| ASPnet: Action Segmentation With Shared-Private Representation of Multiple Data Sources | | 88.5 | 91.6 | 92.7 | 91.4 | 87.5 | Br-Prompt+ASPnet (RGB, flow, accelerometer) | 2023-01-01 |
| Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos | | 87.3 | 90.2 | 91.5 | 88.6 | 89.1 | Semantic2Graph | 2022-09-13 |
| Efficient Temporal Action Segmentation via Boundary-aware Query Voting | ✓ Link | 83.9 | 88.4 | 89.3 | 89.5 | 84.2 | BaFormer | 2024-05-25 |
| Diffusion Action Segmentation | ✓ Link | 83.7 | 89.2 | 90.1 | 88.9 | 85.0 | DiffAct | 2023-03-31 |
| SF-TMN: SlowFast Temporal Modeling Network for Surgical Phase Recognition | | 82.9 | 88.0 | 89.1 | 89.8 | 84.4 | SF-TMN(ASFormer) | 2023-06-15 |
| How Much Temporal Long-Term Context is Needed for Action Segmentation? | ✓ Link | 82.0 | 87.7 | 89.4 | 87.7 | 83.2 | LTContext | 2023-08-22 |
| Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation | ✓ Link | 81.7 | 87.6 | 89.1 | 87.4 | 83.9 | UVAST | 2022-09-01 |
| Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos | ✓ Link | 81.3 | 87.8 | 89.2 | 88.1 | 83.8 | Br-Prompt+ASFormer | 2022-03-26 |
| Do we really need temporal convolutions in action segmentation? | ✓ Link | 81 | 87.5 | 89.2 | 87.4 | 82.9 | EUT | 2022-05-26 |
| Cross-Enhancement Transformer for Action Segmentation | ✓ Link | 80.1 | 86.5 | 87.6 | 86.9 | 81.7 | CETNet | 2022-05-19 |
| Maximization and restoration: Action segmentation through dilation passing and temporal reconstruction | | 79.4 | 86.3 | 87.8 | 87.2 | 82.0 | DPRN | 2022-05-02 |
| ASFormer: Transformer for Action Segmentation | ✓ Link | 79.3 | 85.4 | 85.1 | 85.9 | 81.9 | ASFormer+ASRF | 2021-10-16 |
| Refining Action Segmentation With Hierarchical Video Representations | ✓ Link | 78.5 | 85.7 | 86.6 | 83.9 | 81.0 | ASRF + HASR | 2021-01-01 |
| Alleviating Over-segmentation Errors by Detecting Action Boundaries | ✓ Link | 77.3 | 83.5 | 84.9 | 84.5 | 79.3 | ASRF | 2020-07-14 |
| ASFormer: Transformer for Action Segmentation | ✓ Link | 76.0 | 83.4 | 85.1 | 85.6 | 79.6 | ASFormer | 2021-10-16 |
| Efficient Two-Step Networks for Temporal Action Segmentation | ✓ Link | 75.4 | 83.9 | 85.2 | 82.0 | 78.8 | ETSN | 2021-04-30 |
| Boundary-Aware Cascade Networks for Temporal Action Segmentation | ✓ Link | 74 | 81.3 | 82.3 | 84.4 | 74.3 | BCN | |
| Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation | ✓ Link | 73.8 | 81.5 | 83.0 | 83.2 | 75.8 | SSTDA | 2020-03-05 |
| Coarse to Fine Multi-Resolution Temporal Convolutional Network | ✓ Link | 72.6 | 81.8 | 84.3 | 84.9 | 76.4 | C2F-TCN | 2021-05-23 |
| Action Segmentation with Mixed Temporal Domain Adaptation | | 72.5 | 80.1 | 82.0 | 83.2 | 75.2 | DA | 2021-04-15 |
| MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation | ✓ Link | 70.1 | 78.5 | 80.7 | 83.7 | 74.3 | MS-TCN++ | 2020-06-16 |
| Global2Local: Efficient Structure Search for Video Action Segmentation | ✓ Link | 69.8 | 78 | 80.3 | 82.2 | 73.4 | G2L (MS-TCN) | 2021-01-04 |
| MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation | ✓ Link | 68.3 | 76.6 | 78.7 | 82.2 | 70.7 | MS-TCN++(sh) | 2020-06-16 |
| Is Weakly-supervised Action Segmentation Ready For Human-Robot Interaction? No, Let's Improve It With Action-union Learning | ✓ Link | 67.1 | 81.3 | 84.4 | 77.9 | 77.0 | AUL | 2023-10-22 |
| Temporal Relational Modeling with Self-Supervision for Action Segmentation | ✓ Link | 66.1 | 75.9 | 79.1 | 80 | 72 | DTGRM | 2020-12-14 |
| Depthwise Separable Temporal Convolutional Network for Action Segmentation | | 65.78 | 74.43 | 77.0 | 80.0 | 70.0 | DS-TCN | 2021-01-19 |
| MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation | ✓ Link | 64.5 | 74.0 | 76.3 | 80.7 | 67.9 | MS-TCN | 2019-03-05 |
| Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation | ✓ Link | | | | 66.5 | | TW-FINCH (K=avg/activity) | 2021-03-20 |