paper-with-me

Papers

Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos

2017-07-22 · Suman Saha, Gurkirt Singh, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin

Current state-of-the-art human action recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame. In this work we address the problem of action localisation and instance segmentation in which multiple concurrent actions of the same class may be segmented out of an image sequence. We cast the action tube extraction as an energy maximisation problem in which configurations of region proposals in each frame are assigned a cost and the best action tubes are selected via two passes of dynamic programming. One pass associates region proposals in space and time for each action category, and another pass is used to solve for the tube's temporal extent and to enforce a smooth label sequence through the video. In addition, by taking advantage of recent work on action foreground-background segmentation, we are able to associate each tube with class-specific segmentations. We demonstrate the performance of our algorithm on the challenging LIRIS-HARL dataset and achieve a new state-of-the-art result which is 14.3 times better than previous methods.

📄 PDF Abstract BibTeX arXiv:1707.07213

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionInstance SegmentationSemantic SegmentationTemporal Action Localization

Similar Papers 제목 키워드 기반

End-to-End Spatio-Temporal Action Localisation with Video Transformers

2023-04-24 · CVPR 2024 1 · Alexey Gritsenko, Xuehan Xiong, Josip Djolonga, Mostafa Dehghani 외

The most performant spatio-temporal action localisation models use external person proposals and complex external memory banks. We propose a fully end-to-end, purely-transformer based model that directly ingests an input…

Action DetectionAction RecognitionSpatio-Temporal Action Localization

Enhancing super-resolution ultrasound localisation through multi-frame deconvolution exploiting spatiotemporal coherence

2024-07-08 · Su Yan, Clotilde Vié, Marcelo Lerendegui, Herman Verinaz-Jadan 외

Super-resolution ultrasound imaging through microbubble (MB) localisation and tracking, also known as ultrasound localisation microscopy, allows non-invasive sub-diffraction resolution imaging of microvasculature in anim…

DenoisingSuper-Resolution

Online Real-time Multiple Spatiotemporal Action Localisation and Prediction

2016-11-25 · ICCV 2017 10 · Gurkirt Singh, Suman Saha, Michael Sapienza, Philip Torr 외

We present a deep-learning framework for real-time multiple spatio-temporal (S/T) action localisation, classification and early prediction. Current state-of-the-art approaches work offline and are too slow to be useful i…

Early Action PredictionPrediction

Spatio-Temporal Instance Learning: Action Tubes from Class Supervision

2018-07-08 · Pascal Mettes, Cees G. M. Snoek

The goal of this work is spatio-temporal action localization in videos, using only the supervision from video-level class labels. The state-of-the-art casts this weakly-supervised action localization regime as a Multiple…

Action LocalizationMultiple Instance LearningRerankingSpatio-Temporal Action Localization+2

Human Action Localization with Sparse Spatial Supervision

2016-05-17 · Philippe Weinzaepfel, Xavier Martin, Cordelia Schmid

We introduce an approach for spatio-temporal human action localization using sparse spatial supervision. Our method leverages the large amount of annotated humans available today and extracts human tubes by combining a s…

Action LocalizationDiversity