Qi She

papers

1,089

total citations

papers (12)

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

ICCV 2025arXiv

citations

Learning the Superpixel in a Non-Iterative and Lifelong Manner

CVPR 2021arXiv

citations

Weakly Supervised Object Localization As Domain Adaption

CVPR 2022arXiv

citations

Unifying Nonlocal Blocks for Neural Networks

ICCV 2021arXiv

citations

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

NEURIPS 2025arXiv

citations

MT-ORL: Multi-Task Occlusion Relationship Learning

ICCV 2021arXiv

citations

Learning Cross-hand Policies of High-DOF Reaching and Grasping

ECCV 2024arXiv

citations

Qi She

papers (12)

Involution: Inverting the Inherence of Convolution for Visual Recognition

ACTION-Net: Multipath Excitation for Action Recognition

MINE: Towards Continuous Depth MPI With NeRF for Novel View Synthesis

Learning From Temporal Gradient for Semi-Supervised Action Recognition

On Learning Contrastive Representations for Learning With Noisy Labels

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Learning the Superpixel in a Non-Iterative and Lifelong Manner

Weakly Supervised Object Localization As Domain Adaption

Unifying Nonlocal Blocks for Neural Networks

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

MT-ORL: Multi-Task Occlusion Relationship Learning

Learning Cross-hand Policies of High-DOF Reaching and Grasping

papers (12)

Involution: Inverting the Inherence of Convolution for Visual Recognition

ACTION-Net: Multipath Excitation for Action Recognition

MINE: Towards Continuous Depth MPI With NeRF for Novel View Synthesis

Learning From Temporal Gradient for Semi-Supervised Action Recognition

On Learning Contrastive Representations for Learning With Noisy Labels

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Learning the Superpixel in a Non-Iterative and Lifelong Manner

Weakly Supervised Object Localization As Domain Adaption

Unifying Nonlocal Blocks for Neural Networks

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

MT-ORL: Multi-Task Occlusion Relationship Learning

Learning Cross-hand Policies of High-DOF Reaching and Grasping