Temporal action segmentation: An analysis of modern techniques
Temporal action segmentation (TAS) in videos aims at densely identifying video frames in
minutes-long videos with multiple action classes. As a long-range video understanding task …
minutes-long videos with multiple action classes. As a long-range video understanding task …
Fine-grained temporal contrastive learning for weakly-supervised temporal action localization
We target at the task of weakly-supervised action localization (WSAL), where only video-
level action labels are available during model training. Despite the recent progress, existing …
level action labels are available during model training. Despite the recent progress, existing …
Deep learning approaches for seizure video analysis: A review
Seizure events can manifest as transient disruptions in the control of movements which may
be organized in distinct behavioral sequences, accompanied or not by other observable …
be organized in distinct behavioral sequences, accompanied or not by other observable …
Weakly-supervised action segmentation and unseen error detection in anomalous instructional videos
R Ghoddoosian, I Dwivedi… - Proceedings of the …, 2023 - openaccess.thecvf.com
We present a novel method for weakly-supervised action segmentation and unseen error
detection in anomalous instructional videos. In the absence of an appropriate dataset for this …
detection in anomalous instructional videos. In the absence of an appropriate dataset for this …
Stepformer: Self-supervised step discovery and localization in instructional videos
Instructional videos are an important resource to learn procedural tasks from human
demonstrations. However, the instruction steps in such videos are typically short and sparse …
demonstrations. However, the instruction steps in such videos are typically short and sparse …
Drop-dtw: Aligning common signal between sequences while dropping outliers
In this work, we consider the problem of sequence-to-sequence alignment for signals
containing outliers. Assuming the absence of outliers, the standard Dynamic Time Warping …
containing outliers. Assuming the absence of outliers, the standard Dynamic Time Warping …
Video-text representation learning via differentiable weak temporal alignment
Learning generic joint representations for video and text by a supervised method requires a
prohibitively substantial amount of manually annotated video datasets. As a practical …
prohibitively substantial amount of manually annotated video datasets. As a practical …
Weakly-supervised online action segmentation in multi-view instructional videos
This paper addresses a new problem of weakly-supervised online action segmentation in
instructional videos. We present a framework to segment streaming videos online at test time …
instructional videos. We present a framework to segment streaming videos online at test time …
Flow graph to video grounding for weakly-supervised multi-step localization
In this work, we consider the problem of weakly-supervised multi-step localization in
instructional videos. An established approach to this problem is to rely on a given list of …
instructional videos. An established approach to this problem is to rely on a given list of …
Semi-weakly-supervised learning of complex actions from instructional task videos
Y Shen, E Elhamifar - … of the IEEE/CVF Conference on …, 2022 - openaccess.thecvf.com
We address the problem of action segmentation in instructional task videos with a small
number of weakly-labeled training videos and a large number of unlabeled videos, which …
number of weakly-labeled training videos and a large number of unlabeled videos, which …