SOTAVerified

Human motion prediction

Action prediction is a pre-fact video understanding task, which focuses on future states, in other words, it needs to reason about future states or infer action labels before the end of action execution.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 162 papers

TitleStatusHype
TransFusion: A Practical and Effective Transformer-based Diffusion Model for 3D Human Motion PredictionCode1
Learning Snippet-to-Motion Progression for Skeleton-based Human Motion Prediction—0
Physics-constrained Attack against Convolution-based Human Motion PredictionCode0
Stochastic Multi-Person 3D Motion ForecastingCode1
CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion DiffusionCode1
Remembering What Is Important: A Factorised Multi-Head Retrieval and Auxiliary Memory Stabilisation Scheme for Human Motion Prediction—0
Towards Accurate Human Motion Prediction via Iterative Refinement—0
A Neuro-Symbolic Approach for Enhanced Human Motion PredictionCode0
DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedback—0
Graph-Guided MLP-Mixer for Skeleton-Based Human Motion Prediction—0
SPOTR: Spatio-temporal Pose Transformers for Human Motion Prediction—0
Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal AnchorsCode1
HumanMAC: Masked Motion Completion for Human Motion PredictionCode2
Decompose More and Aggregate Better: Two Closer Looks at Frequency Representation Learning for Human Motion Prediction—0
Few-shot human motion prediction for heterogeneous sensorsCode0
BeLFusion: Latent Diffusion for Behavior-Driven Human Motion PredictionCode1
Multi-view Tracking Using Weakly Supervised Human Motion PredictionCode1
Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction—0
KP-RNN: A Deep Learning Pipeline for Human Motion Prediction and Synthesis of Performance ArtCode0
STPOTR: Simultaneous Human Trajectory and Pose Prediction Using a Non-Autoregressive Transformer for Robot Following AheadCode1
DMMGAN: Diverse Multi Motion Prediction of 3D Human Joints using Attention-Based Generative Adverserial Network—0
Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Prediction—0
Skeleton-Parted Graph Scattering Networks for 3D Human Motion PredictionCode1
Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary SpaceCode1
Learning Disentangled Representations for Controllable Human Motion Prediction—0
Show:102550
← PrevPage 3 of 7Next →

No leaderboard results yet.