MLVC achieves cross-platform robustness for neural video coding by sending scale parameters in the hyperprior, paired with gated memory, ReGLU activations, and perceptual training to reach over 70% BD-rate gains versus hardware HEVC while running at 100 FPS on Apple, Intel, and Qualcomm NPUs.
arXiv preprint arXiv:2401.08154 (2024)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
MMSD and SAMR achieve 99 percent and 99.1 percent average data reduction for traffic images by transmitting segmentation maps, edges, text or semantically masked JPEGs and reconstructing via diffusion or inpainting models.
citing papers explorer
-
MLVC: Multi-platform Learned Video Codec for Real-World Deployment
MLVC achieves cross-platform robustness for neural video coding by sending scale parameters in the hyperprior, paired with gated memory, ReGLU activations, and perceptual training to reach over 70% BD-rate gains versus hardware HEVC while running at 100 FPS on Apple, Intel, and Qualcomm NPUs.
-
Efficient Semantic Image Communication for Traffic Monitoring at the Edge
MMSD and SAMR achieve 99 percent and 99.1 percent average data reduction for traffic images by transmitting segmentation maps, edges, text or semantically masked JPEGs and reconstructing via diffusion or inpainting models.