Learning 3D action models from a few 2D videos for view invariant action recognition

Natarajan, Premkumar; Singh, Vivek Kumar; Nevatia, Ram

doi:10.1109/cvpr.2010.5539876

Cited by 32 publications

(71 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both statistical [10] and graphical [3,18,13,14] frameworks have been proposed in the past. However, most methods try to recognize actions based on human dynamics alone.…”

Section: Related Workmentioning

confidence: 99%

“…However, most methods try to recognize actions based on human dynamics alone. These methods can be grouped on the basis of using 2D [8,23,10] or 3D [20,11,14] action models. 2D approaches work well only for the viewpoint they are trained on.…”

Section: Related Workmentioning

confidence: 99%

“…To avoid use of MOCAP data, poses for whole video sequences can be marked in 2D and be lifted to 3D [19,14]. However, keypose selection using motion energy may not have semantic significance.…”

Section: Action Model Learningmentioning

confidence: 99%

“…2D approaches work well only for the viewpoint they are trained on. [11,20,14] learn 3D action models for viewpoint invariance. [11,14] use foreground blobs for recognition; therefore, their performance depend heavily on accurate foreground extraction.…”

Section: Related Workmentioning

confidence: 99%

“…[11,20,14] learn 3D action models for viewpoint invariance. [11,14] use foreground blobs for recognition; therefore, their performance depend heavily on accurate foreground extraction. Also, human silhouettes are not discriminative enough, from certain viewpoints, for actions performed by movement of hand in front of the actor, e.g.…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

Simultaneous inference of activity, pose and object

Khan

Singh

Nevatia

2012

2012 IEEE Workshop on the Applications of Computer Vision (WACV)

Self Cite

View full text Add to dashboard Cite

Human movements are important cues for recognizing human actions, which can be captured by explicit modeling and tracking of actor or through space-time low-level features. However, relying solely on human dynamics is not enough to discriminate between actions which have similar human dynamics, such as smoking and drinking, irrespective of the modeling method. Object perception plays an important role in such cases. Conversely, human movements are indicative of type of object used for the action. These two processes of object perception and action understanding are thus not independent. Consequently, action recognition improves when human movements and object perception are used in conjunction. Therefore, we propose a probabilistic approach to simultaneously infer what action was performed, what object was used and what poses the actor went through. This joint inference framework can better discriminate between actions and objects which are too similar and lack discriminative features.

show abstract

“…Both statistical [10] and graphical [3,18,13,14] frameworks have been proposed in the past. However, most methods try to recognize actions based on human dynamics alone.…”

Section: Related Workmentioning

confidence: 99%