuan, Yizhou Yu, Ping Luo

Figure 1 for EGC: Image Generation and Classification via a Diffusion Energy-Based Model
Figure 2 for EGC: Image Generation and Classification via a Diffusion Energy-Based Model
Figure 3 for EGC: Image Generation and Classification via a Diffusion Energy-Based Model
Figure 4 for EGC: Image Generation and Classification via a Diffusion Energy-Based Model
Viaarxiv icon

Meta Compositional Referring Expression Segmentation

Apr 12, 2023
Li Xu, Mark He Huang, Xindi Shang, Zehuan Yuan, Ying Sun, Jun Liu

Figure 1 for Meta Compositional Referring Expression Segmentation
Figure 2 for Meta Compositional Referring Expression Segmentation
Figure 3 for Meta Compositional Referring Expression Segmentation
Figure 4 for Meta Compositional Referring Expression Segmentation
Viaarxiv icon

Token Boosting for Robust Self-Supervised Visual Transformer Pre-training

Apr 12, 2023
Tianjiao Li, Lin Geng Foo, Ping Hu, Xindi Shang, Hossein Rahmani, Zehuan Yuan, Jun Liu

Figure 1 for Token Boosting for Robust Self-Supervised Visual Transformer Pre-training
Figure 2 for Token Boosting for Robust Self-Supervised Visual Transformer Pre-training
Figure 3 for Token Boosting for Robust Self-Supervised Visual Transformer Pre-training
Figure 4 for Token Boosting for Robust Self-Supervised Visual Transformer Pre-training
Viaarxiv icon