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

Xiao, Jun; Tang, Zhangpeng; Feng, Yinfu; Xiao, Zhidong

doi:10.1016/j.sigpro.2015.01.004

Cited by 15 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the methods considering key frames, there is a common defect that the constructed key postures are generally not unique to its authentic motion pattern, which may reduce the discriminability of different motion types. Except the pre-captured motion data, sketch-based posture descriptors also become prevailing recently to retrieve 3D motion and create character animations [5,42,46].…”

Section: Related Workmentioning

confidence: 99%

Retrieval of spatial–temporal motion topics from 3D skeleton data

Men

Leung

2019

Vis Comput

View full text Add to dashboard Cite

Retrieval of a specific human motion from 3D skeleton data is intractable because of its articulated complexity. We propose a context-based motion document formation method to reflect geometric variations by calculating covariance descriptors among skeletal joint locations and joint relative distances, and temporal variations by performing a coarse-to-fine segmentation on the motion sequence. The descriptors of query motion traverse all the motion categories to lock its motion words, which can be regarded as the basic units of a motion document. The discrete motion words of different spatiotemporal descriptors are also mapped to divergent index ranges to add prior knowledge of motion with temporal order to latent Dirichlet allocation (LDA). The similarity matching is based on motion-topic distributions from LDA with semantic meanings. The experiments on public datasets show the effectiveness and robustness of the proposed method over existing models.

show abstract

Section: Related Workmentioning

confidence: 99%

Retrieval of spatial–temporal motion topics from 3D skeleton data

Men

Leung

2019

Vis Comput

View full text Add to dashboard Cite

show abstract

“…In order to avoid the cumbersome semantic understanding problem caused by free‐style sketching, we constrain the user to draw skeletons in a specific order, a policy that is widely adopted by pose and motion retrieval methods [DAC*03,TBvdP04,LIM*12,CLAL12,XTFX15]. After users finish skeleton sketching, the retrieved top rated pose will go through a pose refinement process to match the user's sketches the best.…”

Section: System Overviewmentioning

confidence: 99%

A Suggestive Interface for Sketch-based Character Posing

Wang

et al. 2015

Computer Graphics Forum

View full text Add to dashboard Cite

We present a user-friendly suggestive interface for sketch-based character posing. Our interface provides suggestive information on the sketching canvas in succession by combining image retrieval technique with 3D character posing, while the user is drawing. The system highlights the canvas region where the user should draw on and constrains the user's sketches in a reasonable solution space. This is based on an efficient image descriptor, which is used to measure the distance between the user's sketch and 2D views of 3D poses. In order to achieve faster query response, local sensitive hashing is involved in our system. In addition, sampling-based optimization algorithm is adopted to synthesize and optimize the retrieved 3D pose to match the user's sketches the best. Experiments show that our interface can provide smooth suggestive information to improve the reality of sketching poses and shorten the time required for 3D posing.

show abstract

“…Content-based human MoCap data retrieval has drawn lots of research attention in recent years with many good algorithms proposed. In these algorithms, various modalities of query have been used, which include MoCap clip [1]- [11], hand-drawn sketch [12]- [14], puppet motion [15], [16], Kinect skeleton motion [17] and video clip [18]- [20]. MoCap clips are themselves hard to acquire.…”

Section: Introductionmentioning

confidence: 99%

Video-Based Human Motion Capture Data Retrieval via MotionSet Network

et al. 2020

View full text Add to dashboard Cite

Content-based human motion capture (MoCap) data retrieval facilitates reusing motion data that have already been captured and stored in a database. For a MoCap data retrieval system to get practically deployed, both high precision and natural interface are demanded. Targeting both, we propose a video-based human MoCap data retrieval solution in this work. It lets users to specify a query via a video clip, addresses the representational gap between video and MoCap clips and extracts discriminative motion features for precise retrieval. Specifically, the proposed scheme firstly converts each video clip or MoCap clip at a certain viewpoint to a binary silhouette sequence. Regarding a video or MoCap clip as a set of silhouette images, the proposed scheme uses a convolutional neural network, named MotionSet, to extract the discriminative motion feature of the clip. The extracted motion features are used to match a query to repository MoCap clips for the retrieval. Besides the algorithmic solution, we also contribute a human MoCap dataset and a human motion video dataset in couple that contain various action classes. Experiments show that our proposed scheme achieves an increase of around 0.25 in average MAP and costs about 1/26 time for online retrieval, when compared with the benchmark algorithm.

show abstract

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

Cited by 15 publications

References 41 publications

Retrieval of spatial–temporal motion topics from 3D skeleton data

Retrieval of spatial–temporal motion topics from 3D skeleton data

A Suggestive Interface for Sketch-based Character Posing

Video-Based Human Motion Capture Data Retrieval via MotionSet Network

Contact Info

Product

Resources

About