Picture for Lumin Xu

Lumin Xu

KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension

Add code
Nov 04, 2024
Viaarxiv icon

TCFormer: Visual Recognition via Token Clustering Transformer

Add code
Jul 16, 2024
Viaarxiv icon

F-LMM: Grounding Frozen Large Multimodal Models

Add code
Jun 09, 2024
Viaarxiv icon

UniFS: Universal Few-shot Instance Perception with Point Representations

Add code
Apr 30, 2024
Viaarxiv icon

CLIM: Contrastive Language-Image Mosaic for Region Representation

Add code
Dec 19, 2023
Viaarxiv icon

Language-driven Open-Vocabulary Keypoint Detection for Animal Body and Face

Add code
Oct 10, 2023
Viaarxiv icon

CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

Add code
Oct 02, 2023
Figure 1 for CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
Figure 2 for CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
Figure 3 for CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
Figure 4 for CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
Viaarxiv icon

GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition

Add code
Aug 28, 2023
Viaarxiv icon

ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild

Add code
Aug 23, 2022
Figure 1 for ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild
Figure 2 for ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild
Figure 3 for ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild
Figure 4 for ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild
Viaarxiv icon

Pose for Everything: Towards Category-Agnostic Pose Estimation

Add code
Jul 21, 2022
Figure 1 for Pose for Everything: Towards Category-Agnostic Pose Estimation
Figure 2 for Pose for Everything: Towards Category-Agnostic Pose Estimation
Figure 3 for Pose for Everything: Towards Category-Agnostic Pose Estimation
Figure 4 for Pose for Everything: Towards Category-Agnostic Pose Estimation
Viaarxiv icon