activity
20192021
most citedSpatiotemporal Transformer for Video-based Person Re-identification

30 citations · 52 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV202130 cited

Spatiotemporal Transformer for Video-based Person Re-identification

Tianyu Zhang, Longhui Wei, Lingxi Xie +4

Recently, the Transformer module has been transplanted from natural language processing to computer vision. This paper applies the Transformer to video-based person re-identificati…

cs.CV20205 cited

UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification

Tianyu Zhang, Lingxi Xie, Longhui Wei +4

The main difficulty of person re-identification (ReID) lies in collecting annotated data and transferring the model across different domains. This paper presents UnrealPerson, a no…

cs.AI20204 cited

Joint Semantics and Data-Driven Path Representation for Knowledge Graph Inference

Guanglin Niu, Bo Li, Yongfei Zhang +4

Inference on a large-scale knowledge graph (KG) is of great importance for KG applications like question answering. The path-based reasoning models can leverage much information ov…

cs.CL20206 cited

AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding

Guanglin Niu, Bo Li, Yongfei Zhang +2

Recent advances in Knowledge Graph Embedding (KGE) allow for representing entities and relations in continuous vector spaces. Some traditional KGE models leveraging additional type…

cs.CL20197 cited

Rule-Guided Compositional Representation Learning on Knowledge Graphs

Guanglin Niu, Yongfei Zhang, Bo Li +4

Representation learning on a knowledge graph (KG) is to embed entities and relations of a KG into low-dimensional continuous vector spaces. Early KG embedding methods only pay atte…

cs.CV2019

Single Camera Training for Person Re-identification

Tianyu Zhang, Lingxi Xie, Longhui Wei +3

Person re-identification (ReID) aims at finding the same person in different cameras. Training such systems usually requires a large amount of cross-camera pedestrians to be annota…