Weakly-Supervised Action Segmentation and Unseen Error Detection in Anomalous Instructional Videos

no code implementations • ICCV 2023 • Reza Ghoddoosian, Isht Dwivedi, Nakul Agarwal, Behzad Dariush

We present a novel method for weakly-supervised action segmentation and unseen error detection in anomalous instructional videos.

Action Segmentation Segmentation

Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos

no code implementations • CVPR 2022 • Reza Ghoddoosian, Isht Dwivedi, Nakul Agarwal, Chiho Choi, Behzad Dariush

Experimental results show efficacy of the proposed methods both qualitatively and quantitatively in two domains of cooking and assembly.

Action Segmentation Segmentation

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

1 code implementation • 12 Oct 2021 • 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.

Action Segmentation Segmentation

Action Duration Prediction for Segment-Level Alignment of Weakly-Labeled Videos

1 code implementation • 20 Nov 2020 • Reza Ghoddoosian, Saif Sayed, Vassilis Athitsos

This paper focuses on weakly-supervised action alignment, where only the ordered sequence of video-level actions is available for training.

A Realistic Dataset and Baseline Temporal Model for Early Drowsiness Detection

6 code implementations • 15 Apr 2019 • Reza Ghoddoosian, Marnim Galib, Vassilis Athitsos

We present a large and public real-life dataset of 60 subjects, with video segments labeled as alert, low vigilant, or drowsy.