| Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos | | 91.3 | 94.2 | 95.7 | 89.8 | 92.0 | Semantic2Graph | 2022-09-13 |
| FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation | ✓ Link | 87.5 | 95.6 | 96.1 | 84.5 | 93.5 | FACT | 2024-01-01 |
| Diffusion Action Segmentation | ✓ Link | 84.7 | 91.5 | 92.5 | 82.2 | 89.6 | DiffAct | 2023-03-31 |
| Efficient Temporal Action Segmentation via Boundary-aware Query Voting | ✓ Link | 83.5 | 91.3 | 92.0 | 83.0 | 88.7 | BaFormer | 2024-05-25 |
| SF-TMN: SlowFast Temporal Modeling Network for Surgical Phase Recognition | | 83.1 | 90.7 | 91.9 | 83.0 | 88.9 | SF-TMN(ASFormer) | 2023-06-15 |
| Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos | ✓ Link | 83.0 | 92.0 | 94.1 | 81.2 | 91.6 | Br-Prompt+ASFormer | 2022-03-26 |
| Maximization and restoration: Action segmentation through dilation passing and temporal reconstruction | | 82.9 | 92.0 | 92.9 | 82.0 | 90.9 | DPRN | 2022-05-02 |
| BIT: Bi-Level Temporal Modeling for Efficient Supervised Action Segmentation | | 82.6 | 92.8 | 94.8 | 82.0 | 92.6 | BIT | 2023-08-28 |
| Cross-Enhancement Transformer for Action Segmentation | ✓ Link | 81.3 | 91.2 | 91.8 | 80.3 | 87.9 | CETNet | 2022-05-19 |
| Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation | ✓ Link | 81 | 91.3 | 92.7 | 80.2 | 92.1 | UVAST | 2022-09-01 |
| Alleviating Over-segmentation Errors by Detecting Action Boundaries | ✓ Link | 79.8 | 87.8 | 89.4 | 77.3 | 83.7 | ASRF | 2020-07-14 |
| ASFormer: Transformer for Action Segmentation | ✓ Link | 79.2 | 88.8 | 90.1 | 79.7 | 84.6 | ASFormer | 2021-10-16 |
| Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation | ✓ Link | 78.0 | 89.1 | 90.0 | 79.8 | 86.2 | SSTDA | 2020-03-05 |
| Efficient Two-Step Networks for Temporal Action Segmentation | ✓ Link | 77.9 | 90.0 | 91.1 | 78.2 | 86.2 | ETSN | 2021-04-30 |
| Coarse to Fine Multi-Resolution Temporal Convolutional Network | ✓ Link | 77.7 | 88.8 | 90.3 | 80.8 | 86.4 | C2F-TCN | 2021-05-23 |
| Boundary-Aware Cascade Networks for Temporal Action Segmentation | ✓ Link | 77.3 | 87.1 | 88.5 | 79.8 | 84.4 | BCN | |
| Refining Action Segmentation With Hierarchical Video Representations | ✓ Link | 76.4 | 88.6 | 90.9 | 78.7 | 87.5 | SSTDA + HASR | 2021-01-01 |
| Action Segmentation with Mixed Temporal Domain Adaptation | | 76.2 | 88.4 | 90.5 | 80.0 | 85.8 | DA | 2021-04-15 |
| MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation | ✓ Link | 76.0 | 85.7 | 88.8 | 80.1 | 83.5 | MS-TCN++ | 2020-06-16 |
| MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation | ✓ Link | 75.9 | 86.2 | 88.2 | 79.7 | 83.0 | MS-TCN++(sh) | 2020-06-16 |
| Refining Action Segmentation With Hierarchical Video Representations | ✓ Link | 74.8 | 87.2 | 89.2 | 76.9 | 84.5 | ASRF + HASR | 2021-01-01 |
| MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation | ✓ Link | 74.6 | 85.4 | 87.5 | 79.2 | 81.4 | MS-TCN | 2019-03-05 |
| Do we really need temporal convolutions in action segmentation? | ✓ Link | 74 | 87.2 | 88.2 | 77 | 83.9 | EUT | 2022-05-26 |
| Depthwise Separable Temporal Convolutional Network for Action Segmentation | | 72.84 | 85.44 | 88.30 | 78.10 | 84.05 | DS-TCN | 2021-01-19 |
| Is Weakly-supervised Action Segmentation Ready For Human-Robot Interaction? No, Let's Improve It With Action-union Learning | ✓ Link | 67.3 | 85.5 | 88.2 | 69.2 | 84.0 | AUL | 2023-10-22 |
| Temporal Deformable Residual Networks for Action Segmentation in Videos | | 62.7 | 74.4 | 79.2 | 70.1 | 74.1 | TDRN | 2018-06-01 |
| Temporal Convolutional Networks for Action Segmentation and Detection | ✓ Link | 56.0 | 69.3 | 72.2 | 64.0 | - | ED-TCN | 2016-11-16 |
| Segmental Spatiotemporal CNNs for Fine-grained Action Segmentation | | 41.9 | 54.4 | 58.7 | 60.6 | - | ST-CNN | 2016-02-09 |