paper-with-me

Papers

HyLiFormer: Hyperbolic Linear Attention for Skeleton-based Human Action Recognition

2025-02-09 · Yue Li, Haoxuan Qu, Mengyuan Liu, Jun Liu, Yujun Cai

Transformers have demonstrated remarkable performance in skeleton-based human action recognition, yet their quadratic computational complexity remains a bottleneck for real-world applications. To mitigate this, linear attention mechanisms have been explored but struggle to capture the hierarchical structure of skeleton data. Meanwhile, the Poincaré model, as a typical hyperbolic geometry, offers a powerful framework for modeling hierarchical structures but lacks well-defined operations for existing mainstream linear attention. In this paper, we propose HyLiFormer, a novel hyperbolic linear attention Transformer tailored for skeleton-based action recognition. Our approach incorporates a Hyperbolic Transformation with Curvatures (HTC) module to map skeleton data into hyperbolic space and a Hyperbolic Linear Attention (HLA) module for efficient long-range dependency modeling. Theoretical analysis and extensive experiments on NTU RGB+D and NTU RGB+D 120 datasets demonstrate that HyLiFormer significantly reduces computational complexity while preserving model accuracy, making it a promising solution for efficiency-critical applications.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionSkeleton Based Action RecognitionTemporal Action Localization

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

SkelHCC: A Hyperbolic CLIP-Driven Cache Adaptation Framework for Skeleton-based One-Shot Action Recognition

2026-06-02 · Yanan Liu, Anqi Zhu, Jingmin Zhu, Jun Liu 외 arxiv

Skeleton-based action recognition aims to understand human behaviors from body joint sequences and is especially challenging in the one-shot setting, where only a single labeled exemplar is available for each novel actio…

Action Recognition

HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimation

2026-05-11 · Vinduja Thekkath, Ashish Musale, Ajay Waghumbare, Upasna Singh arxiv

We introduce HYPERPOSE, a novel 3D human pose estimation framework that performs spatio-temporal reasoning entirely within the Lorentz model of hyperbolic space $\mathbb{H}^d$ to natively preserve the hierarchical tree t…

3D Human Pose Estimation

HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations

2023-03-10 · Luca Franco, Paolo Mandica, Bharti Munjal, Fabio Galasso

Self-paced learning has been beneficial for tasks where some initial knowledge is available, such as weakly supervised learning and domain adaptation, to select and order the training sample sequence, from easy to comple…

Action RecognitionDomain AdaptationSkeleton Based Action RecognitionUnsupervised Skeleton Based Action Recognition+1

On the spatial attention in Spatio-Temporal Graph Convolutional Networks for skeleton-based human action recognition

2020-11-07 · Negar Heidari, Alexandros Iosifidis

Graph convolutional networks (GCNs) achieved promising performance in skeleton-based human action recognition by modeling a sequence of skeletons as a spatio-temporal graph. Most of the recently proposed GCN-based method…

Action RecognitionTemporal Action Localization

Hypformer: Exploring Efficient Hyperbolic Transformer Fully in Hyperbolic Space

2024-07-01 · Menglin Yang, Harshit Verma, Delvin Ce Zhang, Jiahong Liu 외

Hyperbolic geometry have shown significant potential in modeling complex structured data, particularly those with underlying tree-like and hierarchical structures. Despite the impressive performance of various hyperbolic…