Action Segmentation
Action Segmentation is a challenging problem in high-level video understanding. In its simplest form, Action Segmentation aims to segment a temporally untrimmed video by time and label each segmented part with one of pre-defined action labels. The results of Action Segmentation can be further used as input to various applications, such as video-to-text and action localization.
Source: TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation
Papers
Showing 1–10 of 219 papers
All datasetsBreakfast50 SaladsGTEACOINAssembly101JIGSAWSYoutube INRIA Instructional50SaladsMPII Cooking 2 Dataset
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Br-Prompt+ASPnet (RGB, flow, accelerometer) | F1@50% | 88.5 | — | Unverified |
| 2 | Semantic2Graph | F1@50% | 87.3 | — | Unverified |
| 3 | BaFormer | F1@50% | 83.9 | — | Unverified |
| 4 | DiffAct | F1@50% | 83.7 | — | Unverified |
| 5 | SF-TMN(ASFormer) | F1@50% | 82.9 | — | Unverified |
| 6 | LTContext | F1@50% | 82 | — | Unverified |
| 7 | UVAST | F1@50% | 81.7 | — | Unverified |
| 8 | Br-Prompt+ASFormer | F1@50% | 81.3 | — | Unverified |
| 9 | EUT | F1@50% | 81 | — | Unverified |
| 10 | CETNet | F1@50% | 80.1 | — | Unverified |