4 papers
LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantization
Jie Li, Kwan-Yee K. Wong, Kai Han
Vector quantization (VQ) is a prevalent and fundamental technique that discretizes continuous feature vectors by approximating them using a codebook. As the diversity and complexit…
CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-World
Yating Yu, Congqi Cao, Zhaoying Wang +6
How far are deep models from real-world video anomaly understanding (VAU)? Current works typically emphasize on detecting unexpected occurrences deviated from normal patterns or co…
Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation
Qirui Li, Guangcong Zheng, Qi Zhao +4
The computational demands of self-attention mechanisms pose a critical challenge for transformer-based video generation, particularly in synthesizing ultra-long sequences. Current…
AgileIR: Memory-Efficient Group Shifted Windows Attention for Agile Image Restoration
Hongyi Cai, Mohammad Mahdinur Rahman, Mohammad Shahid Akhtar +3
Image Transformers show a magnificent success in Image Restoration tasks. Nevertheless, most of transformer-based models are strictly bounded by exorbitant memory occupancy. Our go…