TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/APTM

APTM

Reported on 11 benchmarks across 3 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision10 results

  • Text based Person RetrievalonCUHK-PEDES
    R@1· uses extra data· 2023-06-05
    76.53
    best: 77.62 (MARS)
    SOTA
    Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search BenchmarkarXiv:2306.02898
  • Text based Person RetrievalonICFG-PEDES
    R@1· uses extra data· 2023-06-05
    68.51
    SOTA
    Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search BenchmarkarXiv:2306.02898
  • Text based Person RetrievalonRSTPReid
    R@1· uses extra data· 2023-06-05
    67.5
    best: 67.55 (MARS)
    SOTA
    Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search BenchmarkarXiv:2306.02898
  • Text based Person RetrievalonRSTPReid
    R@10· uses extra data· 2023-06-05
    91.45
    SOTA
    Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search BenchmarkarXiv:2306.02898
  • Pedestrian Attribute RecognitiononPA-100K
    Accuracy· uses extra data· 2023-06-05
    80.17
    best: 90.8 (PATH (Partial FT))
    Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search BenchmarkarXiv:2306.02898
  • Text based Person RetrievalonCUHK-PEDES
    R@10· uses extra data· 2023-06-05
    94.15
    best: 94.27 (MARS)
    Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search BenchmarkarXiv:2306.02898
  • Text based Person RetrievalonCUHK-PEDES
    R@5· uses extra data· 2023-06-05
    90.04
    best: 90.63 (MARS)
    Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search BenchmarkarXiv:2306.02898
  • Text based Person RetrievalonCUHK-PEDES
    mAP· uses extra data· 2023-06-05
    66.91
    best: 71.41 (MARS)
    Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search BenchmarkarXiv:2306.02898
  • Text based Person RetrievalonICFG-PEDES
    mAP· uses extra data· 2023-06-05
    41.22
    best: 44.93 (MARS)
    Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search BenchmarkarXiv:2306.02898
  • Text based Person RetrievalonRSTPReid
    R@5· uses extra data· 2023-06-05
    85.7
    best: 88.2 (IRRA)
    Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search BenchmarkarXiv:2306.02898

Robots1 result

  • Autonomous VehiclesonPA-100K
    Accuracy· uses extra data· 2023-06-05
    80.17
    best: 90.8 (PATH (Partial FT))
    Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search BenchmarkarXiv:2306.02898