Bridging feature complementarity gap between encoder and decoder for salient object detection
Deep convolutional neural networks have pushed the resulting performances of salient
object detection to the new state-of-the-art. However, most of the existing methods mainly …
object detection to the new state-of-the-art. However, most of the existing methods mainly …
Co-saliency detection with two-stage co-attention mining and individual calibration
Learning-based methods have become popular in co-salient object detection (CoSOD).
However, existing methods suffer from two challenging issues, including mining the inter …
However, existing methods suffer from two challenging issues, including mining the inter …
Boosting feature-aware network for salient object detection
Deep convolutional neural networks have demonstrated competitive performance in salient
object detection. To capture more precise saliency maps, recent approaches mainly …
object detection. To capture more precise saliency maps, recent approaches mainly …
A unified multiple inducible co-attentions and edge guidance network for co-saliency detection
The learning-based methods have improved the performances of co-salient object detection
(CoSOD). Mining the intra-image saliency individuals and exploring the inter-image co …
(CoSOD). Mining the intra-image saliency individuals and exploring the inter-image co …
Feature recalibration network for salient object detection
Learning-based models have demonstrated the superiority of extracting and aggregating
saliency features. However, we observe that most off-the-shelf methods mainly focus on the …
saliency features. However, we observe that most off-the-shelf methods mainly focus on the …
A Unified Video Semantics Extraction and Noise Object Suppression Network for Video Saliency Detection
Video salient object detection (VSOD) aims to segment the most attractive objects from a
video sequence. Exploring video semantics and suppressing noise objects are two …
video sequence. Exploring video semantics and suppressing noise objects are two …