Recognizing Daily Activities from First-Person Videos with Multi-task Clustering

Yan, Yan; Ricci, Elisa; Liu, Gaowen; Sebe, Nicu

doi:10.1007/978-3-319-16817-3_34

Cited by 11 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multi-task learning [40][41][42][43][44] uses multiple types of data from multiple views to learn the multiple related tasks to improve the accuracy of classification and regression models. Most of these approaches use multiple types of features of same modality for daily activity detection.…”

Section: Multimedia Data Representationmentioning

confidence: 99%

Feature pattern based representation of multimedia documents for efficient knowledge discovery

Pushpalatha

Ananthanarayana

2016

Multimed Tools Appl

View full text Add to dashboard Cite

The rapid growth of multimedia documents has raised huge demand for sophisticated multimedia knowledge discovery systems. The knowledge extraction of the documents mainly relies on the data representation model and the document representation model. As the multimedia document comprised of multimodal multimedia objects, the data representation depends on modality of the objects. The multimodal objects require distinct processing and feature extraction methods resulting in different features with different dimensionalities. Managing multiple types of features is challenging for knowledge extraction tasks. The unified representation of multimedia document benefits the knowledge extraction process, as they are represented by same type of features. The appropriate document representation will benefit the overall decision making process by reducing the search time and memory requirements. In this paper, we propose a domain converting method known as Multimedia to Signal converter (MSC) to represent the multimodal multimedia document in an unified representation by converting multimodal objects as signal objects. A tree based approach known as Multimedia Feature Pattern (MFP) tree is proposed for the compact representation of multimedia documents in terms of features of multimedia objects. The effectiveness of the proposed framework is evaluated by performing the experiments on four multimodal datasets. Experimental results show that the unified representation of multimedia documents helped in improving the classification accuracy for the documents. The MFP tree based representation of multimedia documents not only reduces the search time and memory requirements, also outperforms the competitive approaches for search and retrieval of multimedia documents.Pushpalatha K

show abstract

Section: Multimedia Data Representationmentioning

confidence: 99%

Feature pattern based representation of multimedia documents for efficient knowledge discovery

Pushpalatha

Ananthanarayana

2016

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Multi-task learning has received considerable attention from the vision community, and has been successfully applied to many problems such as image classification [36], visual tracking [37], daily activity recognition from first-person videos [38], image-based indoor localization [39] and head pose classification under motion [40]- [42]. An MTL approach to monocular action recognition is proposed in [43], where the authors exploit relatedness of action categories to learn latent tasks (motion patterns) shared across actions.…”

Section: Multi-task Learningmentioning

confidence: 99%

Multitask Linear Discriminant Analysis for View Invariant Action Recognition

Yan

Ricci

Subramanian

et al. 2014

IEEE Trans. on Image Process.

Self Cite

167

View full text Add to dashboard Cite

Abstract-Robust action recognition under viewpoint changes has received considerable attention recently. To this end, self-similarity matrices (SSMs) have been found to be effective view-invariant action descriptors. To enhance the performance of SSM-based methods, we propose multitask linear discriminant analysis (LDA), a novel multitask learning framework for multiview action recognition that allows for the sharing of discriminative SSM features among different views (i.e., tasks). Inspired by the mathematical connection between multivariate linear regression and LDA, we model multitask multiclass LDA as a single optimization problem by choosing an appropriate class indicator matrix. In particular, we propose two variants of graphguided multitask LDA: 1) where the graph weights specifying view dependencies are fixed a priori and 2) where graph weights are flexibly learnt from the training data. We evaluate the proposed methods extensively on multiview RGB and RGBD video data sets, and experimental results confirm that the proposed approaches compare favorably with the state-of-the-art.Index Terms-Multi-view action recognition, self-similarity matrix, multi-task learning, linear discriminant analysis.

show abstract

“…In this work low-level features are employed, such as line alignment feature, ciated with geodesic flow kernel (GFK), it can predict the snap point confidence. A multi-task clustering approach is proposed in [42,43,44] for daily activity recognition in egocentric videos.…”

mentioning

confidence: 99%