Chen Jun

TL;DR: In this article, an incomplete attribute tagged pedestrian re-identification method and system based on two-level fusion is presented, in which low-level features and high-level general attributive features are preliminarily fused and an attention and saliency model is provided through attributive attention and attention based on statistical significance to measure distances between pedestrian attributive vectors.

TL;DR: In this paper, a spatial-temporal constraint-based target re-identification method is proposed, which includes the following steps that: a visual information probability-based preliminary ranking result is obtained based on the visual information of a target; based on a situation that the target which appears in one camera is impossible to appear in another camera, a Hinge loss function is utilized to construct a filter model to narrow a scope to be inquired; an inter-camera time probability model is realized through Wiebull distribution, and therefore, an inter camera time preliminary probability is represented by

TL;DR: In this article, a dynamic low-resolution pedestrian re-identification method based on scale distance gradient function interface learning is proposed to obtain a good re-ID effect when images are low in resolution and change in scale.

TL;DR: In this article, a specific figure and scene combined video instance retrieval method and system is presented, which comprises the following steps of: retrieving an instance of a particular figure in a video, retrieving a specific scene on the basis of local and global combinatorial optimization; retrieving a video instance on basis of high mark retaining; and fusing a specific Figure retrieval result and a specific Scene retrieval result, for each lens, fusing an initial Scene retrieval results and a Figure retrieval results after adjacent extension, and taking a maximum value of the two fusing results so as to obtain a