paper-with-me

Papers

Unsupervised Action Segmentation for Instructional Videos

2021-06-07 · AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo, Irfan Essa

In this paper we address the problem of automatically discovering atomic actions in unsupervised manner from instructional videos, which are rarely annotated with atomic actions. We present an unsupervised approach to learn atomic actions of structured human tasks from a variety of instructional videos based on a sequential stochastic autoregressive model for temporal segmentation of videos. This learns to represent and discover the sequential relationship between different atomic actions of the task, and which provides automatic and unsupervised self-labeling.

📄 PDF Abstract BibTeX arXiv:2106.03738

Code (0)

등록된 구현이 없습니다.

Tasks

Action SegmentationSegmentationUnsupervised Action Segmentation

Similar Papers 제목 키워드 기반

Unsupervised Discovery of Actions in Instructional Videos

2021-06-28 · AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo, Irfan Essa

In this paper we address the problem of automatically discovering atomic actions in unsupervised manner from instructional videos. Instructional videos contain complex activities and are a rich source of information for …

A Benchmark for Structured Procedural Knowledge Extraction from Cooking Videos

2020-05-02 · EMNLP (nlpbt) 2020 11 · Frank F. Xu, Lei Ji, Botian Shi, Junyi Du 외

Watching instructional videos are often used to learn about procedures. Video captioning is one way of automatically collecting such knowledge. However, it provides only an indirect, overall evaluation of multimodal mode…

Action DetectionFormSemantic Role LabelingSentence+1

Unsupervised Learning and Segmentation of Complex Activities from Video

2018-03-26 · CVPR 2018 6 · Fadime Sener, Angela Yao

This paper presents a new method for unsupervised segmentation of complex activities from video into multiple steps, or sub-activities, without any textual input. We propose an iterative discriminative-generative approac…

Learning to Segment Actions from Observation and Narration

2020-05-07 · ACL 2020 6 · Daniel Fried, Jean-Baptiste Alayrac, Phil Blunsom, Chris Dyer 외

We apply a generative segmental model of task structure, guided by narration, to action segmentation in video. We focus on unsupervised and weakly-supervised settings where no action labels are known during training. Des…

Action SegmentationSegmentation

Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos

2021-10-12 · Reza Ghoddoosian, Saif Sayed, Vassilis Athitsos

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 framewor…

Action SegmentationSegmentation