5 papers · 1 filter
Structure From Tracking: Distilling Structure-Preserving Motion for Video Generation
Yang Fei, George Stoica, Jingyuan Liu +4
Reality is a dance between rigid constraints and deformable structures. For video models, that means generating motion that preserves fidelity as well as structure. Despite progres…
Group Orthogonal Low-Rank Adaptation for RGB-T Tracking
Zekai Shao, Yufan Hu, Jingyuan Liu +2
Parameter-efficient fine-tuning has emerged as a promising paradigm in RGB-T tracking, enabling downstream task adaptation by freezing pretrained parameters and fine-tuning only a…
EdgeAttNet: Towards Barb-Aware Filament Segmentation
Victor Solomon, Piet Martens, Jingyu Liu +1
Accurate segmentation of solar filaments in H-alpha observations is critical for determining filament chirality, a key factor in the behavior of Coronal Mass Ejections (CMEs). Howe…
LUIVITON: Learned Universal Interoperable VIrtual Try-ON
Cong Cao, Xianhang Cheng, Jingyuan Liu +5
To enable large-scale reuse of real-world 3D assets, where garments and characters rarely share skeletons, templates, or dense correspondences, we present a fully automated virtual…
Dynamic and Compressive Adaptation of Transformers From Images to Videos
Guozhen Zhang, Jingyu Liu, Shengming Cao +4
Recently, the remarkable success of pre-trained Vision Transformers (ViTs) from image-text matching has sparked an interest in image-to-video adaptation. However, most current appr…