activity
20162024
most citedHERO: HiErarchical spatio-tempoRal reasOning with Contrastive Action Correspondence for End-to-End Video Object Grounding

4 citations · 22 across the 18 of their papers we have counts for

collaborators

18 papers

cs.CV2024

Learning Expressive And Generalizable Motion Features For Face Forgery Detection

Jingyi Zhang, Peng Zhang, Jingjing Wang +2

Previous face forgery detection methods mainly focus on appearance features, which may be easily attacked by sophisticated manipulation. Considering the majority of current face ma…

cs.CV2024

Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning

Hang Du, Xuejun Yan, Jingjing Wang +2

Recently, arbitrary-scale point cloud upsampling mechanism became increasingly popular due to its efficiency and convenience for practical applications. To achieve this, most previ…

stat.ML2024

"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach

Lingyu Gu, Yongqi Du, Yuan Zhang +4

Modern deep neural networks (DNNs) are extremely powerful; however, this comes at the price of increased depth and having more parameters per layer, making their training and infer…

math.NA2024

Fast Updating Truncated SVD for Representation Learning with Sparse Matrices

Haoran Deng, Yang Yang, Jiahe Li +3

Updating a truncated Singular Value Decomposition (SVD) is crucial in representation learning, especially when dealing with large-scale data matrices that continuously evolve in pr…

cs.CL2023

MProto: Multi-Prototype Network with Denoised Optimal Transport for Distantly Supervised Named Entity Recognition

Shuhui Wu, Yongliang Shen, Zeqi Tan +4

Distantly supervised named entity recognition (DS-NER) aims to locate entity mentions and classify their types with only knowledge bases or gazetteers and unlabeled corpus. However…

cs.CV20234 cited

Single Domain Dynamic Generalization for Iris Presentation Attack Detection

Yachun Li, Jingjing Wang, Yuhui Chen +2

Iris presentation attack detection (PAD) has achieved great success under intra-domain settings but easily degrades on unseen domains. Conventional domain generalization methods mi…