Landmark recognition with compact BoW histogram and ensemble ELM

Cao, Jiuwen; Chen, Tao; Fan, Jianchao

doi:10.1007/s11042-014-2424-1

Cited by 74 publications

(30 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The former consists of converting the query IPs into a bag of k M A N U S C R I P T clusters (obtained from the reference dataset using a clustering algorithm (e.g. k-means)) and then representing the image (or video) as a histogram of the occurrence of each cluster [25]. The latter consists of determining for each query IP the closest IP from the reference set.…”

Section: Ips Matching Via Sparse Representationmentioning

confidence: 99%

See 1 more Smart Citation

Fusion of appearance and motion-based sparse representations for multi-shot person re-identification

2017

View full text Add to dashboard Cite

Fusion of appearance and motionbased sparse representations for multi-shot person re-identification. Neurocomputing, Elsevier, 2017, 248, pp. AbstractWe present in this paper a multi-shot human re-identification system from video sequences based on interest points (IPs) matching. Our contribution is to take advantage of the complementary of person's appearance and style of its movement that leads to a more robust description with respect to various complexity factors. The proposed contributions include person's description and features matching. For person's description, we propose to exploit a fusion strategy of two complementary features provided by appearance and motion description. We describe motion using spatiotemporal IPs, and use spatial IPs for describing the appearance. For feature matching, we use Sparse Representation (SR) as a local matching method between IPs. The fusion strategy is based on the weighted sum of matched IPs votes and then applying the rule of majority vote. This approach is evaluated on a large public dataset, PRID-2011.The experimental results show that our approach clearly outperforms current state-of-the-art.

show abstract

Section: Ips Matching Via Sparse Representationmentioning

confidence: 99%

“…Re-identification rate (%) Using all test dataset [10] 19.2 SURF-1NN [42] 22.5 Our approach (only SURF-SR) 27 Our approach (only Cuboids-SR) 25.5 Our approach (Fusion): α " 0. 5 28.5 Our approach (Fusion): α " 0.3 31 Using only the 200 common people in evaluation Our approach 31 [48] 28.9…”

Section: Approachmentioning

confidence: 99%

Fusion of appearance and motion-based sparse representations for multi-shot person re-identification

2017

View full text Add to dashboard Cite

show abstract

“…With the random assignments on the input weights, the output weights of ELMs can be directly determined by solving a linear least square problem, which bears similarities to designing the output weights of a radial basis function (RBF) network [37], [38] or neural networks with other activation functions [39], [40]. Besides, some other typical work on ELMs include using evolutionary strategy to optimize the input weights such that a compact ELM can be obtained [41], ELMs with sparse representation [42], integrating fuzzy logic with ELMs to improve the approximation performance [43], employing an ensemble of classifiers with the ELM as the base for performance improvement [44], applications of ELM for effective recognition of landmarks [45], [46], and insightful interpretation of ELMs from the perspective of random neurons, random features, and kernels [47].…”

Section: Introductionmentioning

confidence: 99%

Inverse-Free Extreme Learning Machine With Optimal Information Updating

You

Guo

et al. 2016

IEEE Trans. Cybern.

118

View full text Add to dashboard Cite

The extreme learning machine (ELM) has drawn insensitive research attentions due to its effectiveness in solving many machine learning problems. However, the matrix inversion operation involved in the algorithm is computational prohibitive and limits the wide applications of ELM in many scenarios. To overcome this problem, in this paper, we propose an inverse-free ELM to incrementally increase the number of hidden nodes, and update the connection weights progressively and optimally. Theoretical analysis proves the monotonic decrease of the training error with the proposed updating procedure and also proves the optimality in every updating step. Extensive numerical experiments show the effectiveness and accuracy of the proposed algorithm.

show abstract

“…In recent decades, delayed neural networks have obtained much more considerable attention because they often exist in a lot of areas, such as signal processing, model identification and optimization problem [1][2][3][4][5]. Since that time delays is frequently encountered, the problem of stability analysis of time delayed neural networks is an important point in the field of neural networks recently.…”

Section: Introductionmentioning

confidence: 99%