Action Segmentation on Breakfast
84.5AccBIT
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| BITVideo Transcripts=true2023.08 | 84.5 | 89.9 | 85.6 | 73.7 | 93.5 | — | — | |
| PolyphonyInput=MAS2026.05 | 82.5 | 86.1 | 82.2 | 73.2 | 84.3 | — | — | |
| EASTInput=MAEv22026.05 | 82.2 | 85.6 | 81.5 | 71.6 | 83.5 | — | — | |
| PolyphonyInput=I3D2026.05 | 78.6 | 81.9 | 77.8 | 68.3 | 79 | — | — | |
| TCTr2023.03 | 77.5 | 76.6 | 71.1 | 58.5 | 76.1 | — | 72 | |
| TCTr2024.12 | 77.5 | 76.6 | 71.1 | 58.5 | 76.1 | — | 72 | |
| UVASTVideo Transcripts=true2023.08 | 77 | 87.6 | 81.9 | 69.2 | — | — | — | |
| DiffAct2023.03 | 76.4 | 80.3 | 75.9 | 64.6 | 78.4 | — | 75.1 | |
| DiffActmulti-modal features=false2023.03 | 76.4 | 80.3 | 75.9 | 64.6 | 78.4 | — | 75.1 | |
| DiffAct2024.12 | 76.4 | 80.3 | 75.9 | 64.6 | 78.4 | — | 75.1 | |
| ActFusion2024.12 | 76.4 | 81 | 76.2 | 64.7 | 79.3 | — | 75.5 | |
| DiffActInput=I3D2026.05 | 76.4 | 80.3 | 75.9 | 64.6 | 78.4 | — | — | |
| FACTInput=I3D2026.05 | 76.2 | 81.4 | 76.5 | 66.2 | 79.7 | — | — | |
| C2F-TCNmulti-modal features=false2023.03 | 76 | 72.2 | 68.7 | 57.6 | 69.6 | — | 68.8 | |
| TUTmulti-modal features=false2023.03 | 76 | 76.2 | 71.9 | 60 | 73.7 | — | 71.6 | |
| DTL2023.03 | 75.8 | 78.8 | 74.5 | 62.9 | 77.7 | — | 73.9 | |
| DTL2024.12 | 75.8 | 78.8 | 74.5 | 62.9 | 77.7 | — | 73.9 | |
| BIT2023.08 | 75.5 | 80.6 | 75.9 | 64.7 | 79 | — | — | |
| CETNet2022.05 | 74.9 | 79.3 | 74.3 | 61.9 | 77.8 | — | — | |
| CETNetmulti-modal features=false2023.03 | 74.9 | 79.3 | 74.3 | 61.9 | 77.8 | — | 73.6 | |
| FAMMSDTN2023.03 | 74.8 | 78.5 | 72.9 | 60.2 | 77.5 | — | 72.8 | |
| FAMMSDTN2024.12 | 74.8 | 78.5 | 72.9 | 60.2 | 77.5 | — | 72.8 | |
| ASFormerVideo Transcripts=true2023.08 | 74.6 | 85.4 | 78.5 | 63.9 | — | — | — | |
| LTContext2024.12 | 74.2 | 77.6 | 72.6 | 60.1 | 77 | — | 72.3 | |
| LTContextInput=I3D2026.05 | 74.2 | 77.6 | 72.6 | 60.1 | 77 | — | — | |
| Temporal Agg.2024.12 | 74 | 78.8 | 73.7 | 60.8 | 77.8 | — | 73 | |
| ASFormerInference Algorithm=FIFA2022.09 | 73.7 | 76.8 | 71.4 | 58.9 | 75.6 | — | — | |
| Liu et al.multi-modal features=false2023.03 | 73.7 | 77.5 | 72.3 | 59.5 | 76.7 | — | 71.9 | |
| ASFormer2021.10 | 73.5 | 76 | 70.6 | 57.4 | 75 | — | — | |
| ASFormer2022.05 | 73.5 | 76 | 70.6 | 57.4 | 75 | — | — | |
| Singhania et al.2022.09 | 73.5 | 70.1 | 66.6 | 56.2 | 68.2 | — | — | |
| ASFormer2022.09 | 73.5 | 76 | 70.6 | 57.4 | 75 | — | — | |
| ASFormer2023.03 | 73.5 | 76 | 70.6 | 57.4 | 75 | — | 70.5 | |
| ASFormer2023.08 | 73.5 | 76 | 70.6 | 57.4 | 75 | — | — | |
| ASFormer + KARI2024.12 | 73.5 | 76 | 70.6 | 57.4 | 75 | — | 70.5 | |
| C2F-TCNInput=I3D2026.05 | 73.5 | 70.1 | 66.6 | 56.2 | 68.2 | — | — | |
| ASFormerInput=I3D2026.05 | 73.5 | 76 | 70.6 | 57.4 | 75 | — | — | |
| Ours†-BCNbackbone=BCN, search_pipeline=EGI local search2021.01 | 72.9 | 72.5 | 69.9 | 60.2 | 69 | — | — | |
| MSTCN++Video Transcripts=true2023.08 | 72.2 | 84 | 75.7 | 59.4 | — | — | — | |
| DPRN2023.03 | 71.7 | 75.6 | 70.5 | 57.6 | 75.1 | — | 70.1 | |
| SEDT2024.12 | 71.7 | 75.6 | 70.5 | 57.6 | 75.1 | — | 70.1 | |
| MTDA2021.04 | 71 | 74.2 | 68.6 | 56.5 | 73.6 | — | — | |
| MTDA2023.03 | 71 | 74.2 | 68.6 | 56.5 | 73.6 | — | 68.8 | |
| MTDA2024.12 | 71 | 74.2 | 68.6 | 56.5 | 73.6 | — | 68.8 | |
| Ours‡-SSTDAbackbone=SSTDA, search_pipeline=global-to-local searched structure2021.01 | 70.8 | 76.3 | 69.9 | 54.6 | 74.5 | — | — | |
| C2F-TCN2022.05 | 70.8 | 76.3 | 69.9 | 54.6 | 74.5 | — | — | |
| Ours-MS-TCNbackbone=MS-TCN, search_pipeline=global-to-local2021.01 | 70.7 | 74.9 | 69 | 55.2 | 73.3 | — | — | |
| Gao et al.2021.10 | 70.7 | 74.9 | 69 | 55.2 | 73.3 | — | — | |
| Gao et al.2022.09 | 70.7 | 74.9 | 69 | 55.2 | 73.3 | — | — | |
| G2L2023.03 | 70.7 | 74.9 | 69 | 55.2 | 73.3 | — | 68.6 | |
| Global2local2024.12 | 70.7 | 74.9 | 69 | 55.2 | 73.3 | — | 68.6 | |
| BCN2021.01 | 70.4 | 68.7 | 65.5 | 55 | 66.2 | — | — | |
| BCN2021.10 | 70.4 | 68.7 | 65.5 | 55 | 66.2 | — | — | |
| BCN2022.05 | 70.4 | 68.7 | 65.5 | 55 | 66.2 | — | — | |
| BCN2022.09 | 70.4 | 68.7 | 65.5 | 55 | 66.2 | — | — | |
| BCN2023.03 | 70.4 | 68.7 | 65.5 | 55 | 66.2 | — | 65.2 | |
| BCN2024.12 | 70.4 | 68.7 | 65.5 | 55 | 66.2 | — | 65.2 | |
| BCNInput=I3D2026.05 | 70.4 | 68.7 | 65.5 | 55 | 66.2 | — | — | |
| SSTDAbackbone=MS-TCN2021.01 | 70.2 | 75 | 69.1 | 55.2 | 73.7 | — | — | |
| SSTDA2022.05 | 70.2 | 75 | 69.1 | 55.2 | 73.7 | — | — | |
| SSTDA2022.09 | 70.2 | 75 | 69.1 | 55.2 | 73.7 | — | — | |
| ASFormerInference Algorithm=Viterbi2022.09 | 70.2 | 76.1 | 70.5 | 57.1 | 74.5 | — | — | |
| SSTDA2023.03 | 70.2 | 75 | 69.1 | 55.2 | 73.7 | — | 68.6 | |
| SSTDA2024.12 | 70.2 | 75 | 69.1 | 55.2 | 73.7 | — | 68.6 | |
| UVASTInference Algorithm=FIFA2022.09 | 69.7 | 76.9 | 71.5 | 58 | 77.1 | — | — | |
| UVAST2023.03 | 69.7 | 76.9 | 71.5 | 58 | 77.1 | — | 70.6 | |
| UVAST2023.08 | 69.7 | 76.9 | 71.5 | 58 | 77.1 | — | — | |
| UVAST2024.12 | 69.7 | 76.9 | 71.5 | 58 | 77.1 | — | 70.6 | |
| Ours†-MS-TCN++backbone=MS-TCN++, search_pipeline=EGI local search2021.01 | 69.6 | 72.4 | 66.8 | 53.5 | 70.2 | — | — | |
| HASR2023.03 | 69.4 | 74.7 | 69.5 | 57 | 71.9 | — | 68.5 | |
| HASR2024.12 | 69.4 | 74.7 | 69.5 | 57 | 71.9 | — | 68.5 | |
| DTGRM2021.10 | 68.3 | 68.7 | 61.9 | 46.6 | 68.9 | — | — | |
| DTGRM2022.09 | 68.3 | 68.7 | 61.9 | 46.6 | 68.9 | — | — | |
| DTGRMInput=I3D2026.05 | 68.3 | 68.7 | 61.9 | 46.6 | 68.9 | — | — | |
| UVASTDuration Modeling=alignment decoder2022.09 | 68.2 | 76.7 | 70 | 56.6 | 77.2 | — | — | |
| ETSN2022.05 | 67.8 | 74 | 69 | 56.2 | 70.3 | — | — | |
| UARL2023.03 | 67.8 | 65.2 | 59.4 | 47.4 | 66.2 | — | 61.2 | |
| DPRN2024.12 | 67.8 | 65.2 | 59.4 | 47.4 | 66.2 | — | 61.2 | |
| MS-TCN++2021.01 | 67.6 | 64.1 | 58.6 | 45.9 | 65.6 | — | — | |
| ASRF2021.10 | 67.6 | 74.3 | 68.9 | 56.1 | 72.4 | — | — | |
| MS-TCN++2022.05 | 67.6 | 64.1 | 58.6 | 45.9 | 65.6 | — | — | |
| ASRF2022.05 | 67.6 | 74.3 | 68.9 | 56.1 | 72.4 | — | — | |
| MS-TCN++2022.09 | 67.6 | 64.1 | 58.6 | 45.9 | 65.6 | — | — | |
| ASRF2022.09 | 67.6 | 74.3 | 68.9 | 56.1 | 72.4 | — | — | |
| MS-TCN++2023.03 | 67.6 | 64.1 | 58.6 | 45.9 | 65.6 | — | 60.4 | |
| ASRF2023.03 | 67.6 | 74.3 | 68.9 | 56.1 | 72.4 | — | 67.9 | |
| MS-TCN++2023.08 | 67.6 | 64.1 | 58.6 | 45.9 | 64.9 | — | — | |
| ASRF2023.08 | 67.6 | 74.3 | 68.9 | 56.1 | 72.4 | — | — | |
| MS-TCN++2024.12 | 67.6 | 64.1 | 58.6 | 45.9 | 65.6 | — | 60.4 | |
| ASFormer2024.12 | 67.6 | 74.3 | 68.9 | 56.1 | 72.4 | — | 67.9 | |
| MS-TCNFeature Type=I3D2021.04 | 66.3 | 52.6 | 48.1 | 37.9 | 61.7 | — | — | |
| MS-TCN2021.01 | 66.3 | 52.6 | 48.1 | 37.9 | 61.7 | — | — | |
| MS-TCN2021.10 | 66.3 | 52.6 | 48.1 | 37.9 | 61.7 | — | — | |
| MS-TCN2022.05 | 66.3 | 52.6 | 48.1 | 37.9 | 61.7 | — | — | |
| MS-TCN2024.12 | 66.3 | 52.6 | 48.1 | 37.9 | 61.7 | — | 53.3 | |
| MS-TCNInput=I3D2026.05 | 66.3 | 52.6 | 48.1 | 37.9 | 61.7 | — | — | |
| UVASTInference Algorithm=Viterbi2022.09 | 66 | 75.9 | 70 | 57.2 | 76.5 | — | — | |
| MS-TCNFeature Type=IDT2021.04 | 65.1 | 58.2 | 52.9 | 40.8 | 61.4 | — | — | |
| GTRM2021.01 | 65 | 57.5 | 54 | 43.3 | 58.7 | — | — | |
| GTRM2023.03 | 65 | 57.5 | 54 | 43.3 | 58.7 | — | 55.7 |