4 papers
Video Codec-Guided Training-Free Token Compression for Video Large Language Models
Xihua Sheng, Ruijie Liu, Chang Wen Chen
Video large language models (VLLMs) rely on long visual token sequences to understand complex temporal content, which makes visual token compression important for efficient inferen…
Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark
Muyao Niu, Mingze Ma, Yifan Zhan +5
Robust low-light imaging remains challenging for the community. Recent studies have explored fusing Near-Infrared (NIR) with noisy RGB to achieve improved enhancement, yet most met…
URVC: A Unified Real-Time Neural Video Coding Model with Temporal, Spatial, and Perceptual Adaptivity
Xihua Sheng, Chang Wen Chen
Neural video coding has advanced rapidly, achieving competitive compression performance while also enabling real-time coding speed. Yet, existing codecs exhibit severe rigidity whe…
CoMA: Complementary Masking and Hierarchical Dynamic Multi-Window Self-Attention in a Unified Pre-training Framework
Jiaxuan Li, Qing Xu, Xiangjian He +6
Masked Autoencoders (MAE) achieve self-supervised learning of image representations by randomly removing a portion of visual tokens and reconstructing the original image as a prete…