CrossTask
Introduced by Zhukov et al. in Cross-task weakly supervised learning from instructional videos
CrossTask dataset contains instructional videos, collected for 83 different tasks. For each task an ordered list of steps with manual descriptions is provided. The dataset is divided in two parts: 18 primary and 65 related tasks. Videos for the primary tasks are collected manually and provided with annotations for temporal step boundaries. Videos for the related tasks are collected automatically and don't have annotations.
Source: CrossTaskBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
CrossTask
|
VideoCLIP
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
