LangTail uses entity-level semantic priors from language models aligned via contrastive learning in a hierarchical clustering setup to resolve long-tail ambiguity, yielding +13.5, +12.9, and +8.9 mIoU gains on ScanNet-v2, S3DIS, and nuScenes.
hub
Pointnet++: Deep hierarchical feature learning on point sets in a metric space
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
VoxAfford fuses multi-scale voxel features into MLLM output tokens using cross-attention with a learned compatibility gate to achieve SOTA open-vocabulary 3D affordance detection with ~8% mIoU gain and zero-shot robot transfer.
This is the first comprehensive survey of LiDAR in rehabilitation, summarizing applications, AI techniques, trends, gaps, and future directions across studies from 2019-2025.
HealthPoint represents clinical events as points in a 4D space (content, time, modality, case) and applies low-rank relational attention to achieve state-of-the-art mortality prediction from multi-level incomplete multimodal EHRs.
Proposes the first light field-LiDAR semantic segmentation dataset and the Mlpfseg network, which improves mIoU by 1.71 over image-only and 2.38 over point-cloud-only baselines via feature completion and depth perception modules.
An end-to-end spiking encoder-decoder network achieves 92.05/87.04/86.51 AP on KITTI BEV detection with a claimed 3.33x synaptic energy reduction versus an equivalent CNN.
PoHAR enables distributed air quality sensor networks to collaboratively detect hyperlocal indoor activities with 97.41% accuracy using conflict-free data replication, hierarchical clustering, and off-the-shelf ML classifiers on resource-constrained devices.
Fed3D is a federated 3D object detection system using local-global class-aware loss for heterogeneity and prompt modules for low-bandwidth communication, claiming better performance than prior methods on limited local data.
TAX-DPD combines a feed-forward dense GMM for global placement priors with disentangled point cloud diffusion for local geometry and pose to achieve precise robotic object placement.
Octree-based islandization plus hub scheduling cuts redundant feature fetch/compute in point-cloud networks, yielding 1.2×–3.2× extra FPGA speedup as a plug-in.
ELMP performs data-efficient self-supervised adaptation of neural motion planners via analytical policy gradients and point-cloud tool encoding, raising success from 57.3% zero-shot to 89.8% in unseen environments.
An RL data generation pipeline with generalizable rewards and language annotations produces diverse synthetic datasets that improve multi-task policy generalization on three bimanual manipulation tasks.
TSNN matches time series entries to a training-derived memory bank to forecast traffic without any trainable parameters and achieves competitive accuracy on four real-world datasets.
PointCRA reduces information loss in deep point cloud networks by treating temporal trend variation as an extra evaluation dimension alongside spatial and channel attention, guided by a neighborhood homogeneity constraint.
A 360 RGB video pipeline using SfM, Grounded SAM, and RANSAC achieves 5-9% median relative DBH error, only 2-4% above LiDAR, on 61 acquisitions of 43 trees.
citing papers explorer
-
Resolving Long-Tail Ambiguity in Unsupervised 3D Point Cloud Segmentation with Language Priors
LangTail uses entity-level semantic priors from language models aligned via contrastive learning in a hierarchical clustering setup to resolve long-tail ambiguity, yielding +13.5, +12.9, and +8.9 mIoU gains on ScanNet-v2, S3DIS, and nuScenes.
-
VoxAfford: Multi-Scale Voxel-Token Fusion for Open-Vocabulary 3D Affordance Detection
VoxAfford fuses multi-scale voxel features into MLLM output tokens using cross-attention with a learned compatibility gate to achieve SOTA open-vocabulary 3D affordance detection with ~8% mIoU gain and zero-shot robot transfer.
-
LiDAR for Rehabilitation: A Comprehensive Survey of Applications, AI Techniques, and Future Directions
This is the first comprehensive survey of LiDAR in rehabilitation, summarizing applications, AI techniques, trends, gaps, and future directions across studies from 2019-2025.
-
A Clinical Point Cloud Paradigm for In-Hospital Mortality Prediction from Multi-Level Incomplete Multimodal EHRs
HealthPoint represents clinical events as points in a 4D space (content, time, modality, case) and applies low-rank relational attention to achieve state-of-the-art mortality prediction from multi-level incomplete multimodal EHRs.
-
Geometry-Aware Cross Modal Alignment for Light Field-LiDAR Semantic Segmentation
Proposes the first light field-LiDAR semantic segmentation dataset and the Mlpfseg network, which improves mIoU by 1.71 over image-only and 2.38 over point-cloud-only baselines via feature completion and depth perception modules.
-
Neuromorphic LiDAR-based Bird's Eye View Object Detection using Energy-efficient Spiking Neural Networks
An end-to-end spiking encoder-decoder network achieves 92.05/87.04/86.51 AP on KITTI BEV detection with a claimed 3.33x synaptic energy reduction versus an equivalent CNN.
-
PoHAR: Understanding Hyperlocal Human Activities with Pollution Sensor Networks
PoHAR enables distributed air quality sensor networks to collaboratively detect hyperlocal indoor activities with 97.41% accuracy using conflict-free data replication, hierarchical clustering, and off-the-shelf ML classifiers on resource-constrained devices.
-
Fed3D: Federated 3D Object Detection
Fed3D is a federated 3D object detection system using local-global class-aware loss for heterogeneity and prompt modules for low-bandwidth communication, claiming better performance than prior methods on limited local data.
-
Disentangled Point Diffusion for Precise Object Placement
TAX-DPD combines a feed-forward dense GMM for global placement priors with disentangled point cloud diffusion for local geometry and pose to achieve precise robotic object placement.
-
L-PCN: A Point Cloud Accelerator Exploiting Spatial Locality through Octree-based Islandization
Octree-based islandization plus hub scheduling cuts redundant feature fetch/compute in point-cloud networks, yielding 1.2×–3.2× extra FPGA speedup as a plug-in.
-
ELMP: Efficient Learning for Motion Planning via Analytical Policy Gradients
ELMP performs data-efficient self-supervised adaptation of neural motion planners via analytical policy gradients and point-cloud tool encoding, raising success from 57.3% zero-shot to 89.8% in unseen environments.
-
Scalable Multi-Task Data Generation via Reinforcement Learning for Language-Conditioned Bimanual Dexterous Manipulation
An RL data generation pipeline with generalizable rewards and language annotations produces diverse synthetic datasets that improve multi-task policy generalization on three bimanual manipulation tasks.
-
TSNN: A Non-parametric and Interpretable Framework for Traffic Time Series Forecasting
TSNN matches time series entries to a training-derived memory bank to forecast traffic without any trainable parameters and achieves competitive accuracy on four real-world datasets.
-
Channel-Level Relation to Attentive Aggregation with Neighborhood-Homogeneity Constraint for Point Cloud Analysis
PointCRA reduces information loss in deep point cloud networks by treating temporal trend variation as an extra evaluation dimension alongside spatial and channel attention, guided by a neighborhood homogeneity constraint.
-
Estimating the Diameter at Breast Height of Trees in a Forest from RGB
A 360 RGB video pipeline using SfM, Grounded SAM, and RANSAC achieves 5-9% median relative DBH error, only 2-4% above LiDAR, on 61 acquisitions of 43 trees.
- Flow Motion Policy: Manipulator Motion Planning with Flow Matching Models