Overtourism and sustainability: A bibliometric study (2018–2021)
The term “overtourism” refers to the negative impact of tourism on the quality of life of citizens
and visitor experiences in a destination. It is a relatively new concept in scientific research …
and visitor experiences in a destination. It is a relatively new concept in scientific research …
What's next in talent management?
E Pagan-Castaño, JC Ballester-Miquel… - Journal of Business …, 2022 - Elsevier
This article presents a literature review of the academic research on talent management
(TM). This research topic is contemporary and highly relevant, given its links with human …
(TM). This research topic is contemporary and highly relevant, given its links with human …
Wine prices in economics: A bibliometric analysis
This article presents a literature review and a bibliometric analysis of academic research on
wine prices in economics. The study comprises a review of 180 articles published in journals …
wine prices in economics. The study comprises a review of 180 articles published in journals …
Semantically meaningful class prototype learning for one-shot image segmentation
One-shot semantic image segmentation aims to segment the object regions for the novel
class with only one annotated image. Recent works adopt the episodic training strategy to …
class with only one annotated image. Recent works adopt the episodic training strategy to …
Co-ldl: A co-training-based label distribution learning method for tackling label noise
Performances of deep neural networks are prone to be degraded by label noise due to their
powerful capability in fitting training data. Deeming low-loss instances as clean data is one …
powerful capability in fitting training data. Deeming low-loss instances as clean data is one …
Exploiting web images for fine-grained visual recognition by eliminating open-set noise and utilizing hard examples
Labeling objects at a subordinate level typically requires expert knowledge, which is not
always available when using random annotators. As such, learning directly from web …
always available when using random annotators. As such, learning directly from web …
Robust learning from noisy web data for fine-grained recognition
Due to DNNs' memorization effect, label noise lessens the performance of the web-
supervised fine-grained visual categorization task. Previous literature primarily relies on …
supervised fine-grained visual categorization task. Previous literature primarily relies on …
Self-attention based fine-grained cross-media hybrid network
W Shan, D Huang, J Wang, F Zou, S Li - Pattern Recognition, 2022 - Elsevier
Due to the heterogeneity gap, the data representations of different types of media are
inconsistent. It is challenging to measure the fine-grained gap between different media. To …
inconsistent. It is challenging to measure the fine-grained gap between different media. To …
Unsupervised pre-training for 3D object detection with transformer
Transformer improve the performance of 3D object detection with few hyperparameters.
Inspired by the recent success of the pre-training Transformer in 2D object detection and …
Inspired by the recent success of the pre-training Transformer in 2D object detection and …
Few-shot object detection via understanding convolution and attention
Abstract Few-Shot Object Detection (FSOD) aims to make the detector adapt to unseen
classes with only a few training samples. Typical FSOD methods use Faster R-CNN as the …
classes with only a few training samples. Typical FSOD methods use Faster R-CNN as the …