mlsanityData to 7 Oct 2026

RAM: Recover Any 3D Human Motion in-the-Wild

arXiv 2603.19929 ↗First posted 20 Mar 2026cs.CV cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

RAM incorporates a motion-aware semantic tracker with adaptive Kalman filtering to achieve robust identity association under severe occlusions and dynamic interactions. A memory-augmented Temporal HMR module further enhances human motion reconstruction by injecting spatio-temporal priors for consistent and smooth motion estimation. Moreover, a lightweight Predictor module forecasts future poses to maintain reconstruction continuity, while a gated combiner adaptively fuses reconstructed and predicted features to ensure coherence and robustness. Experiments on in-the-wild multi-person benchmarks such as PoseTrack and 3DPW, demonstrate that RAM substantially outperforms previous state-of-the-art in both Zero-shot tracking stability and 3D accuracy, offering a generalizable paradigm for markerless 3D human motion capture in-the-wild.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 79 of its 101 references that are in the map. First posted on arXiv 20 Mar 2026.

Builds on

79 of 101 references.

References · 79

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2023Segment Anythingcited by 8,158
  3. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  4. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
  5. 2017End-to-end Recovery of Human Shape and Posecited by 883
  6. 2016Simple Online and Realtime Trackingcited by 862
  7. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  8. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  9. 2019Tracking without bells and whistlescited by 382
  10. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 344
  11. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  12. 2023TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinementcited by 281
38 more
  1. 2022MixFormer: End-to-End Tracking with Iterative Mixed Attentioncited by 278
  2. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  3. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  4. 2017PoseTrack: A Benchmark for Human Pose Estimation and Trackingcited by 173
  5. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  6. 2017Deep representation learning for human motion prediction and classificationcited by 97
  7. 20163D Human Pose Estimation from a Single Image via Distance Matrix Regressioncited by 73
  8. 2023Hybrid-SORT: Weak Cues Matter for Online Multi-Object Trackingcited by 66
  9. 2023MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Trackingcited by 64
  10. 2024SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfercited by 61
  11. 2024DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Predictioncited by 59
  12. 2021DEFT: Detection Embeddings for Trackingcited by 56
  13. 2025Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecastingcited by 53
  14. 2021RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representationcited by 52
  15. 20204D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Camerascited by 49
  16. 2023Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimationcited by 46
  17. 2024IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localizationcited by 42
  18. 2024Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localizationcited by 35
  19. 2022Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Trackingcited by 33
  20. 2024Scaling Law for Time Series Forecastingcited by 31
  21. 2025SepPrune: Structured Pruning for Efficient Deep Speech Separationcited by 31
  22. 2022Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Drivingcited by 30
  23. 2024Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Cameracited by 30
  24. 2024Human Motion Instruction Tuningcited by 29
  25. 2024Unsupervised Hyperspectral Image Super-Resolution via Self-Supervised Modality Decouplingcited by 26
  26. 2023Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimationcited by 24
  27. 2020Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videoscited by 23
  28. 2025ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localizationcited by 22
  29. 2024Mitigating the Risk of Health Inequity Exacerbated by Large Language Modelscited by 21
  30. 2025EdgeTAM: On-Device Track Anything Modelcited by 21
  31. 2024The Role of Deductive and Inductive Reasoning in Large Language Modelscited by 20
  32. 2023PanoContext-Former: Panoramic Total Scene Understanding with a Transformercited by 19
  33. 2024MultiPhys: Multi-Person Physics-aware 3D Motion Estimationcited by 18
  34. 2024MambaTrack: A Simple Baseline for Multiple Object Tracking with State Space Modelcited by 18
  35. 2022Mask-FPAN: Semi-Supervised Face Parsing in the Wild With De-Occlusion and UV GANcited by 16
  36. 2026A Survey of Weight Space Learning: Understanding, Representation, and Generationcited by 15
  37. 2025ChatMotion: A Multimodal Multi-Agent for Human Motion Analysiscited by 13
  38. 2025CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Modelcited by 13

50 most cited of 79 All 79 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 11.

11 papers.

  1. 2026ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrievalcited by 39
  2. 2026INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrievalcited by 26
  3. 2026HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrievalcited by 24
  4. 2026ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrievalcited by 15
  5. 2026MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonalitycited by 3
  6. 2026Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimizationcited by 0
  7. 2026Improving Multimodal Reasoning via Worst Dimension Optimizationcited by 0
  8. 2026VigilFormer: Deformable Attention for Video Anomaly Detection with Causal Risk Inferencecited by 0
  9. 2026Bridging Geographic Bias in Urban Streetscape Inference via Lifelong Learning with Visual-Semantic Pivotingcited by 0
  10. 2026URDF Synthesis from RGB-D Sequences via Differentiable Joint Inference and Energy-Consistent Verificationcited by 0
  11. 2026SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verificationcited by 0