Episode-Constrained Cross-Validation in Video Concept Retrieval

Gemert, Jan C. van; Veenman, Cor J.; Geusebroek, Jan‐Mark

doi:10.1109/tmm.2009.2017619

Cited by 10 publications

(8 citation statements)

References 22 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Current action recognition methods determine which action occurs in a video with good accuracy [9,13,23,30,32]. The task of localization is more demanding as it also requires specifying the location where the action happens in the video.…”

Section: Related Workmentioning

confidence: 99%

Action Localization with Tubelets from Motion

Jain

Gemert

Jeǵou

et al. 2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

242

246

View full text Add to dashboard Cite

This paper considers the problem of action localization, where the objective is to determine when and where certain actions appear. We introduce a sampling strategy to produce 2D+t sequences of bounding boxes, called tubelets. Compared to state-of-the-art alternatives, this drastically reduces the number of hypotheses that are likely to include the action of interest. Our method is inspired by a recent technique introduced in the context of image localization. Beyond considering this technique for the first time for videos, we revisit this strategy for 2D+t sequences obtained from super-voxels. Our sampling strategy advantageously exploits a criterion that reflects how action related motion deviates from background motion.We demonstrate the interest of our approach by extensive experiments on two public datasets: UCF Sports and MSR-II. Our approach significantly outperforms the state-of-theart on both datasets, while restricting the search of actions to a fraction of possible bounding box sequences.

show abstract

Section: Related Workmentioning

confidence: 99%

Action Localization with Tubelets from Motion

Jain

Gemert

Jeǵou

et al. 2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

242

246

View full text Add to dashboard Cite

show abstract

“…During training, 10 samples are retrieved from random locations for each frame of each training video, yielding roughly 750.000 samples to be trained by the Decision Forest. The main parameters of the Forest -the randomness and the number of trees -are set through validation [40]. For a test video, samples are extracted every 11 th pixel in width and height for each frame, followed by individual classification.…”

Section: Implementation Detailsmentioning

confidence: 99%

Water detection through spatio-temporal invariant descriptors

Mettes

Tan

Veltkamp

2017

Computer Vision and Image Understanding

View full text Add to dashboard Cite

In this work, we aim to segment and detect water in videos. Water detection is beneficial for appllications such as video search, outdoor surveillance, and systems such as unmanned ground vehicles and unmanned aerial vehicles. The specific problem, however, is less discussed compared to general texture recognition. Here, we analyze several motion properties of water. First, we describe a video pre-processing step, to increase invariance against water reflections and water colours. Second, we investigate the temporal and spatial properties of water and derive corresponding local descriptors. The descriptors are used to locally classify the presence of water and a binary water detection mask is generated through spatio-temporal Markov Random Field regularization of the local classifications. Third, we introduce the Video Water Database, containing several hours of water and non-water videos, to validate our algorithm. Experimental evaluation on the Video Water Database and the DynTex database indicates the effectiveness of the proposed algorithm, outperforming multiple algorithms for dynamic texture recognition and material recognition by ca. 5% and 15% respectively.

show abstract

“…Next to convolutional networks, other competitive object detection methods are based on the bag-of-words (BOW) model [31,33,34] or its Fisher vector incarnation [6,28]. Such methods start with a limited set of object-proposals to reduce the search space.…”

Section: Automatic Object Detectionmentioning

confidence: 99%

Nature Conservation Drones for Automatic Localization and Counting of Animals

Gemert

Verschoor²,

Mettes

et al. 2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

General rightsIt is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulationsIf you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible. Abstract. This paper is concerned with nature conservation by automatically monitoring animal distribution and animal abundance. Typically, such conservation tasks are performed manually on foot or after an aerial recording from a manned aircraft. Such manual approaches are expensive, slow and labor intensive. In this paper, we investigate the combination of small unmanned aerial vehicles (UAVs or "drones") with automatic object recognition techniques as a viable solution to manual animal surveying. Since no controlled data is available, we record our own animal conservation dataset with a quadcopter drone. We evaluate two nature conservation tasks: i) animal detection ii) animal counting using three state-of-the-art generic object recognition methods that are particularly well-suited for on-board detection. Results show that object detection techniques for human-scale photographs do not directly translate to a drone perspective, but that light-weight automatic object detection techniques are promising for nature conservation tasks.

show abstract

Episode-Constrained Cross-Validation in Video Concept Retrieval

Cited by 10 publications

References 22 publications

Action Localization with Tubelets from Motion

Action Localization with Tubelets from Motion

Water detection through spatio-temporal invariant descriptors

Nature Conservation Drones for Automatic Localization and Counting of Animals

Contact Info

Product

Resources

About