Results 11 to 20 of about 6,095,709 (227)
Two types of the 3rd person feature in English?!
Ampersand, 2017 This paper aims to investigate the morphosyntactic properties of the person feature in the English imposter construction studied by Collins & Postal. In this construction, the same definite DP can select a 1st person reflexive or a 3rd person reflexive ...
Kaori Furuya
doaj +2 more sources
Joint Detection and Identification Feature Learning for Person Search [PDF]
Computer Vision and Pattern Recognition, 2016 Existing person re-identification benchmarks and methods mainly focus on matching cropped pedestrian images between queries and candidates. However, it is different from real-world scenarios where the annotations of pedestrian bounding boxes are ...
Tong Xiao +4 more
semanticscholar +3 more sources
Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification [PDF]
Computer Vision and Pattern Recognition, 2023 Due to the modality gap between visible and infrared images with high visual ambiguity, learning diverse modality-shared semantic concepts for visible-infrared person re-identification (VI-ReID) remains a challenging problem.
Jiawei Feng, Ancong Wu, Wei-Shi Zheng
semanticscholar +1 more source
Feature Completion Transformer for Occluded Person Re-Identification [PDF]
IEEE transactions on multimedia, 2023 Occluded person re-identification is a challenging problem due to the destruction of occluders in different camera views. Most existing paradigms focus on visible human body parts through some external models to reduce noise interference.
Tao Wang +5 more
semanticscholar +1 more source
Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer [PDF]
AAAI Conference on Artificial Intelligence, 2021 Occluded person re-identification is a challenging task as human body parts could be occluded by some obstacles (e.g. trees, cars, and pedestrians) in certain scenes.
Tao Wang +4 more
semanticscholar +1 more source
Feature Erasing and Diffusion Network for Occluded Person Re-Identification [PDF]
Computer Vision and Pattern Recognition, 2021 Occluded person re-identification (ReID) aims at matching occluded person images to holistic ones across different camera views. Target Pedestrians (TP) are often disturbed by Non-Pedestrian Occlusions (NPO) and Non-Target Pedestrians (NTP).
Zhikang Wang +5 more
semanticscholar +1 more source
Learning Feature Recovery Transformer for Occluded Person Re-Identification [PDF]
IEEE Transactions on Image Processing, 2022 One major issue that challenges person re-identification (Re-ID) is the ubiquitous occlusion over the captured persons. There are two main challenges for the occluded person Re-ID problem, $i.e.$ , the interference of noise during feature matching and ...
Boqiang Xu +3 more
semanticscholar +1 more source
Neural Feature Search for RGB-Infrared Person Re-Identification [PDF]
Computer Vision and Pattern Recognition, 2021 RGB-Infrared person re-identification (RGB-IR ReID) is a challenging cross-modality retrieval problem, which aims at matching the person-of-interest over visible and infrared camera views.
Yehansen Chen +4 more
semanticscholar +1 more source
Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification [PDF]
European Conference on Computer Vision, 2022 Graph-based models have achieved great success in person re-identification tasks recently, which compute the graph topology structure (affinities) among different people first and then pass the information across them to achieve stronger features. But we
Xulin Li +9 more
semanticscholar +1 more source
Feature Completion for Occluded Person Re-Identification [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021 Person re-identification (reID) plays an important role in computer vision. However, existing methods suffer from performance degradation in occluded scenes.
Rui Hou +5 more
semanticscholar +1 more source