Unsupervised Action Proposals Using Support Vector Classifiers for Online Video Processing
| Autor: | Pilar Martin-Martin, Saturnino Maldonado-Bascón, Marcos Baptista Rios, Roberto J. López-Sastre, F.J. Acevedo-Rodriguez |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Computer science
action proposals 02 engineering and technology lcsh:Chemical technology Machine learning computer.software_genre unsupervised learning 01 natural sciences Biochemistry Article computer vision Analytical Chemistry 0202 electrical engineering electronic engineering information engineering Code (cryptography) lcsh:TP1-1185 Electrical and Electronic Engineering Instrumentation action recognition business.industry 010401 analytical chemistry Search engine indexing intelligent video sensor Atomic and Molecular Physics and Optics 0104 chemical sciences Support vector machine Action (philosophy) Feature (computer vision) Filter (video) Unsupervised learning 020201 artificial intelligence & image processing Artificial intelligence business computer |
| Zdroj: | Sensors Volume 20 Issue 10 Sensors (Basel, Switzerland) Sensors, Vol 20, Iss 2953, p 2953 (2020) |
| ISSN: | 1424-8220 |
| DOI: | 10.3390/s20102953 |
| Popis: | In this work, we introduce an intelligent video sensor for the problem of Action Proposals (AP). AP consists of localizing temporal segments in untrimmed videos that are likely to contain actions. Solving this problem can accelerate several video action understanding tasks, such as detection, retrieval, or indexing. All previous AP approaches are supervised and offline, i.e. they need both the temporal annotations of the datasets during training and access to the whole video to effectively cast the proposals. We propose here a new approach which, unlike the rest of the state-of-the-art models, is unsupervised. This implies that we do not allow it to see any labeled data during learning nor to work with any pre-trained feature on the used dataset. Moreover, our approach also operates in an online manner, which can be beneficial for many real-world applications where the video has to be processed as soon as it arrives at the sensor, e.g., robotics or video monitoring. The core of our method is based on a Support Vector Classifier (SVC) module which produces candidate segments for AP by distinguishing between sets of contiguous video frames. We further propose a mechanism to refine and filter those candidate segments. This filter optimizes a learning-to-rank formulation over the dynamics of the segments. An extensive experimental evaluation is conducted on Thumos&rsquo 14 and ActivityNet datasets, and, to the best of our knowledge, this work supposes the first unsupervised approach on these main AP benchmarks. Finally, we also provide a thorough comparison to the current state-of-the-art supervised AP approaches. We achieve 41% and 59% of the performance of the best-supervised model on ActivityNet and Thumos&rsquo 14, respectively, confirming our unsupervised solution as a correct option to tackle the AP problem. The code to reproduce all our results will be publicly released upon acceptance of the paper. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |