TransVOD (Swin Base)

Reported on 5 benchmarks across 5 tasks · 1 paper · 5 SOTA

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

Methodology4 results

3DonImageNet VID
MAP · uses extra data· 2022-01-13
90.1
best: 93.2 (YOLOV++)
SOTA
TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers arXiv:2201.05047
2D ClassificationonImageNet VID
MAP · uses extra data· 2022-01-13
90.1
best: 93.2 (YOLOV++)
SOTA
TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers arXiv:2201.05047
2D Object DetectiononImageNet VID
MAP · uses extra data· 2022-01-13
90.1
best: 93.2 (YOLOV++)
SOTA
TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers arXiv:2201.05047
16konImageNet VID
MAP · uses extra data· 2022-01-13
90.1
best: 93.2 (YOLOV++)
SOTA
TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers arXiv:2201.05047

Computer Vision1 result

Object DetectiononImageNet VID
MAP · uses extra data· 2022-01-13
90.1
best: 93.2 (YOLOV++)
SOTA
TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers arXiv:2201.05047