Promotion: Prototypes as motion learners
In this work we introduce ProMotion a unified prototypical transformer-based framework
engineered to model fundamental motion tasks. ProMotion offers a range of compelling …
engineered to model fundamental motion tasks. ProMotion offers a range of compelling …
Temporally consistent referring video object segmentation with hybrid memory
Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining
consistent object segmentation due to temporal context variability and the presence of other …
consistent object segmentation due to temporal context variability and the presence of other …
Learning Motion-guided Multi-scale Memory Features for Video Shadow Detection
Natural images often contain multiple shadow regions, and existing video shadow detection
methods tend to fail in fully identifying all shadow regions, since they mainly learned …
methods tend to fail in fully identifying all shadow regions, since they mainly learned …
Deep spectral improvement for unsupervised image instance segmentation
Recently, there has been growing interest in deep spectral methods for image localization
and segmentation, influenced by traditional spectral segmentation approaches. These …
and segmentation, influenced by traditional spectral segmentation approaches. These …
Structural Transformer with Region Strip Attention for video object segmentation
Memory-based methods in semi-supervised video object segmentation (VOS) achieve
competitive performance by performing feature similarity between the current frame and …
competitive performance by performing feature similarity between the current frame and …
M2fNet: Multi-Modal Forest Monitoring Network on Large-Scale Virtual Dataset
Forest monitoring and education are key to forest protection, education and management,
which is an effective way to measure the progress of a country's forest and climate …
which is an effective way to measure the progress of a country's forest and climate …
Physically-guided open vocabulary segmentation with weighted patched alignment loss
Open vocabulary segmentation is a challenging task that aims to segment out the thousands
of unseen categories. Directly applying CLIP to open-vocabulary semantic segmentation is …
of unseen categories. Directly applying CLIP to open-vocabulary semantic segmentation is …
LiDAR-Forest Dataset: LiDAR Point Cloud Simulation Dataset for Forestry Application
The popularity of LiDAR devices and sensor technology has gradually empowered users
from autonomous driving to forest monitoring, and research on 3D LiDAR has made …
from autonomous driving to forest monitoring, and research on 3D LiDAR has made …
Enhance audio-visual segmentation with hierarchical encoder and audio guidance
C Guo, H Huang, Y Zhou - Neurocomputing, 2024 - Elsevier
As one of the pivotal technologies leading towards embodied intelligence, audio-visual
segmentation is geared towards achieving precise segmentation of sounding objects …
segmentation is geared towards achieving precise segmentation of sounding objects …
Towards Temporally Consistent Referring Video Object Segmentation
Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining
consistent object segmentation due to temporal context variability and the presence of other …
consistent object segmentation due to temporal context variability and the presence of other …