A neural network performs simultaneous static-moving segmentation and ego-motion estimation directly from raw radar point clouds using MLPs and RNNs.
A density-based algorithm for discovering clusters in large spatial databases with noise,
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
ArmSSL is a black-box verifiable and adversarially robust watermarking framework for SSL pre-trained encoders using paired discrepancy enlargement, latent entanglement, distribution alignment, and reference-guided tuning.
SPL unifies unsupervised and sparsely-supervised 3D object detection via semantic pseudo-labeling that produces bounding boxes and point labels, followed by memory-based prototype learning that mines features from both labeled and unlabeled data.
ESPADA uses semantic segmentation from VLMs and LLMs plus DTW to downsample non-critical segments in demonstrations, delivering about 2x faster robot execution in behavior cloning while maintaining task success rates.
A spatiotemporal graph is built from raw events; its Laplacian eigenvectors, computed via a reordered matrix using an event-density prior, are used to filter noise events.
A POI-zone and Pareto-calibrated framework infers trip purposes from GPS data and cuts distributional JSD from survey benchmarks by 23-48% on 81 million Los Angeles staypoints.
Event-based perception combined with progressive low-to-high speed training improves robotic table tennis return accuracy by 35.8% using the same number of training episodes.
citing papers explorer
-
Redefining Radar Segmentation: Simultaneous Static-Moving Segmentation and Ego-Motion Estimation using Radar Point Clouds
A neural network performs simultaneous static-moving segmentation and ego-motion estimation directly from raw radar point clouds using MLPs and RNNs.
-
ArmSSL: Adversarial Robust Black-Box Watermarking for Self-Supervised Learning Pre-trained Encoders
ArmSSL is a black-box verifiable and adversarially robust watermarking framework for SSL pre-trained encoders using paired discrepancy enlargement, latent entanglement, distribution alignment, and reference-guided tuning.
-
Unified Unsupervised and Sparsely-Supervised 3D Object Detection by Semantic Pseudo-Labeling and Prototype Learning
SPL unifies unsupervised and sparsely-supervised 3D object detection via semantic pseudo-labeling that produces bounding boxes and point labels, followed by memory-based prototype learning that mines features from both labeled and unlabeled data.
-
ESPADA: Execution Speedup via Semantics Aware Demonstration Data Downsampling for Imitation Learning
ESPADA uses semantic segmentation from VLMs and LLMs plus DTW to downsample non-critical segments in demonstrations, delivering about 2x faster robot execution in behavior cloning while maintaining task success rates.
-
Denoising for Neuromorphic Cameras Based on Graph Spectral Features
A spatiotemporal graph is built from raw events; its Laplacian eigenvectors, computed via a reordered matrix using an event-density prior, are used to filter noise events.
-
Uncertainty-Aware Trip Purpose Inference from GPS Trajectories via POI Semantic Zones and Pareto Calibration
A POI-zone and Pareto-calibrated framework infers trip purposes from GPS data and cuts distributional JSD from survey benchmarks by 23-48% on 81 million Los Angeles staypoints.
-
Biologically Inspired Event-Based Perception and Sample-Efficient Learning for High-Speed Table Tennis Robots
Event-based perception combined with progressive low-to-high speed training improves robotic table tennis return accuracy by 35.8% using the same number of training episodes.