Copertina

DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understanding

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kreutz, Thomas, Mühlhäuser, Max, Guinea, Alejandro Sanchez
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

LiOn-XA: Unsupervised Domain Adaptation via LiDAR-Only Cross-Modal Adversarial Training
di: Kreutz, Thomas, et al.
Pubblicazione: (2024)

Whenever, Wherever: Towards Orchestrating Crowd Simulations with Spatio-Temporal Spawn Dynamics
di: Kreutz, Thomas, et al.
Pubblicazione: (2025)

SafePath: Conformal Prediction for Safe LLM-Based Autonomous Navigation
di: Doula, Achref, et al.
Pubblicazione: (2025)

Affinity Contrastive Learning for Skeleton-based Human Activity Understanding
di: Liu, Hongda, et al.
Pubblicazione: (2026)

Exploring the Capabilities of LLMs for IMU-based Fine-grained Human Activity Understanding
di: Xu, Lilin, et al.
Pubblicazione: (2025)

Hyperbolic Image-and-Pointcloud Contrastive Learning for 3D Classification
di: Hu, Naiwen, et al.
Pubblicazione: (2024)

EPContrast: Effective Point-level Contrastive Learning for Large-scale Point Cloud Understanding
di: Pan, Zhiyi, et al.
Pubblicazione: (2024)

SKI Models: Skeleton Induced Vision-Language Embeddings for Understanding Activities of Daily Living
di: Sinha, Arkaprava, et al.
Pubblicazione: (2025)

Non-stationary BERT: Exploring Augmented IMU Data For Robust Human Activity Recognition
di: Sun, Ning, et al.
Pubblicazione: (2024)

Diffusion-Based Generation and Imputation of Driving Scenarios from Limited Vehicle CAN Data
di: Ripper, Julian, et al.
Pubblicazione: (2025)

Curve Skeletonization in Continuous domain for Meshes and Point Clouds
di: Bardhan, Jai, et al.
Pubblicazione: (2026)

Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
di: Diao, Yunfeng, et al.
Pubblicazione: (2022)

Hyperbolic Contrastive Learning for Hierarchical 3D Point Cloud Embedding
di: Liu, Yingjie, et al.
Pubblicazione: (2025)

Detecting the Anomalies in LiDAR Pointcloud
di: Zhang, Chiyu, et al.
Pubblicazione: (2023)

Motion Keyframe Interpolation for Any Human Skeleton via Temporally Consistent Point Cloud Sampling and Reconstruction
di: Mo, Clinton, et al.
Pubblicazione: (2024)

VESPA: Towards un(Human)supervised Open-World Pointcloud Labeling for Autonomous Driving
di: Tempfli, Levente, et al.
Pubblicazione: (2025)

Point Cloud Understanding via Attention-Driven Contrastive Learning
di: Wang, Yi, et al.
Pubblicazione: (2024)

Advancing 3D Point Cloud Understanding through Deep Transfer Learning: A Comprehensive Survey
di: Sohail, Shahab Saquib, et al.
Pubblicazione: (2024)

Point-Supervised Skeleton-Based Human Action Segmentation
di: Wang, Hongsong, et al.
Pubblicazione: (2026)

Exploring Semantic Masked Autoencoder for Self-supervised Point Cloud Understanding
di: Zha, Yixin, et al.
Pubblicazione: (2025)

Foundation Model for Skeleton-Based Human Action Understanding
di: Wang, Hongsong, et al.
Pubblicazione: (2025)

Skeletonization Quality Evaluation: Geometric Metrics for Point Cloud Analysis in Robotics
di: Wen, Qingmeng, et al.
Pubblicazione: (2025)

MS-CLR: Multi-Skeleton Contrastive Learning for Human Action Recognition
di: Kiray, Mert, et al.
Pubblicazione: (2025)

A Unified Framework for Human-centric Point Cloud Video Understanding
di: Xu, Yiteng, et al.
Pubblicazione: (2024)

CoE: Deep Coupled Embedding for Non-Rigid Point Cloud Correspondences
di: Zeng, Huajian, et al.
Pubblicazione: (2024)

Skeleton-based Robust Registration Framework for Corrupted 3D Point Clouds
di: Wang, Yongqiang, et al.
Pubblicazione: (2025)

CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding
di: Liu, Yunze, et al.
Pubblicazione: (2024)

Improving Out-of-distribution Human Activity Recognition via IMU-Video Cross-modal Representation Learning
di: Cheshmi, Seyyed Saeid, et al.
Pubblicazione: (2025)

3DInAction: Understanding Human Actions in 3D Point Clouds
di: Ben-Shabat, Yizhak, et al.
Pubblicazione: (2023)

CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Framework
di: Xu, Yanlong, et al.
Pubblicazione: (2025)

Representation Learning for Point Cloud Understanding
di: Yan, Siming
Pubblicazione: (2025)

PAVLM: Advancing Point Cloud based Affordance Understanding Via Vision-Language Model
di: Liu, Shang-Ching, et al.
Pubblicazione: (2024)

OG-PCL: Efficient Sparse Point Cloud Processing for Human Activity Recognition
di: Yan, Jiuqi, et al.
Pubblicazione: (2025)

Contrastive Metric Learning for Point Cloud Segmentation in Highly Granular Detectors
di: Marriott-Clarke, Max, et al.
Pubblicazione: (2026)

DuoCLR: Dual-Surrogate Contrastive Learning for Skeleton-based Human Action Segmentation
di: Tian, Haitao, et al.
Pubblicazione: (2025)

Finding Outliers in a Haystack: Anomaly Detection for Large Pointcloud Scenes
di: Faulkner, Ryan, et al.
Pubblicazione: (2025)

Point-In-Context: Understanding Point Cloud via In-Context Learning
di: Liu, Mengyuan, et al.
Pubblicazione: (2024)

COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition
di: Chen, Baiyu, et al.
Pubblicazione: (2025)

Geometric Prior Based Deep Human Point Cloud Geometry Compression
di: Wu, Xinju, et al.
Pubblicazione: (2023)

Preserving Topological and Geometric Embeddings for Point Cloud Recovery
di: Zhou, Kaiyue, et al.
Pubblicazione: (2025)