Local Distance Comparison for Multiple-shot People Re-identification

Zhang, Guanwen; Wang, Yu; Kato, Jien; Marutani, Takafumi; Mase, Kenji

doi:10.1007/978-3-642-37431-9_52

Cited by 24 publications

(30 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…⃝ 2015 The Institute of Electronics, Information and Communication Engineers ance [9]. By utilizing information from existing datasets, an adaptive metric learning method is further introduced to strength the multi-modal distribution properties [11].…”

Section: Copyright Cmentioning

confidence: 99%

“…The metric learning method is effective, however it generally fails to deal with both issues together. One efficient method is to weaken the effects of the non-rigid deformation issue, such as projecting feature representations to common subspaces or formulating them in multi-modal distribution [5], [9], and focus on dealing with the varying illumination issue. In the second group, the approaches are efficient in comparing the corresponding parts against the non-rigid deformation, whereas they rely on hand-crafting the effective features and extracting parts information.…”

Section: Basic Ideamentioning

confidence: 99%

“…These images were selected by maximizing the variance with respect to the resolution, illumination, occlusion, and posture [16], which makes the dataset a very challenging one. Similar as in [5], [7], [9], we choose all the 72 people in the experiments. The 20 people, captured by the same camera view, are also included with the consideration of challenges on wide range of posture, real surveillance footage, and wide range of resolution.…”

Section: Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

Multiple-Shot People Re-Identification by Patch-Wise Learning

Zhang

Kato

Wang

et al. 2015

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARY In this paper, we propose a patch-wise learning based approach to deal with the multiple-shot people re-identification task. In the proposed approach, re-identification is formulated as a patch-wise set-toset matching problem, with each patch set being matched using a specifically learned Mahalanobis distance metric. The proposed approach has two advantages: (1) a patch-wise representation that moderates the ambiguousness of a non-rigid matching problem (of human body) to an approximate rigid one (of body parts); (2) a patch-wise learning algorithm that enables more constraints to be included in the learning process and results in distance metrics of high quality. We evaluate the proposed approach on popular benchmark datasets and confirm its competitive performance compared to the state-of-the-art methods.

show abstract

Section: Copyright Cmentioning

confidence: 99%

Section: Basic Ideamentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Multiple-Shot People Re-Identification by Patch-Wise Learning

Zhang

Kato

Wang

et al. 2015

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…To deal with the first issue, we have proposed a reidentification method based on a local distance comparison framework [12]. Owing to the multi-camera scenario and feature representation, people appearances are generally multi-modal distributed in feature space [2], [10], [12].…”

Section: Introductionmentioning

confidence: 99%

“…Owing to the multi-camera scenario and feature representation, people appearances are generally multi-modal distributed in feature space [2], [10], [12]. Further exploration reveals that in such distributions, the appearance instances of the same person tend to form several separated clusters (called subsets), each with some specific semantic meaning associated with a particular feature property such as color or edge.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Metric Learning for People Re-Identification

Zhang

Kato

Wang

et al. 2014

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYThere exist two intrinsic issues in multiple-shot person reidentification: (1) large differences in camera view, illumination, and nonrigid deformation of posture that make the intra-class variance even larger than the inter-class variance; (2) only a few training data that are available for learning tasks in a realistic re-identification scenario. In our previous work, we proposed a local distance comparison framework to deal with the first issue. In this paper, to deal with the second issue (i.e., to derive a reliable distance metric from limited training data), we propose an adaptive learning method to learn an adaptive distance metric, which integrates prior knowledge learned from a large existing auxiliary dataset and task-specific information extracted from a much smaller training dataset. Experimental results on several public benchmark datasets show that combined with the local distance comparison framework, our adaptive learning method is superior to conventional approaches. key words: multiple-shot people re-identification, adaptive metric learning, local distance comparison

show abstract