activity
20152022
most citedLearning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction

103 citations · 476 across the 41 of their papers we have counts for

collaborators
Showing cs.CVShow all

77 papers · 1 filter

cs.CV20222 cited

Hyperbolic Vision Transformers: Combining Improvements in Metric Learning

Aleksandr Ermolov, Leyla Mirvakhabova, Valentin Khrulkov +2

Metric learning aims to learn a highly discriminative model encouraging the embeddings of similar classes to be close in the chosen metrics and pushed apart for dissimilar ones. Th…

cs.CV20226 cited

Federated and Generalized Person Re-identification through Domain and Feature Hallucinating

Fengxiang Yang, Zhun Zhong, Zhiming Luo +2

In this paper, we study the problem of federated domain generalization (FedDG) for person re-identification (re-ID), which aims to learn a generalized model with multiple decentral…

cs.CV20223 cited

Cross-Modality Earth Mover's Distance for Visible Thermal Person Re-Identification

Yongguo Ling, Zhun Zhong, Donglin Cao +4

Visible thermal person re-identification (VT-ReID) suffers from the inter-modality discrepancy and intra-identity variations. Distribution alignment is a popular solution for VT-Re…

cs.CV20222 cited

Local and Global GANs with Semantic-Aware Upsampling for Image Generation

Hao Tang, Ling Shao, Philip H. S. Torr +1

In this paper, we address the task of semantic-guided image generation. One challenge common to most existing image-level generation methods is the difficulty in generating small o…

cs.CV20221 cited

Relation Regularized Scene Graph Generation

Yuyu Guo, Lianli Gao, Jingkuan Song +4

Scene graph generation (SGG) is built on top of detected objects to predict object pairwise visual relations for describing the image content abstraction. Existing works have revea…

cs.CV20225 cited

Fast Differentiable Matrix Square Root

Yue Song, Nicu Sebe, Wei Wang

Computing the matrix square root or its inverse in a differentiable manner is important in a variety of computer vision tasks. Previous methods either adopt the Singular Value Deco…