paper-with-me

Papers

On Evaluating Weakly Supervised Action Segmentation Methods

2020-05-19 · Yaser Souri, Alexander Richard, Luca Minciullo, Juergen Gall

Action segmentation is the task of temporally segmenting every frame of an untrimmed video. Weakly supervised approaches to action segmentation, especially from transcripts have been of considerable interest to the computer vision community. In this work, we focus on two aspects of the use and evaluation of weakly supervised action segmentation approaches that are often overlooked: the performance variance over multiple training runs and the impact of selecting feature extractors for this task. To tackle the first problem, we train each method on the Breakfast dataset 5 times and provide average and standard deviation of the results. Our experiments show that the standard deviation over these repetitions is between 1 and 2.5% and significantly affects the comparison between different approaches. Furthermore, our investigation on feature extraction shows that, for the studied weakly-supervised action segmentation methods, higher-level I3D features perform worse than classical IDT features.

📄 PDF Abstract BibTeX arXiv:2005.09743

Code (0)

등록된 구현이 없습니다.

Tasks

Action SegmentationSegmentation

Similar Papers 제목 키워드 기반

Normalized Cut Loss for Weakly-supervised CNN Segmentation

2018-04-04 · CVPR 2018 6 · Meng Tang, Abdelaziz Djelouah, Federico Perazzi, Yuri Boykov 외

Most recent semantic segmentation methods train deep convolutional neural networks with fully annotated masks requiring pixel-accuracy for good quality training. Common weakly-supervised approaches generate full masks fr…

Interactive SegmentationSegmentationSemantic Segmentation

Learning a Weakly-Supervised Video Actor-Action Segmentation Model with a Wise Selection

2020-03-29 · CVPR 2020 6 · Jie Chen, Zhiheng Li, Jiebo Luo, Chenliang Xu

We address weakly-supervised video actor-action segmentation (VAAS), which extends general video object segmentation (VOS) to additionally consider action labels of the actors. The most successful methods on VOS synthesi…

Action SegmentationSegmentationSemantic SegmentationVideo Object Segmentation+1

DAWN: Domain-Adaptive Weakly Supervised Nuclei Segmentation via Cross-Task Interactions

2024-04-23 · Ye Zhang, Yifeng Wang, Zijie Fang, Hao Bian 외

Weakly supervised segmentation methods have gained significant attention due to their ability to reduce the reliance on costly pixel-level annotations during model training. However, the current weakly supervised nuclei …

Domain AdaptationPseudo LabelSegmentationWeakly supervised segmentation

Fast Weakly Supervised Action Segmentation Using Mutual Consistency

2019-04-05 · Yaser Souri, Mohsen Fayyaz, Luca Minciullo, Gianpiero Francesca 외

Action segmentation is the task of predicting the actions for each frame of a video. As obtaining the full annotation of videos for action segmentation is expensive, weakly supervised approaches that can learn only from …

Action SegmentationSegmentationWeakly Supervised Action Segmentation (Transcript)

Weakly Supervised Actor-Action Segmentation via Robust Multi-Task Ranking

2017-07-01 · CVPR 2017 7 · Yan Yan, Chenliang Xu, Dawen Cai, Jason J. Corso

Fine-grained activity understanding in videos has attracted considerable recent attention with a shift from action classification to detailed actor and action understanding that provides compelling results for perceptual…

Action ClassificationAction SegmentationAction UnderstandingSegmentation