A hybrid social influence model for pedestrian motion segmentation
Sign Up to like & getrecommendations! Published in 2018 at "Neural Computing and Applications"
DOI: 10.1007/s00521-018-3527-9
Abstract: A hybrid social influence model (HSIM) has been proposed which is a novel and automatic method for pedestrian motion segmentation. One of the major attractions of the HSIM is its capability to handle motion segmentation… read more here.
Keywords: motion; motion segmentation; model; pedestrian motion ... See more keywords
Clustering in pursuit of temporal correlation for human motion segmentation
Sign Up to like & getrecommendations! Published in 2017 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-017-5408-0
Abstract: Temporal correlation is an important property of the video sequence. However, most methods only accomplish the clustering of frames via the measurement of similarity between frame pair, and the temporal correlation among frames is rarely… read more here.
Keywords: temporal correlation; correlation; human motion; motion segmentation ... See more keywords
Learning Clustering for Motion Segmentation
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Circuits and Systems for Video Technology"
DOI: 10.1109/tcsvt.2021.3069094
Abstract: Subspace clustering has been extensively studied from the hypothesis-and-test, algebraic, and spectral clustering-based perspectives. Most assume that only a single type/class of subspace is present. Generalizations to multiple types are non-trivial, plagued by challenges such… read more here.
Keywords: motion segmentation; subspace; linear subspace; learning clustering ... See more keywords
Consistency and Diversity Induced Human Motion Segmentation
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"
DOI: 10.1109/tpami.2022.3147841
Abstract: Subspace clustering is a classical technique that has been widely used for human motion segmentation and other related tasks. However, existing segmentation methods often cluster data without guidance from prior knowledge, resulting in unsatisfactory segmentation… read more here.
Keywords: motion segmentation; consistency; diversity; segmentation ... See more keywords
EM-Driven Unsupervised Learning for Efficient Motion Segmentation
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"
DOI: 10.1109/tpami.2022.3198480
Abstract: In this paper, we present a CNN-based fully unsupervised method for motion segmentation from optical flow. We assume that the input optical flow can be represented as a piecewise set of parametric motion models, typically,… read more here.
Keywords: motion segmentation; network; motion; segmentation ... See more keywords