Mars
Emerging6papers using it
2017first seen
The MARS dataset is a benchmark for evaluating video-based person re-identification methods, containing video sequences with annotated identities to assess the effectiveness of algorithms in recognizing individuals across different camera views.
Papers using Mars (6)
- Region-based Quality Estimation Network For Large-scale Person Re-identificationUnleashing the Potential of Tracklets for Unsupervised Video Person Re-IdentificationSkeletons Speak Louder than Text: A Motion-Aware Pretraining Paradigm for Video-Based Person Re-IdentificationKeyRe-ID: Keypoint-Guided Person Re-Identification using Part-Aware Representation in VideosRevisiting Temporal Modeling for Video-based Person ReIDSpatiotemporal Transformer for Video-based Person Re-identification