paper-with-me

Spatio-Temporal Action Localization 벤치마크

Spatio-Temporal Action Localization on AVA-Kinetics

7개 결과 · ⬇ CSV · JSON

val mAP

36.36 37.92 39.48 41.04 42.6 2020-06 2026-09 ACAR (multi-scale, ensemble) — 40.49 (2020-06-14) ACAR (multi-scale, R-101, 8 × 8) — 36.36 (2020-06-14) RM (multi-scale, ensemble) — 40.52 (2021-06-15) RM (multi-scale, ir-CSN-152) — 37.95 (2021-06-15) InternVideo — 41.01 (2022-12-06) VideoMAE V2-g — 42.6 (2023-03-29) STAR/L — 41.7 (2023-04-24) ACAR (multi-scale, ensemble) — 40.49 (2020-06-14) RM (multi-scale, ensemble) — 40.52 (2021-06-15) InternVideo — 41.01 (2022-12-06) VideoMAE V2-g — 42.6 (2023-03-29)
RankModel val mAPtest mAP Extra Training Data PaperCodeYear
1 VideoMAE V2-g 42.6 VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking OpenGVLab/VideoMAEv2 2023
2 STAR/L 41.7 End-to-End Spatio-Temporal Action Localisation with Video Transformers 2023
3 InternVideo 41.01 InternVideo: General Video Foundation Models via Generative and Discriminative Learning opengvlab/internvideo · yingsen1/unimd 2022
4 RM (multi-scale, ensemble) 40.52 Relation Modeling in Spatio-Temporal Action Localization 2021
5 ACAR (multi-scale, ensemble) 40.4939.62 Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization towhee-io/towhee · Siyu-C/ACAR-Net · salmank255/ROADSlowFast 2020
6 RM (multi-scale, ir-CSN-152) 37.95 Relation Modeling in Spatio-Temporal Action Localization 2021
7 ACAR (multi-scale, R-101, 8 × 8) 36.36 Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization towhee-io/towhee · Siyu-C/ACAR-Net · salmank255/ROADSlowFast 2020
1–7 / 7 페이지당 10 20 50 100