Topology and channel affinity reinforced global attention for person re‐identification
Sign Up to like & getrecommendations! Published in 2021 at "International Journal of Intelligent Systems"
DOI: 10.1002/int.22506
Abstract: Person re‐identification (re‐id), with the goal to recognize persons from images captured by nonoverlapping cameras, is a challenging topic in computer vision. It has been studied extensively in recent years, and the attention mechanism is… read more here.
Keywords: information; person identification; mifga; topology ... See more keywords
Two-stream person re-identification with multi-task deep neural networks
Sign Up to like & getrecommendations! Published in 2018 at "Machine Vision and Applications"
DOI: 10.1007/s00138-018-0915-1
Abstract: Person re-identification (re-id) with images is very useful in video surveillance to find specific targets. However, it is challenging due to the complex variations of human poses, camera viewpoints, lighting, occlusion, resolution, background clutter and… read more here.
Keywords: multi task; deep neural; task; person identification ... See more keywords
Person re-identification in the real scene based on the deep learning
Sign Up to like & getrecommendations! Published in 2021 at "Artificial Life and Robotics"
DOI: 10.1007/s10015-021-00689-9
Abstract: Person re-identification aims at automatically retrieving a person of interest across multiple non-overlapping camera views. Because of increasing demand for real-world applications in intelligent video surveillance, person re-identification has become an important computer vision task… read more here.
Keywords: identification real; person; real scene; person identification ... See more keywords
A spatial and temporal features mixture model with body parts for video-based person re-identification
Sign Up to like & getrecommendations! Published in 2019 at "Applied Intelligence"
DOI: 10.1007/s10489-019-01459-8
Abstract: The goal of video-based person re-identification is to recognize a person at different camera settings. Most previous methods use features from the full body to represent a person. In this paper, we propose a novel… read more here.
Keywords: video based; person identification; based person; person ... See more keywords
Dual adaptive alignment and partitioning network for visible and infrared cross-modality person re-identification
Sign Up to like & getrecommendations! Published in 2022 at "Applied Intelligence"
DOI: 10.1007/s10489-021-02390-7
Abstract: Visible and infrared person re-identification (VI-ReID) describes the task of matching the images of a person, captured by visible-light and infrared cameras; this is a particular challenge in night time surveillance applications. Existing cross-modality recognition… read more here.
Keywords: modality; cross modality; alignment partitioning; person identification ... See more keywords
Illumination and scale invariant relevant visual features with hypergraph-based learning for multi-shot person re-identification
Sign Up to like & getrecommendations! Published in 2017 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-017-4875-7
Abstract: Person re-identification which aims at matching people across disjoint cameras has received increasing attention due to the widespread use of video surveillance applications. Existing methods concentrate either on robust feature extraction or view-invariant feature transformation.… read more here.
Keywords: person identification; person; multi shot; shot person ... See more keywords
Sparse representations based distributed attribute learning for person re-identification
Sign Up to like & getrecommendations! Published in 2017 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-017-4967-4
Abstract: Searching for specific persons from surveillance videos captured by different cameras, known as person re-identification, is a key yet under-addressed challenge. Difficulties arise from the large variations of human appearance in different poses, and from… read more here.
Keywords: attribute learning; distributed attribute; person identification; sparse representations ... See more keywords
Person re-identification using salient region matching game
Sign Up to like & getrecommendations! Published in 2017 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-017-5541-9
Abstract: The human saliency feature has been increasingly used for person re-identification across non-overlapping cameras but is deficient in retaining the minor features of the salient region, thus resulting in matching accuracy decline. To address this… read more here.
Keywords: matching game; salient region; person identification; region ... See more keywords
Low illumination person re-identification
Sign Up to like & getrecommendations! Published in 2018 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-018-6239-3
Abstract: Low illumination is a common problem for recognition and tracking. Low illumination video-based person re identification (re-id) is an important application in practice. Low illumination usually results in severe loss of visual appearance and space-time… read more here.
Keywords: illumination; illumination person; low illumination; person identification ... See more keywords
Independent metric learning with aligned multi-part features for video-based person re-identification
Sign Up to like & getrecommendations! Published in 2019 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-018-7119-6
Abstract: Video-based person re-identification attracts wide attention because it plays a crucial role for many applications in the video surveillance. The task of video-based person re-identification is to match image sequences of the pedestrian recorded by… read more here.
Keywords: video based; person identification; part; metric learning ... See more keywords
Deep feature learning with mixed distance maximization for person Re-identification
Sign Up to like & getrecommendations! Published in 2019 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-019-07867-9
Abstract: In despite of several advanced approaches, deep learning for person re-identification is still regarded as a challenging task due to local optima in the objective function of the deep networks in addition to various changes… read more here.
Keywords: mixed distance; distance; distance maximization; person identification ... See more keywords