From the 2 of 39 papers with an AI index.
61 citations
- Shenzhen Technology UniversityCN6 papers
- Sun Yat-sen UniversityCN5 papers
- University of Hong KongHK4 papers
- University Town of ShenzhenCN4 papers
- Chinese University of Hong KongHK3 papers
- Xiamen UniversityCN3 papers
- Anhui UniversityCN2 papers
- City University of Hong KongHK2 papers
- Henan Normal UniversityCN2 papers
- Nanjing University of Science and TechnologyCN2 papers
- National University of Defense TechnologyCN2 papers
- South China University of TechnologyCN2 papers
6 papers · 1 filter
Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations
Ruoxi Guo, Huaijin Pi, Zehong Shen +8
Text-driven human motion synthesis has showcased its potential for revolutionizing motion design in the movie and game industry. Existing methods often rely on 3D motion capture da…
A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction
Meng'en Qin, Yu Song, Quanling Zhao +3
Learning multi-scale representations is the common strategy to tackle object scale variation in dense prediction tasks. Although existing feature pyramid networks have greatly adva…
Unleashing the Potential of All Test Samples: Mean-Shift Guided Test-Time Adaptation
Jizhou Han, Chenhao Ding, SongLin Dong +3
Visual-language models (VLMs) like CLIP exhibit strong generalization but struggle with distribution shifts at test time. Existing training-free test-time adaptation (TTA) methods…
SpikeSMOKE: Spiking Neural Networks for Monocular 3D Object Detection with Cross-Scale Gated Coding
Xuemei Chen, Huamin Wang, Jing Peng +4
With the wide application of 3D object detection in some fields such as autonomous driving, its energy consumption is constantly increasing, making the research on low-power consum…
Learn by Reasoning: Analogical Weight Generation for Few-Shot Class-Incremental Learning
Jizhou Han, Chenhao Ding, Yuhang He +4
Few-shot class-incremental Learning (FSCIL) enables models to learn new classes from limited data while retaining performance on previously learned classes. Traditional FSCIL metho…
Symmetrization Weighted Binary Cross-Entropy: Modeling Perceptual Asymmetry for Human-Consistent Neural Edge Detection
Hao Shu
Edge detection (ED) is a fundamental perceptual process in computer vision, forming the structural basis for high-level reasoning tasks such as segmentation, recognition, and scene…