This is your work, valued

Hangzhou, China

Kephone Gaon

Expert
@Dawn-LX

Researcher at Manycore Tech Inc., Hangzhou, China.

dawn-lx.github.io/

CausalCache-VDM. Official implementation of our paper: "Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing" (ICML 2025)

83

VidSGG-BIG. Pytorch implementation of our paper Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs, which is accepted by CVPR2022

47

OpenVoc-VidVRD. Official code for the ICLR2023 paper Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection

43

VidVRD-tracklets. Video Visual Relation Detection (VidVRD) tracklets generation. also for ACM MM Visual Relation Understanding Grand Challenge

40

VidSGG-TrajDataPrepare. Code for prepare traj data for VidSGG task, like bbox detection, RoI feature extraction, and object tracking

6

VidVRD-II-backup. the original official VidVRD-II has been deleted, we provide a backup version

5

Interesting-Python-APIs. Python

4

GCN-pytorch. An implementation of GCN (Graph Convolution Network) in PyTorch

4