Browse State-of-the-Art › 3D Action Recognition
3D Action Recognition
38 papers with code · 3 benchmarks · 15 datasets archive 2025-07-28
Image: Rahmani et al
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Assembly101 (7 rows) | HandFormer-B/21 | On the Utility of 3D Hand Poses for Action Recognition | code | Syntology official (archive's flag): 8 ran · 8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified | Compare |
| NTU RGB+D (5 rows) | Kinet | No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with... | code | — | Compare |
| 100 sleep nights of 8 caregivers (1 row) | htf | A System for Real-Time Interactive Analysis of Deep Learning Training | code | Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
15 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
6 subtasks in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 91 · with a code link: 38 · where Syntology ran a sample: 12 (9 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (12 of 91 tagged: 9 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 91 of 91, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
30 Oct 2017 24 repositories listed Syntology community repositories only · 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 3 pointer-only (licence)Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision problems.
-
20 Nov 2018 13 repositories listed Syntology official: harvested, nothing ran · 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified (of 16 harvested samples) · 6 pointer-only (licence)The explosive growth in video streaming gives rise to challenges on performing video understanding at high accuracy and low computation cost.
-
19 Jun 2019 6 repositories listed Syntology community repositories only · 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (of 11 harvested samples) · 4 pointer-only (licence)In this work we aim to learn object representations that are useful for control and reinforcement learning (RL).
-
28 Apr 2021 4 repositories listedIn this work, we propose PoseC3D, a new approach to skeleton-based action recognition, which relies on a 3D heatmap stack instead of a graph sequence as the base representation of human skeletons.
-
20 May 2018 4 repositories listedIn addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely investigated in existing…
-
31 Mar 2020 3 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)Spatial-temporal graphs have been widely used by skeleton-based action recognition algorithms to model human action dynamics.
-
30 May 2020 2 repositories listedOne primary technical challenge in photoacoustic microscopy (PAM) is the necessary compromise between spatial resolution and imaging speed.
-
11 Apr 2016 2 repositories listedRecent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes.
-
9 Oct 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)To this end, we introduce a Convex Hull Adaptive Shift based multi-Entity action recognition method (CHASE), which mitigates inter-entity distribution gaps and unbiases subsequent backbones.
-
26 Sep 2024 1 repository listedIn self-supervised skeleton-based action recognition, the mask reconstruction paradigm is gaining interest in enhancing model refinement and robustness through effective masking.
-
15 Jul 2024 1 repository listedSelf-supervised pretraining methods with masked prediction demonstrate remarkable within-dataset performance in skeleton-based action recognition.
-
14 Mar 2024 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified (of 13 harvested samples)3D hand pose is an underexplored modality for action recognition.
-
14 Aug 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)To be specific, the proposed MAMP takes as input the masked spatio-temporal skeleton sequence and predicts the corresponding temporal motion of the masked human joints.
-
14 Jul 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)To address these problems, we propose an Interactive Spatiotemporal Token Attention Network (ISTA-Net), which simultaneously model spatial, temporal, and interactive relations.
-
26 Aug 2022 1 repository listedIn this work, we formulate the cross-modal interaction as a bidirectional knowledge distillation problem.
-
20 Jul 2022 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)Furthermore, to leverage the complementarity of domain-shared features and target-specific features, we propose a novel collaborative clustering strategy to enforce pair-wise relationship consistency between the two…
-
27 Jun 2022 1 repository listed Syntology official (archive's flag): 19 ran · 19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified (of 26 harvested samples)To solve this problem, we present a multi-scale spatial graph convolution (MS-GC) module and a multi-scale temporal graph convolution (MT-GC) module to enrich the receptive field of the model in spatial and temporal…
-
27 May 2022 1 repository listedThen, a spatial convolution is employed to capture the local structure of points in the 3D space, and a temporal convolution is used to model the dynamics of the spatial regions along the time dimension.
-
28 Mar 2022 1 repository listedAssembly101 is a new procedural activity dataset featuring 4321 videos of people assembling and disassembling 101 "take-apart" toy vehicles.
-
21 Mar 2022 1 repository listedScene flow is a powerful tool for capturing the motion field of 3D point clouds.
-
28 Feb 2022 1 repository listedTo that end, we propose to learn exercise-oriented image and video representations from unlabeled samples such that a small dataset annotated by experts suffices for supervised error detection.
-
14 Dec 2021 1 repository listedSpecifically, a spatial operation is employed to capture the local structure of each spatial region in a tube and a temporal operation is used to model the dynamics of the spatial regions along the tube.
-
1 Dec 2021 1 repository listedFurthermore, unlike existing volumetric MVS techniques, our 3D CNN operates on a feature-augmented point cloud, allowing for effective aggregation of multi-view information and flexible iterative refinement of depth…
-
16 Nov 2021 1 repository listedInstead of capturing spatio-temporal local structures, SequentialPointNet encodes the temporal evolution of static appearances to recognize human actions.
-
19 Jun 2021 1 repository listedTo capture the dynamics in point cloud videos, point tracking is usually employed.
-
17 Jun 2021 1 repository listedTo address this, we present BABEL, a large dataset with language labels describing the actions being performed in mocap sequences.
-
1 Aug 2020 1 repository listedWe propose novel approaches for simultaneously identifying important weights of a convolutional neural network (ConvNet) and providing more attention to the important weights during training.
-
Roweisposes, Including Eigenposes, Supervised Eigenposes, and Fisherposes, for 3D Action Recognition28 Jun 2020 1 repository listedAlthough various methods have been proposed for 3D action recognition, some of which are basic and some use deep learning, the need of basic methods based on generalized eigenvalue problem is sensed for action…
-
12 May 2020 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)Each available 3DV voxel intrinsically involves 3D spatial and motion feature jointly.
-
5 Jan 2020 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified (of 17 harvested samples)To achieve this, we model various exploratory inspection and diagnostic tasks for deep learning training processes as specifications for streams using a map-reduce paradigm with which many data scientists are already…
-
Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints11 Sep 2019 1 repository listed
-
30 Jul 2019 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
13 Jun 2019 1 repository listed
-
5 Jun 2018 1 repository listed
-
15 Feb 2018 1 repository listed
-
21 Aug 2017 1 repository listed
-
2 May 2017 1 repository listed
-
14 Apr 2017 1 repository listed
-
KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognition14 Sep 2024 0 repositories listed
-
PRENet: A Plane-Fit Redundancy Encoding Point Cloud Sequence Network for Real-Time 3D Action Recognition11 May 2024 0 repositories listed
-
CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner15 Mar 2024 0 repositories listed
-
Learning Scene Flow With Skeleton Guidance For 3D Action Recognition23 Jun 2023 0 repositories listed
-
Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization18 Apr 2023 0 repositories listed
-
Spatial-Temporal Transformer for 3D Point Cloud Sequences19 Oct 2021 0 repositories listed
-
Unsupervised View-Invariant Human Posture Representation17 Sep 2021 0 repositories listed
-
Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning4 Aug 2021 0 repositories listed
-
Real-time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model24 May 2021 0 repositories listed
-
Independent Sign Language Recognition with 3D Body, Hands, and Face Reconstruction24 Nov 2020 0 repositories listed
-
VI-Net: View-Invariant Quality of Human Movement Assessment11 Aug 2020 0 repositories listed
-
1 Aug 2020 0 repositories listed
-
Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition12 Jul 2020 0 repositories listed
-
Graph Partitioning and Graph Neural Network based Hierarchical Graph Matching for Graph Similarity Computation16 May 2020 0 repositories listed
-
CoSimGNN: Towards Large-scale Graph Similarity Computation14 May 2020 0 repositories listed
-
Combining Deep Learning Classifiers for 3D Action Recognition21 Apr 2020 0 repositories listed
-
16 Dec 2019 0 repositories listed
-
Skeleton based Activity Recognition by Fusing Part-wise Spatio-temporal and Attention Driven Residues2 Dec 2019 0 repositories listed
-
Order-Preserving Wasserstein Discriminant Analysis1 Oct 2019 0 repositories listed
-
DWnet: Deep-Wide Network for 3D Action Recognition29 Aug 2019 0 repositories listed
-
A Deep Learning Approach for Real-Time 3D Human Action Recognition from Skeletal Data8 Jul 2019 0 repositories listed
-
16 Jun 2019 0 repositories listed
-
Localized Trajectories for 2D and 3D Action Recognition10 Apr 2019 0 repositories listed
-
Learning to Recognize 3D Human Action from A New Skeleton-based Representation Using Deep Convolutional Neural Networks26 Dec 2018 0 repositories listed
-
Dynamic Graph Modules for Modeling Object-Object Interactions in Activity Recognition13 Dec 2018 0 repositories listed
-
1 Sep 2018 0 repositories listed
-
Skeletal Movement to Color Map: A Novel Representation for 3D Action Recognition with Inception Residual Networks18 Jul 2018 0 repositories listed
-
3D Human Action Recognition with Siamese-LSTM Based Deep Metric Learning5 Jul 2018 0 repositories listed
-
Coding Kendall's Shape Trajectories for 3D Action Recognition1 Jun 2018 0 repositories listed
-
30 May 2018 0 repositories listed
-
Depth Pooling Based Large-scale 3D Action Recognition with Convolutional Neural Networks17 Mar 2018 0 repositories listed
-
5 Mar 2018 0 repositories listed
-
Robust 3D Action Recognition through Sampling Local Appearances and Global Distributions4 Dec 2017 0 repositories listed
-
Scalable and Compact 3D Action Recognition with Approximated RBF Kernel Machines28 Nov 2017 0 repositories listed
-
Train, Diagnose and Fix: Interpretable Approach for Fine-grained Action Recognition22 Nov 2017 0 repositories listed
-
A Compact Kernel Approximation for 3D Action Recognition6 Sep 2017 0 repositories listed
-
1 Jul 2017 0 repositories listed
-
Two-Stream 3D Convolutional Neural Network for Skeleton-Based Action Recognition23 May 2017 0 repositories listed
-
9 Apr 2017 0 repositories listed
-
9 Mar 2017 0 repositories listed
-
28 Feb 2017 0 repositories listed
-
Deep Learning on Lie Groups for Skeleton-based Action Recognition18 Dec 2016 0 repositories listed
-
A Tube-and-Droplet-based Approach for Representing and Analyzing Motion Trajectories10 Sep 2016 0 repositories listed
-
24 Jul 2016 0 repositories listed
-
3D Action Recognition From Novel Viewpoints1 Jun 2016 0 repositories listed
-
Efficient Temporal Sequence Comparison and Classification Using Gram Matrix Embeddings on a Riemannian Manifold1 Jun 2016 0 repositories listed
-
Kernelized Covariance for Action Recognition22 Apr 2016 0 repositories listed
-
Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons (Extended Version)1 Apr 2016 0 repositories listed
-
First-Take-All: Temporal Order-Preserving Hashing for 3D Action Videos6 Jun 2015 0 repositories listed
-
1 May 2015 0 repositories listed
-
Histogram of Oriented Principal Components for Cross-View Action Recognition24 Sep 2014 0 repositories listed
-
Mining Mid-level Features for Action Recognition Based on Effective Skeleton Representation14 Sep 2014 0 repositories listed
-
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition17 Aug 2014 0 repositories listed
Syntology lines on 13 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections