29 citations · 92 across the 24 of their papers we have counts for
5 papers · 2 filters
MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer
Minghao Zhu, Zhengpu Wang, Mengxian Hu +5
Transferring visual-language knowledge from large-scale foundation models for video recognition has proved to be effective. To bridge the domain gap, additional parametric modules…
SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detection
Yun Peng, Xiao Lin, Nachuan Ma +4
Visual anomaly detection is vital in real-world applications, such as industrial defect detection and medical diagnosis. However, most existing methods focus on local structural an…
Efficient Text-driven Motion Generation via Latent Consistency Training
Mengxian Hu, Minghao Zhu, Xun Zhou +4
Text-driven human motion generation based on diffusion strategies establishes a reliable foundation for multimodal applications in human-computer interactions. However, existing ad…
Causality-based Cross-Modal Representation Learning for Vision-and-Language Navigation
Liuyi Wang, Zongtao He, Ronghao Dang +3
Vision-and-Language Navigation (VLN) has gained significant research interest in recent years due to its potential applications in real-world scenarios. However, existing VLN metho…
CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge
Xiao Lin, Minghao Zhu, Ronghao Dang +5
Most of existing category-level object pose estimation methods devote to learning the object category information from point cloud modality. However, the scale of 3D datasets is li…