Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons (Extended Version)
In this paper, we explore tensor representations that can compactly capture higher-order relationships between skeleton joints for 3D action recognition. We first define RBF kernels on 3D joint sequences, which are then linearized to form kernel descriptors. The higher-order outer-products of these kernel descriptors form our tensor representations. We present two different kernels for action recognition, namely (i) a sequence compatibility kernel that captures the spatio-temporal compatibility of joints in one sequence against those in the other, and (ii) a dynamics compatibility kernel that explicitly models the action dynamics of a sequence. Tensors formed from these kernels are then used to train an SVM. We present experiments on several benchmark datasets and demonstrate state of the art results, substantiating the effectiveness of our representations.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Action RecognitionAction RecognitionFormTemporal Action LocalizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Tensor Representations for Action Recognition
Human actions in video sequences are characterized by the complex interplay between spatial features and their temporal dynamics. In this paper, we propose novel tensor representations for compactly capturing such higher…
Action RecognitionAction Recognition In VideosSkeleton Based Action RecognitionSubspace Kernel Learning on Tensor Sequences
Learning from structured multi-way data, represented as higher-order tensors, requires capturing complex interactions across tensor modes while remaining computationally efficient. We introduce Uncertainty-driven Kernel …
Action RecognitionHigher-order Pooling of CNN Features via Kernel Linearization for Action Recognition
Most successful deep learning algorithms for action recognition extend models designed for image-based tasks such as object recognition to video. Such extensions are typically trained for actions on single video frames o…
Action RecognitionFine-grained Action RecognitionObject RecognitionTemporal Action LocalizationLearning Good State and Action Representations via Tensor Decomposition
The transition kernel of a continuous-state-action Markov decision process (MDP) admits a natural tensor structure. This paper proposes a tensor-inspired unsupervised learning method to identify meaningful low-dimensiona…
Tensor DecompositionGate-Shift-Fuse for Video Action Recognition
Convolutional Neural Networks are the de facto models for image recognition. However 3D CNNs, the straight forward extension of 2D CNNs for video recognition, have not achieved the same success on standard action recogni…
Action RecognitionTemporal Action LocalizationVideo Recognition