Variations of a Hough-Voting Action Recognition System

Waltisberg, Daniel; Yao, Angela; Gall, Jüergen; Gool, Luc Van

doi:10.1007/978-3-642-17711-8_31

Cited by 51 publications

(36 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, only one among them succeeded to submit results for the classification task, which we report with Tables 3 and 4. The team BIWI [19] used a Hough transform-based method to classify interaction videos. Their method is based on [21], which uses a spatio-temporal voting with extracted local XYT features.…”

Section: Resultsmentioning

confidence: 99%

“…Team BIWI BIWI team from ETH Zurich proposes to use a Hough transformbased voting framework for action recognition [19]. They separate the voting into two stages to bypass the inherent high dimensionality problem in Hough transform representation.…”

Section: Resultsmentioning

confidence: 99%

“…We introduce three new public datasets through these challenges, and discuss results of state-ofthe-art activity recognition systems designed and implemented by the contestants. A methodology using a spatio-temporal voting [19] successfully classified segmented videos in the UT-Interaction datasets, but had a difficulty correctly localizing activities from continuous videos. Both the method using local features [10] and the HMM based method [18] recognized actions from low-resolution videos (i.e.…”

mentioning

confidence: 99%

See 2 more Smart Citations

An Overview of Contest on Semantic Description of Human Activities (SDHA) 2010

Ryoo

Chen²,

Aggarwal³

et al. 2010

Lecture Notes in Computer Science

206

153

View full text Add to dashboard Cite

Abstract. This paper summarizes results of the 1st Contest on Semantic Description of Human Activities (SDHA), in conjunction with ICPR 2010. SDHA 2010 consists of three types of challenges, High-level Human Interaction Recognition Challenge, Aerial View Activity Classification Challenge, and Wide-Area Activity Search and Recognition Challenge. The challenges are designed to encourage participants to test existing methodologies and develop new approaches for complex human activity recognition scenarios in realistic environments. We introduce three new public datasets through these challenges, and discuss results of state-ofthe-art activity recognition systems designed and implemented by the contestants. A methodology using a spatio-temporal voting [19] successfully classified segmented videos in the UT-Interaction datasets, but had a difficulty correctly localizing activities from continuous videos. Both the method using local features [10] and the HMM based method [18] recognized actions from low-resolution videos (i.e. UT-Tower dataset) successfully. We compare their results in this paper.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

An Overview of Contest on Semantic Description of Human Activities (SDHA) 2010

Ryoo

Chen²,

Aggarwal³

et al. 2010

Lecture Notes in Computer Science

206

153

View full text Add to dashboard Cite

show abstract

“…Classification results are shown in Table 3 and compared with state-of-the-art recognition systems [22,[60][61][62][63][64][65][66][67][68]. Accordingly, the proposed method has a great improvement in classification accuracy.…”

Section: Resultsmentioning

confidence: 99%

Unsupervised Object Modeling and Segmentation with Symmetry Detection for Human Activity Recognition

Cheng

Huang

2015

Symmetry

View full text Add to dashboard Cite

Abstract:In this paper we present a novel unsupervised approach to detecting and segmenting objects as well as their constituent symmetric parts in an image. Traditional unsupervised image segmentation is limited by two obvious deficiencies: the object detection accuracy degrades with the misaligned boundaries between the segmented regions and the target, and pre-learned models are required to group regions into meaningful objects. To tackle these difficulties, the proposed approach aims at incorporating the pair-wise detection of symmetric patches to achieve the goal of segmenting images into symmetric parts. The skeletons of these symmetric parts then provide estimates of the bounding boxes to locate the target objects. Finally, for each detected object, the graphcut-based segmentation algorithm is applied to find its contour. The proposed approach has significant advantages: no a priori object models are used, and multiple objects are detected. To verify the effectiveness of the approach based on the cues that a face part contains an oval shape and skin colors, human objects are extracted from among the detected objects. The detected human objects and their parts are finally tracked across video frames to capture the object part movements for learning the human activity models from video clips. Experimental results show that the proposed method gives good performance on publicly available datasets.

show abstract

“…This is very challenging video material with far greater variety in actors, shot editing, viewpoint, locations, lighting and clutter than the typical surveillance videos used previously for classifying interactions [3,21,29] where there is a fixed camera and scene. We provide additional ground truth annotation for the dataset, specifying which shots contain people looking at each other.…”

Section: Introductionmentioning

confidence: 99%

"Here's looking at you, kid". Detecting people looking at each other in videos

Marín-Jiménez

Zisserman

Ferrari³

2011

Procedings of the British Machine Vision Conference 2011

View full text Add to dashboard Cite

The objective of this work is to determine if people are interacting in TV video by detecting whether they are looking at each other or not. We determine both the temporal period of the interaction and also spatially localize the relevant people. We make the following three contributions: (i) head pose estimation in unconstrained scenarios (TV video) using Gaussian Process regression; (ii) propose and evaluate several methods for assessing whether and when pairs of people are looking at each other in a video shot; and (iii) introduce new ground truth annotation for this task, extending the TV Human Interactions Dataset [22]. The peformance of the methods is evaluated on this dataset, which consists of 300 video clips extracted from TV shows. Despite the variety and difficulty of this video material, our best method obtains an average precision of 86.2%.

show abstract

Variations of a Hough-Voting Action Recognition System

Cited by 51 publications

References 7 publications

An Overview of Contest on Semantic Description of Human Activities (SDHA) 2010

An Overview of Contest on Semantic Description of Human Activities (SDHA) 2010

Unsupervised Object Modeling and Segmentation with Symmetry Detection for Human Activity Recognition

"Here's looking at you, kid". Detecting people looking at each other in videos

Contact Info

Product

Resources

About