paper-with-me

Papers

Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognition

2024-11-08 · Abhisek Ray, Ayush Raj, Maheshkumar H. Kolekar

Extracting multiscale contextual information and higher-order correlations among skeleton sequences using Graph Convolutional Networks (GCNs) alone is inadequate for effective action classification. Hypergraph convolution addresses the above issues but cannot harness the long-range dependencies. Transformer proves to be effective in capturing these dependencies and making complex contextual features accessible. We propose an Autoregressive Adaptive HyperGraph Transformer (AutoregAd-HGformer) model for in-phase (autoregressive and discrete) and out-phase (adaptive) hypergraph generation. The vector quantized in-phase hypergraph equipped with powerful autoregressive learned priors produces a more robust and informative representation suitable for hyperedge formation. The out-phase hypergraph generator provides a model-agnostic hyperedge learning technique to align the attributes with input skeleton embedding. The hybrid (supervised and unsupervised) learning in AutoregAd-HGformer explores the action-dependent feature along spatial, temporal, and channel dimensions. The extensive experimental results and ablation study indicate the superiority of our model over state-of-the-art hypergraph architectures on NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets.

📄 PDF Abstract BibTeX arXiv:2411.05692

Code (1)

rayabhisek123/autoregad-hgformer 공식 구현 pytorch

Tasks

Action ClassificationActivity Recognition

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Residual Connection 설명 없음
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 $x$…
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…
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers

2021-09-15 · Angel Martínez-González, Michael Villamizar, Jean-Marc Odobez

We propose to leverage Transformer architectures for non-autoregressive human motion prediction. Our approach decodes elements in parallel from a query sequence, instead of conditioning on previous predictions such as in…

ClassificationHuman motion predictionmotion prediction

Hypergraph Transformer for Skeleton-based Action Recognition

2022-11-17 · Yuxuan Zhou, Zhi-Qi Cheng, Chao Li, Yanwen Fang 외

Skeleton-based action recognition aims to recognize human actions given human joint coordinates with skeletal interconnections. By defining a graph with joints as vertices and their natural connections as edges, previous…

Action RecognitionSkeleton Based Action Recognition

Partial Skeleton Visibility for Action Recognition: A Constrained Field-of-View Approach

2026-07-01 · Yingjie Dai, Tianyang Xu, Yanglin Deng, Xiao-Jun Wu 외 arxiv

Skeleton-based action recognition has achieved remarkable success by exploiting joint coordinates and their topological connections, yet prevailing methods overwhelmingly assume complete and clean skeleton inputs. In rea…

Action UnderstandingAction Recognition

Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition

2021-12-20 · Jinfeng Wei, Yunxin Wang, Mengli Guo, Pei Lv 외

Graph convolutional networks (GCNs) based methods have achieved advanced performance on skeleton-based action recognition task. However, the skeleton graph cannot fully represent the motion information contained in skele…

Action RecognitionSkeleton Based Action Recognition

Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition

2023-02-17 · Shengqin Wang, Yongji Zhang, Hong Qi, Minghao Zhao 외

Skeleton-based action recognition relies on the extraction of spatial-temporal topological information. Hypergraphs can establish prior unnatural dependencies for the skeleton. However, the existing methods only focus on…

Action RecognitionSkeleton Based Action Recognition