4 papers
An Efficient Adaptive Compression Method for Human Perception and Machine Vision Tasks
Lei Liu, Zhenghao Chen, Zhihao Hu +1
While most existing neural image compression (NIC) and neural video compression (NVC) methodologies have achieved remarkable success, their optimization is primarily focused on hum…
Group-aware Parameter-efficient Updating for Content-Adaptive Neural Video Compression
Zhenghao Chen, Luping Zhou, Zhihao Hu +1
Content-adaptive compression is crucial for enhancing the adaptability of the pre-trained neural codec for various contents. Although these methods have been very practical in neur…
Unsupervised Part Discovery via Dual Representation Alignment
Jiahao Xia, Wenjian Huang, Min Xu +4
Object parts serve as crucial intermediate representations in various downstream tasks, but part-level representation learning still has not received as much attention as other vis…
PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis
Zicheng Wang, Zhenghao Chen, Yiming Wu +3
Point cloud analysis has seen substantial advancements due to deep learning, although previous Transformer-based methods excel at modeling long-range dependencies on this task, the…