9 papers
CoDance: An Unbind-Rebind Paradigm for Robust Multi-Subject Animation
Shuai Tan, Biao Gong, Ke Ma +5
Character image animation is gaining significant importance across various domains, driven by the demand for robust and flexible multi-subject rendering. While existing methods exc…
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…
Slicing Vision Transformer for Flexible Inference
Yitian Zhang, Huseyin Coskun, Xu Ma +6
Vision Transformers (ViT) is known for its scalability. In this work, we target to scale down a ViT to fit in an environment with dynamic-changing resource constraints. We observe…
SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device
Yushu Wu, Zhixing Zhang, Yanyu Li +11
We have witnessed the unprecedented success of diffusion-based video generation over the past year. Recently proposed models from the community have wielded the power to generate c…