Mark Ding

SAM2Long. [ICCV 2025] SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree

Dispider. [CVPR 2025]Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction

FAME. [CVPR 2022] Code for Motion-aware Contrastive Video Representation Learning via Foreground-background Merging

GNN-Practical-Attack. Code for Towards More Practical Adversarial Attacks on Graph Neural Networks (NeurIPS 2020)

STA. [ICCV 2023] Code for Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation

Effect-of-Contrastive-Loss-on-Unsupervised-Representation-Learning. EECS 442 project

DCLR. Official code for Dual Contrastive Learning for Spatio-temporal Representation (ACM MM 2022)