Results 161 to 170 of about 6,095,709 (227)
Some of the next articles are maybe not open access.
Learning 3D Shape Feature for Texture-insensitive Person Re-identification
Computer Vision and Pattern Recognition, 2021It is well acknowledged that person re-identification (person ReID) highly relies on visual texture information like clothing. Despite significant progress has been made in recent years, texture-confusing situations like clothing changing and persons ...
Jiaxin Chen +6 more
semanticscholar +1 more source
Conditional Feature Learning Based Transformer for Text-Based Person Search
IEEE Transactions on Image Processing, 2022Text-based person search aims at retrieving the target person in an image gallery using a descriptive sentence of that person. The core of this task is to calculate a similarity score between the pedestrian image and description, which requires inferring
Chenyang Gao +8 more
semanticscholar +1 more source
Person Features and Pronominal Anaphora
Linguistic Inquiry, 2011This article aims at clarifying the role of person at the interface between syntax and the interpretive systems. We argue that first person interpretations of third person pronouns (de se readings) stem from the option of leaving the referential index underspecified on the pronoun, thus accounting for the interplay of this phenomenon with the ...
Delfitto D, Fiorin G
openaire +4 more sources
Personality Features in Essential Hyperhidrosis
The International Journal of Psychiatry in Medicine, 1981The psychological aspects of essential hyperhidrosis, while long recognized, have been minimally investigated. This study compares the personality features of hyperhidrotic subjects to those of normal subjects and persons suffering from dermatological disorders of nonpsychogenic etiology, using the Shanan Sentence Completion Technique, Stein Self ...
B, Lerer, J, Jacobowitz, A, Wahba
openaire +2 more sources
Motion Feature Aggregation for Video-Based Person Re-Identification
IEEE Transactions on Image Processing, 2022Most video-based person re-identification (re-id) methods only focus on appearance features but neglect motion features. In fact, motion features can help to distinguish the target persons that are hard to be identified only by appearance features ...
Xinqian Gu +3 more
semanticscholar +1 more source
Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification
ACM Multimedia, 2021Occluded person re-identification (ReID) aims to match person images with occlusion. It is fundamentally challenging because of the serious occlusion which aggravates the misalignment problem between images. At the cost of incorporating a pose estimator,
Kecheng Zheng +5 more
semanticscholar +1 more source
IEEE Transactions on Information Forensics and Security, 2021
Domain invariance and discrimination of learned features as two crucial factors affect the performance of unsupervised domain adaptation (UDA) person re-identification (Re-ID).
Huafeng Li +4 more
semanticscholar +1 more source
Domain invariance and discrimination of learned features as two crucial factors affect the performance of unsupervised domain adaptation (UDA) person re-identification (Re-ID).
Huafeng Li +4 more
semanticscholar +1 more source
Context-Aware Feature Learning for Noise Robust Person Search
IEEE transactions on circuits and systems for video technology (Print), 2022Person search aims to localize and identify specific pedestrians from numerous surveillance scene images. In this work, we focus on the noise in person search. We categorize the noise into scene-inherent noise and human-introduced noise.
Cairong Zhao +6 more
semanticscholar +1 more source
Improved Instance Discrimination and Feature Compactness for End-to-End Person Search
IEEE transactions on circuits and systems for video technology (Print), 2022Person search aims to locate and retrieve specific pedestrians in scene images, including two subtasks, pedestrian detection and person re-identification. Recently, triplet loss has been widely used in person re-identification, which effectively improves
Shaowei Hou +5 more
semanticscholar +1 more source
3D Person Re-Identification Based on Global Semantic Guidance and Local Feature Aggregation
IEEE transactions on circuits and systems for video technology (Print)Person re-identification (Re-ID) has played an extremely crucial role in ensuring social safety and has attracted considerable research attention. 3D shape information is an important clue to understand the posture and shape of pedestrians. However, most
Changshuo Wang +4 more
semanticscholar +1 more source