580 citations
- University of Science and Technology of ChinaCN53 papers
- Chinese Academy of SciencesCN51 papers
- Hefei Institutes of Physical ScienceCN23 papers
- High Magnetic Field LaboratoryCN21 papers
- University of Chinese Academy of SciencesCN19 papers
- National Astronomical ObservatoriesCN16 papers
- Nanjing UniversityCN15 papers
- Collaborative Innovation Center of Advanced MicrostructuresCN9 papers
- Hefei National Center for Physical Sciences at NanoscaleCN9 papers
- University of Tennessee at KnoxvilleUS8 papers
- The University of TokyoJP7 papers
- Beihang UniversityCN6 papers
18 papers · 1 filter
Text-Region Matching for Multi-Label Image Recognition with Missing Labels
Leilei Ma, Hongxing Xie, Lei Wang +3
Recently, large-scale visual language pre-trained (VLP) models have demonstrated impressive performance across various downstream tasks. Motivated by these advancements, pioneering…
HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection
Bin Tang, Zhengyi Liu, Yacheng Tan +1
The High-Resolution Transformer (HRFormer) can maintain high-resolution representation and share global receptive fields. It is friendly towards salient object detection (SOD) in w…
SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection
Zhengyi Liu, Yacheng Tan, Qian He +1
Convolutional neural networks (CNNs) are good at extracting contexture features within certain receptive fields, while transformers can model the global long-range dependency featu…
Tracking by Joint Local and Global Search: A Target-aware Attention based Approach
Xiao Wang, Jin Tang, Bin Luo +3
Tracking-by-detection is a very popular framework for single object tracking which attempts to search the target object within a local search window for each frame. Although such l…
Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting
Lingbo Liu, Jiaqi Chen, Hefeng Wu +3
Crowd counting is a fundamental yet challenging task, which desires rich information to generate pixel-wise crowd density maps. However, most previous methods only used the limited…
Viewpoint-aware Progressive Clustering for Unsupervised Vehicle Re-identification
Aihua Zheng, Xia Sun, Chenglong Li +1
Vehicle re-identification (Re-ID) is an active task due to its importance in large-scale intelligent monitoring in smart cities. Despite the rapid progress in recent years, most ex…