Discriminative Subsequence Mining for Action Classification

Nowozin, Sebastian; BakIr, Gökhan; Tsuda, Koji

doi:10.1109/iccv.2007.4409049

Cited by 143 publications

(107 citation statements)

References 16 publications

Supporting

Mentioning

106

Contrasting

Order By: Relevance

“…Our SVM baseline is comparable to similar methods (e.g. SVM of [4,22,37] ) reported in literature, while our BMRM-SMM performs favorably comparing to these state-of-the-art methods. We attribute it to the contextual information that we are able to exploit through the usage of φ 2 features in our SMM framework.…”

Section: Kth Datasetsupporting

confidence: 60%

Human Action Segmentation and Recognition Using Discriminative Semi-Markov Models

et al. 2010

View full text Add to dashboard Cite

A challenging problem in human action understanding is to jointly segment and recognize human actions from an unseen video sequence, where one person performs a sequence of continuous actions.In this paper, we propose a discriminative semiMarkov model approach, and define a set of features over boundary frames, segments as well as neighboring segments. This enable us to conveniently capture a combination of local and global features that best represent a specific action type. To efficiently solve the inference problem of simultaneously segmentation and recognition, we devise a Viterbi-like dynamic programming algorithm, which is able to process 20 frames per second in practice. Moreover, the model is discriminatively learned from large margin principle, and is formulated as an optimization problem with exponentially many constraints. To solve it efficiently, we present two different optimization algorithms, namely cutting plane method and bundle method, and demonstrate that each can be alternatively deployed in a "plug and play" fashion. From its theoretical aspect, we also analyze the generalization error of the proposed approach and provide a PAC-Bayes bound.A preliminary version has been published at [28].Qingfeng Shi NICTA and ANU, Canberra, Australia E-mail: qinfeng.shi@rsise.anu.edu.au Li Wang Southeast University, Nanjing, China E-mail: wang.li.seu.nj@gmail.com Li Cheng TTI-Chicago, USA E-mail: licheng@tti-c.orgThe proposed approach is evaluated on a variety of datasets, and is shown to perform competitively to the state-of-the-art methods. For example, on KTH dataset, it achieves 95% ± 0.01 recognition accuracy, where the best known result on this dataset is 92% ± 0.03 [8].

show abstract

Section: Kth Datasetsupporting

confidence: 60%

Human Action Segmentation and Recognition Using Discriminative Semi-Markov Models

et al. 2010

View full text Add to dashboard Cite

show abstract

“…Despite these constraints, as shown in Figure 6(c) and (d), the actions are correctly localised and identified. Table 2 shows results by a number of previous published works on the same dataset, including Spat-Temp Dollar: The very sparse spatio-temporal descriptor by Dollar [5] and Subseq Boost Nowozin: The boosted SVM classifier by Nowozin [23]. As Table 6 shows, our proposed technique, Scale Invariant Mined Dense Corners has a higher classification accuracy than other published methods.…”

Section: Methodsmentioning

confidence: 77%

Scale Invariant Action Recognition Using Compound Features Mined from Dense Spatio-temporal Corners

Gilbert

Illingworth

Bowden

2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The use of sparse invariant features to recognise classes of actions or objects has become common in the literature. However, features are often "engineered" to be both sparse and invariant to transformation and it is assumed that they provide the greatest discriminative information. To tackle activity recognition, we propose learning compound features that are assembled from simple 2D corners in both space and time. Each corner is encoded in relation to its neighbours and from an over complete set (in excess of 1 million possible features), compound features are extracted using data mining. The final classifier, consisting of sets of compound features, can then be applied to recognise and localise an activity in real-time while providing superior performance to other state-of-the-art approaches (including those based upon sparse feature detectors). Furthermore, the approach requires only weak supervision in the form of class labels for each training sequence. No ground truth position or temporal alignment is required during training.

show abstract

“…This tree is traversed by one of the basic search algorithms such as depth first search (DFS), breath first search (BFS), or the A * algorithm. Here, we used a variant of A * , and deepened the tree depth gradually (Nowozin et al, 2008). This strategy makes pruning effective when there are short high-gain sequence features.…”

Section: Searching For Sequence Featuresmentioning

confidence: 99%

Learning from Past Treatments and Their Outcome Improves Prediction of In Vivo Response to Anti-HIV Therapy

Saigo

Altmann

Bogojeska

et al. 2011

Statistical Applications in Genetics and Molecular Biology

Self Cite

View full text Add to dashboard Cite

Infections with the human immunodeficiency virus type 1 (HIV-1) are treated with combinations of drugs. Unfortunately, HIV responds to the treatment by developing resistance mutations. Consequently, the genome of the viral target proteins is sequenced and inspected for resistance mutations as part of routine diagnostic procedures for ensuring an effective treatment. For predicting response to a combination therapy, currently available computer-based methods rely on the genotype of the virus and the composition of the regimen as input. However, no available tool takes full advantage of the knowledge about the order of and the response to previously prescribed regimens. The resulting high-dimensional feature space makes existing methods difficult to apply in a straightforward fashion. The machine learning system proposed in this work, sequence boosting, is tailored to exploiting such high-dimensional information, i.e. the extraction of longitudinal features, by utilizing the recent advancements in data mining and boosting.When applied to predicting the latest treatment outcome for 3,759 treatment-experienced patients from the EuResist integrated database, sequence boosting achieved superior performance compared to SVMs with RBF kernels. Moreover, sequence boosting allows an easy access to the discriminative treatment information.Analysis of feature importance values provided by our model confirmed known facts regarding HIV treatment. For instance, application of potent and recently licensed drugs was beneficial for patients, and, conversely, the patient group that was subject to NRTI mono-therapies in the past had poor treatment perspectives today. Furthermore, our model revealed novel biological insights. More precisely, the combination of previously used drugs with their in vivo response is more in- * Hiroto Saigo and Andre Altmann are joint first authors. Please send correspondence to Hiroto Saigo,

show abstract

Discriminative Subsequence Mining for Action Classification

Cited by 143 publications

References 16 publications

Human Action Segmentation and Recognition Using Discriminative Semi-Markov Models

Human Action Segmentation and Recognition Using Discriminative Semi-Markov Models

Scale Invariant Action Recognition Using Compound Features Mined from Dense Spatio-temporal Corners

Learning from Past Treatments and Their Outcome Improves Prediction of In Vivo Response to Anti-HIV Therapy

Contact Info

Product

Resources

About