STS-Mixer decomposes 4D point cloud videos into multi-band spectral signals via graph transforms and mixes them with spatiotemporal representations to achieve better results on 3D action recognition and 4D semantic segmentation benchmarks.
Parameter-efficient fine-tuning in spectral domain for point cloud learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
LIDARLearn is a unified PyTorch library integrating 29 supervised point cloud architectures, 7 self-supervised pre-training methods, and 5 PEFT strategies with built-in cross-validation, statistical testing, and automated reporting.
citing papers explorer
-
STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understanding
STS-Mixer decomposes 4D point cloud videos into multi-band spectral signals via graph transforms and mixes them with spatiotemporal representations to achieve better results on 3D action recognition and 4D semantic segmentation benchmarks.
-
LIDARLearn: A Unified Deep Learning Library for 3D Point Cloud Classification, Segmentation, and Self-Supervised Representation Learning
LIDARLearn is a unified PyTorch library integrating 29 supervised point cloud architectures, 7 self-supervised pre-training methods, and 5 PEFT strategies with built-in cross-validation, statistical testing, and automated reporting.