Occlusion-aware detection and re-id calibrated network for multi-object tracking
Multi-Object Tracking (MOT) is a crucial computer vision task that aims to predict the
bounding boxes and identities of objects simultaneously. While state-of-the-art methods …
bounding boxes and identities of objects simultaneously. While state-of-the-art methods …
Semantic-constraint matching transformer for weakly supervised object localization
Weakly supervised object localization (WSOL) strives to learn to localize objects with only
image-level supervision. Due to the local receptive fields generated by convolution …
image-level supervision. Due to the local receptive fields generated by convolution …
Dual-Augmented Transformer Network for Weakly Supervised Semantic Segmentation
J Deng, Z Li - arxiv preprint arxiv:2310.00307, 2023 - arxiv.org
Weakly supervised semantic segmentation (WSSS), a fundamental computer vision task,
which aims to segment out the object within only class-level labels. The traditional methods …
which aims to segment out the object within only class-level labels. The traditional methods …
COMNet: Co-Occurrent Matching for Weakly Supervised Semantic Segmentation
Y Su, J Deng, Z Li - arxiv preprint arxiv:2309.16959, 2023 - arxiv.org
Image-level weakly supervised semantic segmentation is a challenging task that has been
deeply studied in recent years. Most of the common solutions exploit class activation map …
deeply studied in recent years. Most of the common solutions exploit class activation map …