paper-with-me

Papers

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

2022-03-24 · CVPR 2022 1 · Reza Ghoddoosian, Isht Dwivedi, Nakul Agarwal, Chiho Choi, Behzad Dariush

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 using Dynamic Programming and show its advantages over greedy sliding window approach. We improve our framework by introducing the Online-Offline Discrepancy Loss (OODL) to encourage the segmentation results to have a higher temporal consistency. Furthermore, only during training, we exploit frame-wise correspondence between multiple views as supervision for training weakly-labeled instructional videos. In particular, we investigate three different multi-view inference techniques to generate more accurate frame-wise pseudo ground-truth with no additional annotation cost. We present results and ablation studies on two benchmark multi-view datasets, Breakfast and IKEA ASM. Experimental results show efficacy of the proposed methods both qualitatively and quantitatively in two domains of cooking and assembly.

📄 PDF Abstract BibTeX arXiv:2203.13309

Code (0)

등록된 구현이 없습니다.

Tasks

Action SegmentationSegmentation

Similar Papers 제목 키워드 기반

Branches Mutual Promotion for End-to-End Weakly Supervised Semantic Segmentation

2023-08-09 · Lei Zhu, Hangzhou He, Xinliang Zhang, Qian Chen 외

End-to-end weakly supervised semantic segmentation aims at optimizing a segmentation model in a single-stage training process based on only image annotations. Existing methods adopt an online-trained classification branc…

ClassificationSegmentationSemantic SegmentationWeakly supervised segmentation+2

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 compu…

Action SegmentationSegmentation

Learning from Video and Text via Large-Scale Discriminative Clustering

2017-07-27 · ICCV 2017 10 · Antoine Miech, Jean-Baptiste Alayrac, Piotr Bojanowski, Ivan Laptev 외

Discriminative clustering has been successfully applied to a number of weakly-supervised learning tasks. Such applications include person and action recognition, text-to-video alignment, object co-segmentation and coloca…

Action RecognitionClusteringTemporal Action LocalizationVideo Alignment+3

CG-fusion CAM: Online segmentation of laser-induced damage on large-aperture optics

2023-07-18 · Yueyue Han, Yingyan Huang, Hangcheng Dong, Fengdong Chen 외

Online segmentation of laser-induced damage on large-aperture optics in high-power laser facilities is challenged by complicated damage morphology, uneven illumination and stray light interference. Fully supervised seman…

SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos

2020-06-05 · CVPR 2021 1 · Mingfei Gao, Yingbo Zhou, ran Xu, Richard Socher 외

Online action detection in untrimmed videos aims to identify an action as it happens, which makes it very important for real-time applications. Previous methods rely on tedious annotations of temporal action boundaries f…

Action DetectionAction RecognitionOnline Action Detection