Deep multi-domain prediction for 3D video coding
Three-dimensional (3D) video contains plentiful multi-domain correlations, including spatial,
temporal, and inter-view correlations. In this paper, a deep multi-domain prediction method …
temporal, and inter-view correlations. In this paper, a deep multi-domain prediction method …
Progressive co-attention network for fine-grained visual classification
T Zhang, D Chang, Z Ma, J Guo - … International Conference on …, 2021 - ieeexplore.ieee.org
Fine-grained visual classification aims to recognize images belonging to multiple sub-
categories within a same category. It is a challenging task due to the inherently subtle …
categories within a same category. It is a challenging task due to the inherently subtle …
Dilated-scale-aware category-attention convnet for multi-class object counting
Object counting aims to estimate the number of objects in images. The leading counting
approaches focus on single-category counting tasks and achieve impressive performance …
approaches focus on single-category counting tasks and achieve impressive performance …
AI based service management for 6G green communications
Green communications have always been a target for the information industry to alleviate
energy overhead and reduce fossil fuel usage. In current 5G and future 6G era, there is no …
energy overhead and reduce fossil fuel usage. In current 5G and future 6G era, there is no …
Learning sequentially diversified representations for fine-grained categorization
Learning representation carrying rich local information is essential for recognizing fine-
grained objects. Existing methods to this task resort to multi-stage frameworks to capture fine …
grained objects. Existing methods to this task resort to multi-stage frameworks to capture fine …
Decoupled self-supervised label augmentation for fully-supervised image classification
Self-supervised label augmentation has emerged as an effective means to overcome the
data scarcity problem for supervised vision tasks. Existing rotation-based self-supervised …
data scarcity problem for supervised vision tasks. Existing rotation-based self-supervised …
Adaptive Multi-Proxy for Remote Sensing Image Retrieval
X Li, S Wei, J Wang, Y Du, M Ge - Remote Sensing, 2022 - mdpi.com
With the development of remote sensing technology, content-based remote sensing image
retrieval has become a research hotspot. Remote sensing image datasets not only contain …
retrieval has become a research hotspot. Remote sensing image datasets not only contain …
Cross-scenario device-free activity recognition based on deep adversarial networks
Device-free activity recognition (DFAR) is an emerging technique which could infer human
activities by analyzing his/her influence on surrounding wireless signals. It may empower …
activities by analyzing his/her influence on surrounding wireless signals. It may empower …
RGB-D salient object detection via cross-modal joint feature extraction and low-bound fusion loss
RGB-D salient object detection aims at identifying attractive objects in a scene by combining
the color image and depth map. However, due to the differences between RGB-D image …
the color image and depth map. However, due to the differences between RGB-D image …
Convolutional Fine-Grained Classification With Self-Supervised Target Relation Regularization
Fine-grained visual classification can be addressed by deep representation learning under
supervision of manually pre-defined targets (eg, one-hot or the Hadamard codes). Such …
supervision of manually pre-defined targets (eg, one-hot or the Hadamard codes). Such …