6 papers · 2 filters
TalkVerse: Democratizing Minute-Long Audio-Driven Video Generation
Zhenzhi Wang, Jian Wang, Ke Ma +2
We introduce TalkVerse, a large-scale, open corpus for single-person, audio-driven talking video generation designed to enable fair, reproducible comparison across methods. While c…
PAVE: An End-to-End Dataset for Production Autonomous Vehicle Evaluation
Xiangyu Li, Chen Wang, Yumao Liu +3
Most existing autonomous-driving datasets (e.g., KITTI, nuScenes, and the Waymo Perception Dataset), collected by human-driving mode or unidentified driving mode, can only serve as…
DoGCLR: Dominance-Game Contrastive Learning Network for Skeleton-Based Action Recognition
Yanshan Li, Ke Ma, Miaomiao Wei +1
Existing self-supervised contrastive learning methods for skeleton-based action recognition often process all skeleton regions uniformly, and adopt a first-in-first-out (FIFO) queu…
ACD-CLIP: Decoupling Representation and Dynamic Fusion for Zero-Shot Anomaly Detection
Ke Ma, Jun Long, Hongxiao Fei +3
Pre-trained Vision-Language Models (VLMs) struggle with Zero-Shot Anomaly Detection (ZSAD) due to a critical adaptation gap: they lack the local inductive biases required for dense…
Taming Diffusion Transformer for Efficient Mobile Video Generation in Seconds
Yushu Wu, Yanyu Li, Anil Kag +9
Diffusion Transformers (DiT) have shown strong performance in video generation tasks, but their high computational cost makes them impractical for resource-constrained devices like…
LidarPainter: One-Step Away From Any Lidar View To Novel Guidance
Yuzhou Ji, Ke Ma, Hong Cai +3
Dynamic driving scene reconstruction is of great importance in fields like digital twin system and autonomous driving simulation. However, unacceptable degradation occurs when the…