Online dictionary learning for sparse coding

Mairal, Julien; Bach, Francis; Ponce, Jean; Sapiro, Guillermo

doi:10.1145/1553374.1553463

Cited by 1,828 publications

(1,460 citation statements)

References 21 publications

Supporting

Mentioning

1,444

Contrasting

Unclassified

Order By: Relevance

“…The dictionary is learned by the algorithm in [62], and the sparse codes are learned using orthogonal matching pursuit (OMP) [62]. The parameter λ is set 0.15.…”

Section: Sparse Codingmentioning

confidence: 99%

Action recognition via spatio-temporal local features: A comprehensive study

Zhen

Shao

2016

Image and Vision Computing

View full text Add to dashboard Cite

Local methods based on spatio-temporal interest points (STIPs) have shown their effectiveness for human action recognition. The bag-of-words (BoW) model has been widely used and dominated in this field. Recently, a large number of techniques based on local features including improved variants of the BoW model, sparse coding (SC), Fisher kernels (FK), vector of locally aggregated descriptors (VLAD) as well as the naive Bayes nearest neighbor (NBNN) classifier have been proposed and developed for visual recognition. However, some of them are proposed in the image domain and have not yet been applied to the video domain and it is still unclear how effectively these techniques would perform on action recognition. In this paper, we provide a comprehensive study on these local methods for human action recognition. We implement these techniques and conduct comparison under unified experimental settings on three widely used benchmarks, i.e., the KTH, UCF-YouTube and HMDB51 datasets. We discuss insightfully the findings from the experimental results and draw useful conclusions, which are expected to guide practical applications and future work for the action recognition community.

show abstract

“…The dictionary is learned by the algorithm in [62], and the sparse codes are learned using orthogonal matching pursuit (OMP) [62]. The parameter λ is set 0.15.…”

Section: Sparse Codingmentioning

confidence: 99%

Action recognition via spatio-temporal local features: A comprehensive study

Zhen

Shao

2016

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…Here α(x, D) is the sparse representation for the pair (x, D), and can be done fast using orthogonal matching pursuit (OMP) [49] for which we can leverage the already existing efficient implementations [50,51]. Note that OMP is a greedy algorithm and we resort to it for reasons related to efficiency rather than correctness or exact recovery.…”

Section: Formulationmentioning

confidence: 99%

Action recognition using global spatio-temporal features derived from sparse representations

Somasundaram

Cherian

Morellas

et al. 2014

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Recognizing actions is one of the important challenges in computer vision with respect to video data, with applications to surveillance, diagnostics of mental disorders, and video retrieval. Compared to other data modalities such as documents and images, processing video data demands orders of magnitude higher computational and storage resources. One way to alleviate this difficulty is to focus the computations to informative (salient) regions of the video. In this paper, we propose a novel global spatio-temporal selfsimilarity measure to score saliency using the ideas of dictionary learning and sparse coding. In contrast to existing methods that use local spatio-temporal feature detectors along with descriptors (such as HOG, HOG3D, HOF, etc.), dictionary learning helps consider the saliency in a global setting (on the entire video) in a computationally efficient way. We consider only a small percentage of the most salient (least self-similar) regions found using our algorithm, over which spatio-temporal descriptors such as HOG and region covariance descriptors are computed. The ensemble of such block descriptors in a bag-of-features framework provides a holistic description of the motion sequence which can be used in a classification setting. Experiments on several benchmark datasets in video based action classification demonstrate that our approach performs competitively to the state of the art.

show abstract

“…A recent approach [26] has been proposed to iteratively build a dictionary by processing one element (or a small subset) of the training set at a time. As mentioned by the authors: such online approach "is particularly important in the context of image and video processing [35], where it is common to learn dictionaries adapted to small patches, with training data that may include several millions of these patches (roughly one per pixel and per frame)".…”

Section: Iterative Dictionary Buildingmentioning

confidence: 99%

“…However, Mairal et al [26] approach suffers from excessive computational cost regarding active learning requirements. Indeed, during the dictionary update steps, the new dictionary D t is computed by minimizing a surrogate cost function of the empirical cost function (under some constraints) using both the new annotated data x t and its decomposition α t over the dictionary D t−1 obtained at the previous iteration.…”

Section: Iterative Dictionary Buildingmentioning

confidence: 99%

“…One could, for example, consider very recent work of Mairal et al [26] which iteratively builds a dictionary using on-line techniques in order to speed up the dictionary computation. However, this method is not adapted to the active learning context since all the histograms must be recomputed at each iteration with the new dictionary, and thus there is no strategy for selecting the optimal samples for annotation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Incremental kernel learning for active image retrieval without global dictionaries

Gosselin

Precioso

Philipp‐Foliguet

2011

Pattern Recognition

View full text Add to dashboard Cite

In content-based image retrieval context, a classic strategy consists in computing off-line a dictionary of visual features. This visual dictionary is then used to provide a new representation of the data which should ease any task of classification or retrieval. This strategy, based on past research works in text retrieval, is suitable for the context of batch learning, when a large training set can be built either by using a strong prior knowledge of data semantics (like for textual data) or with an expensive off-line pre-computation. Such an approach has major drawbacks in the context of interactive retrieval, where the user iteratively builds the training data set in a semi-supervised approach by providing positive and negative annotations to the system in the relevance feedback loop. The training set is thus built for each retrieval session without any prior knowledge about the concepts of interest for this session. We propose a completely different approach to build the dictionary on-line from features extracted in relevant images. We design the corresponding kernel function, which is learnt during the retrieval session. For each new label, the kernel function is updated with a complexity linear with respect to the size of the database. We propose an efficient active learning strategy for the weakly supervised retrieval method developed in this paper. Moreover this framework allows the combination of features of different types. Experiments are carried out on standard databases, and show that a small dictionary can be dynamically extracted from the features with better performances than a global one.

show abstract

Online dictionary learning for sparse coding

Cited by 1,828 publications

References 21 publications

Action recognition via spatio-temporal local features: A comprehensive study

Action recognition via spatio-temporal local features: A comprehensive study

Action recognition using global spatio-temporal features derived from sparse representations

Incremental kernel learning for active image retrieval without global dictionaries

Contact Info

Product

Resources

About