paper-with-me

3D Action Recognition

3개 벤치마크 · 논문 96편 · 이 태스크의 논문 보기 →

Benchmarks

Assembly101

결과 49개

NTU RGB+D

결과 35개

Most implemented

Papers

STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understanding

2026-04-13 · Wenhao Li, Xueying Jiang, Gongjie Zhang, Xiaoqin Zhang 외 arxiv

4D point cloud videos capture rich spatial and temporal dynamics of scenes which possess unique values in various 4D understanding tasks. However, most existing methods work in the spatiotemporal domain where the underly…

Representation Learning3D Action RecognitionSemantic Segmentation

Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perception

2026-02-26 · Yiding Sun, Jihua Zhu, Haozhe Cheng, Chaoyi Lu 외 arxiv

Point cloud video understanding is critical for robotics as it accurately encodes motion and scene interaction. We recognize that 4D datasets are far scarcer than 3D ones, which hampers the scalability of self-supervised…

3D Action RecognitionSemantic SegmentationAction SegmentationTransfer Learning

Learning Topology-Driven Multi-Subspace Fusion for Grassmannian Deep Network

2025-11-09 · Xuan Yu, Tianyang Xu arxiv

Grassmannian manifold offers a powerful carrier for geometric representation learning by modelling high-dimensional data as low-dimensional subspaces. However, existing approaches predominantly rely on static single-subs…

Representation Learning3D Action Recognition

Informative Sample Selection Model for Skeleton-based Action Recognition with Limited Training Samples

2025-10-29 · Zhigang Tu, Zhengbo Zhang, Jia Gong, Junsong Yuan 외 arxiv

Skeleton-based human action recognition aims to classify human skeletal sequences, which are spatiotemporal representations of actions, into predefined categories. To reduce the reliance on costly annotations of skeletal…

3D Action RecognitionActive Learning

Human Action Recognition from Point Clouds over Time

2025-10-07 · James Dickens arxiv

Recent research into human action recognition (HAR) has focused predominantly on skeletal action recognition and video-based methods. With the increasing availability of consumer-grade depth sensors and Lidar instruments…

Monocular Depth Estimation3D Action RecognitionPoint Clouds

CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition

2024-10-09 · Yuhang Wen, Mengyuan Liu, Songtao Wu, Beichen Ding

Skeleton-based multi-entity action recognition is a challenging task aiming to identify interactive actions or group activities involving multiple diverse entities. Existing models for individuals often fall short in thi…

3D Action RecognitionAction RecognitionGroup Activity RecognitionHuman Interaction Recognition+1

전체 96편 보기 →