Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos
This work addresses the problem of analyzing instructional videos with weak labels for applications like video understanding and automation, representing a strong specific gain in this domain.
The paper tackles task recognition and action segmentation in weakly-labeled instructional videos by proposing a two-stream hierarchical framework, achieving significant performance improvements on Breakfast and Cooking 2 datasets and reducing segmentation inference time by 80-90%.
This paper focuses on task recognition and action segmentation in weakly-labeled instructional videos, where only the ordered sequence of video-level actions is available during training. We propose a two-stream framework, which exploits semantic and temporal hierarchies to recognize top-level tasks in instructional videos. Further, we present a novel top-down weakly-supervised action segmentation approach, where the predicted task is used to constrain the inference of fine-grained action sequences. Experimental results on the popular Breakfast and Cooking 2 datasets show that our two-stream hierarchical task modeling significantly outperforms existing methods in top-level task recognition for all datasets and metrics. Additionally, using our task recognition framework in the proposed top-down action segmentation approach consistently improves the state of the art, while also reducing segmentation inference time by 80-90 percent.