Global attention-assisted representation learning for vehicle re-identification
Sign Up to like & getrecommendations! Published in 2022 at "Signal, Image and Video Processing"
DOI: 10.1007/s11760-021-02021-1
Abstract: Like pedestrian re-identification, vehicle re-identification (re-id) is an important part of building smart cities, and its purpose is to identify the same vehicle in vehicle images captured by multiple cameras. Vehicle re-id is more challenging… read more here.
Keywords: attention assisted; vehicle; global attention; vehicle identification ... See more keywords
An Abnormal Traffic Detection Model Combined BiIndRNN With Global Attention
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Access"
DOI: 10.1109/access.2022.3159550
Abstract: As time series data with internal correlation, networks traffic data can be used for abnormal detection using Recurrent Neural Network (RNN) and its variants, but existing models are difficult to calculate in parallel, and gradient… read more here.
Keywords: global attention; traffic; detection; model ... See more keywords
Global-Attention-Based Neural Networks for Vision Language Intelligence
Sign Up to like & getrecommendations! Published in 2021 at "IEEE/CAA Journal of Automatica Sinica"
DOI: 10.1109/jas.2020.1003402
Abstract: In this paper, we develop a novel global-attention-based neural network (GANN) for vision language intelligence, specifically, image captioning (language description of a given image). As many previous works, the encoder-decoder framework is adopted in our… read more here.
Keywords: global attention; attention; feature; caption ... See more keywords
Ship Segmentation via Encoder-Decoder Network With Global Attention in High-Resolution SAR Images
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Geoscience and Remote Sensing Letters"
DOI: 10.1109/lgrs.2021.3100572
Abstract: Ship detection in the synthetic aperture radar (SAR) image is of great significance in the fields of military and coastal defense. Most ship detection methods are designed based on the object detection framework, which can… read more here.
Keywords: encoder decoder; segmentation; ship segmentation; global attention ... See more keywords