Pith. sign in

REVIEW 6 cited by

Hypergraph Transformer for Skeleton-based Action Recognition

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2211.09590 v5 pith:DUFY6IUP submitted 2022-11-17 cs.CV

classification cs.CV
keywords graphgcnsmodelshypergraphmodelself-attentionstate-of-the-artaction
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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 works successfully adopted Graph Convolutional networks (GCNs) to model joint co-occurrences and achieved superior performance. More recently, a limitation of GCNs is identified, i.e., the topology is fixed after training. To relax such a restriction, Self-Attention (SA) mechanism has been adopted to make the topology of GCNs adaptive to the input, resulting in the state-of-the-art hybrid models. Concurrently, attempts with plain Transformers have also been made, but they still lag behind state-of-the-art GCN-based methods due to the lack of structural prior. Unlike hybrid models, we propose a more elegant solution to incorporate the bone connectivity into Transformer via a graph distance embedding. Our embedding retains the information of skeletal structure during training, whereas GCNs merely use it for initialization. More importantly, we reveal an underlying issue of graph models in general, i.e., pairwise aggregation essentially ignores the high-order kinematic dependencies between body joints. To fill this gap, we propose a new self-attention (SA) mechanism on hypergraph, termed Hypergraph Self-Attention (HyperSA), to incorporate intrinsic higher-order relations into the model. We name the resulting model Hyperformer, and it beats state-of-the-art graph models w.r.t. accuracy and efficiency on NTU RGB+D, NTU RGB+D 120, and Northwestern-UCLA datasets.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

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

    cs.CV 2026-07 unverdicted novelty 7.0 of 10

    PartialVisGraph is a hypergraph framework with learnable virtual hyperedges and a sample-adaptive transformer incorporating visibility prior, achieving reported SOTA gains up to 68.8% under simulated partial FoV on NT...

  2. STAR: Skeletal Token Alignment and Rearrangement for Interaction Recognition

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Skeleton-only interaction recognition that aligns skeleton and video features during training outperforms prior state-of-the-art on four benchmarks.

  3. Beyond Pairwise Relations: Dynamic Manipulation Hypergraphs for Vision-Based Human Activity Recognition

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Dynamic manipulation hypergraphs with time-varying multi-entity templates outperform matched pairwise graphs and static hypergraphs on fine-grained manipulation recognition.

  4. Patch-Wise Hypergraph Contrastive Learning with Dual Normal Distribution Weighting for Multi-Domain Stain Transfer

    cs.CV 2025-03 unverdicted novelty 5.0 of 10

    STNHCL uses hypergraph modeling of patch relationships and dual Gaussian weighting of negative samples to achieve state-of-the-art multi-domain stain transfer while addressing limitations of cycle consistency.

  5. CascadeFormer: A Family of Two-stage Cascading Transformers for Skeleton-based Human Action Recognition

    cs.CV 2025-08 conditional novelty 4.0 of 10

    A masked-pretrained skeleton transformer with a second fine-tuning transformer and cross-attention fusion reaches 94.66% on Penn Action, 91.16% on N-UCLA, and 81.01%/88.17% on NTU RGB+D 60 cross-subject/cross-view.

  6. FLASH: Efficient Impact Fall Detection with Unified Hypergraph State-Space Model

    cs.CV 2026-07 reject novelty 3.0 of 10

    FLASH uses single-matrix hypergraph convolutions plus Mamba to detect fall impact frames efficiently, but it is less accurate than its own dual-hypergraph predecessor.

Pith tools