A semantic feature for human motion retrieval

Feng, Yinfu; Xiao, Jun; Zhuang, Yueting; Yang, Xiaosong; Zhang, Jian Jun

doi:10.1002/cav.1505

Cited by 19 publications

(14 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But if a pose feature is probabilistic, there is a way to prevent this disadvantage, that is taking the normalized statistical value of each pose feature as the descriptor of the motion [12]. The computation is very fast, and the performance is robust in motion matching.…”

Section: Related Workmentioning

confidence: 99%

“…This idea is adopted in this paper, so the feature model is trained by the probabilistic model GMM. However, in the work of [12], the key-poses are estimated separately in each motion class, which will cause some redundancy, because the common key-poses shared in different motion classes are duplicated in different models. In this paper, a semi-supervised learning method is applied to take full advantage of the partial pose labels, and all the key-poses are estimated only once in the same time, to overcome the redundancy.…”

Section: Related Workmentioning

confidence: 99%

“…After the GPF feature extraction, we apply the K-means clustering-based key-frame extraction algorithm, introduced by [12], and then a set of key-frames are selected as ŝ = {x T 1 , x T 2 , . .…”

Section: Notations and Pre-processingmentioning

confidence: 99%

“…But unfortunately, most state-of-the-art research classifies a motion by its pose feature directly, and does not utilize the 'key-pose' as a middle level between the pose feature and the motion class. In the work of Qi et al [12], the Gaussian mixture model (GMM) is applied to model the key-poses of every motion class. However, the result of this unsupervised learning method shows that the mean value of each Gaussian model may not align with the motions' semantic category.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A human motion feature based on semi-supervised learning of GMM

et al. 2014

Self Cite

View full text Add to dashboard Cite

those motion data to create realistic motions for new characters by applying motion editing [1,2], motion synthesis [3][4][5] and motion retargeting [6] techniques has become the focus of research in the past several years. However, prior to reusing and processing the old motions, one fundamental problem of identifying and extracting similar motion clips from the database has to be solved. It is essentially a motion matching problem. The general procedure is to calculate a concise and representative feature for each motion, and then compare the similarities with all other motions in the mocap database. The efficiency and accuracy of these motion retrieval and annotation processes largely depend on the property of the used features.Most early work [7] uses textual description such as running, walking, to label existing motions in a database. It does not only involve a lot of manual work, the textual label is also too short and general to fully represent the features of each motion. Later works [8][9][10][11] use the numeric-based features and logic-based features involving the 3D coordinates of each joint in each frame. It includes too much redundant information and the 'huge' feature makes the motion matching really slow. Some recent works [12] present semantic features which better represent the essence of motions and the low dimension of features largely speeds up the motion retrieval process. In this paper, we present a new feature in this category. The work [13] has shown that a human motion clip could be described with some representative poses, which we call the 'key-pose'. Intuitively, two similar motions may share most key-poses, while the motions belonging to different motion classes may share none or only a few key-poses (as shown in Fig. 1). A good selection of key-poses can be used to represent different motion classes. The second benefit to use key-poses as a feature is, although the category of motions is infinite, the types of key-poses are relatively limited. A new category Abstract Using motion capture to create naturally looking motion sequences for virtual character animation has become a standard procedure in the games and visual effects industry. With the fast growth of motion data, the task of automatically annotating new motions is gaining an importance. In this paper, we present a novel statistic feature to represent each motion according to the pre-labeled categories of key-poses. A probabilistic model is trained with semi-supervised learning of the Gaussian mixture model (GMM). Each pose in a given motion could then be described by a feature vector of a series of probabilities by GMM. A motion feature descriptor is proposed based on the statistics of all pose features. The experimental results and comparison with existing work show that our method performs more accurately and efficiently in motion retrieval and annotation.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Notations and Pre-processingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A human motion feature based on semi-supervised learning of GMM

et al. 2014

Self Cite

View full text Add to dashboard Cite

show abstract

“…The textual description is intuitive and efficient, while it requires a lot of manual work for annotating all of the motion sequences in database. To overcome this shortcoming, the content-based human motion retrieval has attracted much attention, which retrieves the motion clips via submitting a similar and short motion clip [5,7,8] as query. However, sometimes it is hard to acquire the appropriate motion clips as query.…”

Section: Introductionmentioning

confidence: 99%

Sketch-based human motion retrieval via selected 2D geometric posture descriptor

et al. 2015

Self Cite

View full text Add to dashboard Cite

a b s t r a c tSketch-based human motion retrieval is a hot topic in computer animation in recent years. In this paper, we present a novel sketch-based human motion retrieval method via selected 2-dimensional (2D) Geometric Posture Descriptor (2GPD). Specially, we firstly propose a rich 2D pose feature call 2D Geometric Posture Descriptor (2GPD), which is effective in encoding the 2D posture similarity by exploiting the geometric relationships among different human body parts. Since the original 2GPD is of high dimension and redundant, a semi-supervised feature selection algorithm derived from Laplacian Score is then adopted to select the most discriminative feature component of 2GPD as feature representation, and we call it as selected 2GPD. Finally, a posture-by-posture motion retrieval algorithm is used to retrieve a motion sequence by sketching several key postures. Experimental results on CMU human motion database demonstrate the effectiveness of our proposed approach.

show abstract

Real‐time motion data annotation via action string

Xiao

Zhuang

Zhang

et al. 2014

Computer Animation & Virtual

Self Cite

View full text Add to dashboard Cite

Even though there is an explosive growth of motion capture data, there is still a lack of efficient and reliable methods to automatically annotate all the motions in a database. Moreover, because of the popularity of mocap devices in home entertainment systems, real-time human motion annotation or recognition becomes more and more imperative. This paper presents a new motion annotation method that achieves both the aforementioned two targets at the same time. It uses a probabilistic pose feature based on the Gaussian Mixture Model to represent each pose. After training a clustered pose feature model, a motion clip could be represented as an action string. Then, a dynamic programming-based string matching method is introduced to compare the differences between action strings. Finally, in order to achieve the real-time target, we construct a hierarchical action string structure to quickly label each given action string. The experimental results demonstrate the efficacy and efficiency of our method.

show abstract

A semantic feature for human motion retrieval

Cited by 19 publications

References 32 publications

A human motion feature based on semi-supervised learning of GMM

A human motion feature based on semi-supervised learning of GMM

Sketch-based human motion retrieval via selected 2D geometric posture descriptor

Real‐time motion data annotation via action string

Contact Info

Product

Resources

About