AI Paper Atlas

Research map / Benchmarks / MSR-Action3D (24 frames)

MSR-Action3D (24 frames) leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MSR-Action3D (24 frames). Best accuracy: 97.21 (PoinTriE, ECCV 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

MSR-Action3D (24 frames) · accuracy

11 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
197.21PoinTriETri-Efficient Transfer Learning for Point Cloud Videos
ECCV 2026 · Table 1
Point cloud classification
295.12Point-MAE+CSA
Point-MAE
Adapting Pre-trained 3D Models for Point Cloud Video Understanding via Cross-frame Spatio-temporal Perception
CVPR 2025 · Table 1
Point cloud classification
394.77UST-SSM (Ours)UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling
ICCV 2025 · Table 1
Point cloud classification
493.38Mamba4D (PST-Transformer + Ours)
PST-Transformer
Mamba4D: Efficient 4D Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models
CVPR 2025 · Table 1
Point cloud classification
593.27PSTNet + PointCMP (end-to-end fine-tuning)
PSTNet
PointCMP: Contrastive Mask Prediction for Self-Supervised Learning on Point Cloud Videos
CVPR 2023 · Table: Action recognition accu
Point cloud classification
693.27Kinet
PointNet++
No Pain, Big Gain: Classify Dynamic Point Cloud Sequences With Static Models by Fitting Feature-Level Space-Time Surfaces
CVPR 2022 · Table: Quantitative results ac
Point cloud classification
793.03CPR
PSTNet
Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning
AAAI 2023 · Table 1
Point cloud classification
892.33PPTrPoint Primitive Transformer for Long-Term 4D Point Cloud Video Understanding
ECCV 2022 · Table 3
Point cloud classification
992.233DinAction3DInAction: Understanding Human Actions in 3D Point Clouds
CVPR 2024 · Table 3
Human pose estimation
1091.2PSTNetPSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences
ICLR 2021 · Table: Action recognition accu
Point cloud classification
1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.