🏢 Tianjin University

VPNet, a novel semantic scene completion network, uses multi-frame knowledge distillation and confident voxel proposals to improve accuracy and handle dynamic aspects of 3D scenes from point clouds, a…

Unsupervised learning framework enables high-fidelity non-line-of-sight (NLOS) imaging from irregularly undersampled transients, surpassing state-of-the-art methods in speed and robustness.

MARS, a novel plugin framework, unlocks model-free RL’s intermittent control ability by encoding action sequences into a compact latent space, improving learning efficiency and real-world robotic task…

Test-Time Dynamic Image Fusion (TTD) paradigm provably improves image fusion by dynamically weighting source data based on their relative dominance, reducing generalization error without extra trainin…

Synergistic Dual Spatial-aware Generation boosts image-to-text and text-to-image accuracy using a novel 3D scene graph and dual learning framework.

Persistence Homology Distillation (PsHD) leverages topological data analysis to robustly preserve structural information in semi-supervised continual learning, significantly outperforming existing met…

FUG: A new graph contrastive pre-training strategy solves GNN transferability issues across datasets with diverse node features, achieving comparable performance to retraining while significantly impr…

SGRL, a novel graph contrastive learning framework, significantly boosts performance by leveraging the inherent ‘representation scattering’ mechanism and integrating graph topology, outperforming exis…