mlsanityData to 14 Oct 2026

TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis

arXiv 2305.00976 ↗First posted 2 May 2023cs.CV cs.CLcited by 198

Not on the map. Why?

Cited by 35 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this paper, we present TMR, a simple yet effective approach for text to 3D human motion retrieval. While previous work has only treated retrieval as a proxy evaluation metric, we tackle it as a standalone task. Our method extends the state-of-the-art text-to-motion synthesis model TEMOS, and incorporates a contrastive loss to better structure the cross-modal latent space. We show that maintaining the motion generation loss, along with the contrastive training, is crucial to obtain good performance. We introduce a benchmark for evaluation and provide an in-depth analysis by reporting results on several protocols. Our extensive experiments on the KIT-ML and HumanML3D datasets show that TMR outperforms the prior work by a significant margin, for example reducing the median rank from 54 to 19. Finally, we showcase the potential of our approach on moment retrieval. Our code and models are publicly available at https://mathis.petrovich.fr/tmr.

Key facts. Cited by 198 papers in the map (data through 14 Oct 2026). Builds on 42 of its 66 references that are in the map. First posted on arXiv 2 May 2023.

Builds on

42 of 66 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  6. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  7. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  8. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  9. 2022CoCa: Contrastive Captioners are Image-Text Foundation Modelscited by 1,274
  10. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  11. 2021Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrievalcited by 1,177
  12. 2022Human Motion Diffusion Modelcited by 1,080
30 more
  1. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
  2. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 780
  3. 2017Localizing Moments in Video with Natural Languagecited by 663
  4. 2021CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrievalcited by 651
  5. 2022When and why vision-language models behave like bags-of-words, and what to do about it?cited by 610
  6. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 588
  7. 2017TALL: Temporal Activity Localization via Language Querycited by 584
  8. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 575
  9. 2019End-to-End Learning of Visual Representations from Uncurated Instructional Videoscited by 507
  10. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  11. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 492
  12. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
  13. 2016The KIT Motion-Language Datasetcited by 338
  14. 2021BABEL: Bodies, Action and Behavior with English Labelscited by 265
  15. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  16. 2022MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesiscited by 218
  17. 2020TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrievalcited by 215
  18. 2021Synthesis of Compositional Animations from Textual Descriptionscited by 178
  19. 2022TEACH: Temporal Action Composition for 3D Humanscited by 176
  20. 2020Skeleton-Aware Networks for Deep Motion Retargetingcited by 124
  21. 2021MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptionscited by 108
  22. 2021Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformerscited by 93
  23. 2018Neural Kinematic Networks for Unsupervised Motion Retargettingcited by 88
  24. 2022Teaching Structured Vision&Language Concepts to Vision&Language Modelscited by 71
  25. 2023SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generationcited by 64
  26. 2020VLG-Net: Video-Language Graph Matching Network for Video Groundingcited by 50
  27. 2022MultiAct: Long-Term 3D Human Motion Generation from Multiple Action Labelscited by 45
  28. 2020Neural Pose Transfer by Spatially Adaptive Instance Normalizationcited by 38
  29. 2020Perpetual Motion: Generating Unbounded Human Motioncited by 36
  30. 2022LocATe: End-to-end Localization of Actions in 3D with Transformerscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 13; 2024: 44; 2025: 65; 2026: 76.

198 papers.

Sort:

By area:

  1. 2023OmniControl: Control Any Joint at Any Time for Human Motion Generationcited by 238
  2. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 168
  3. 2023MMM: Generative Masked Motion Modelcited by 131
  4. 2023HumanTOMATO: Text-aligned Whole-body Motion Generationcited by 104
  5. 2025Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videoscited by 102
  6. 2023TLControl: Trajectory and Language Control for Human Motion Synthesiscited by 94
  7. 2024Multi-Track Timeline Control for Text-Driven 3D Human Motion Generationcited by 91
  8. 2025MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Spacecited by 86
  9. 2024Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregressioncited by 85
  10. 2024InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interactioncited by 64
  11. 2024MotionFix: Text-Driven 3D Human Motion Editingcited by 64
  12. 2023AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyondcited by 63
38 more
  1. 2024LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioningcited by 59
  2. 2024BAMM: Bidirectional Autoregressive Motion Modelcited by 55
  3. 2025SnapMoGen: Human Motion Generation from Expressive Textscited by 47
  4. 2023DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusioncited by 37
  5. 2025MotionGPT3: Human Motion as a Second Modalitycited by 37
  6. 2026Kimodo: Scaling Controllable Human Motion Generationcited by 37
  7. 2025HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generationcited by 36
  8. 2024Enabling Synergistic Full-Body Control in Prompt-Based Co-Speech Motion Generationcited by 35
  9. 2025InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generationcited by 32
  10. 2024MotionChain: Conversational Motion Controllers via Multimodal Promptscited by 30
  11. 2024Unimotion: Unifying 3D Human Motion Synthesis and Understandingcited by 30
  12. 2024EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Spacecited by 30
  13. 2025Absolute Coordinates Make Motion Generation Easycited by 29
  14. 2025SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Predictioncited by 27
  15. 2023Plan, Posture and Go: Towards Open-World Text-to-Motion Generationcited by 26
  16. 2023Revisit Human-Scene Interaction via Space Occupancycited by 25
  17. 2024E.T. the Exceptional Trajectories: Text-to-camera-trajectory generation with character awarenesscited by 25
  18. 2024Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patchescited by 22
  19. 2024Scaling Large Motion Models with Million-Level Human Motionscited by 22
  20. 2025The Quest for Generalizable Motion Generation: Data, Model, and Evaluationcited by 22
  21. 2024Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patternscited by 21
  22. 2024KinMo: Kinematic-aware Human Motion Understanding and Generationcited by 21
  23. 2025HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generationcited by 19
  24. 2024LGTM: Local-to-Global Text-Driven Human Motion Diffusion Modelcited by 18
  25. 2024Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editingcited by 18
  26. 2024A Cross-Dataset Study for Text-based 3D Human Motion Retrievalcited by 17
  27. 2025Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animationcited by 17
  28. 2025From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robotscited by 17
  29. 2024Tri-Modal Motion Retrieval by Learning a Joint Embedding Spacecited by 16
  30. 2024Contact-aware Human Motion Generation from Textual Descriptionscited by 16
  31. 2024Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motioncited by 16
  32. 2024MMHead: Towards Fine-grained Multi-modal 3D Facial Animationcited by 16
  33. 2024SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimizationcited by 15
  34. 2025Dynamic Motion Blending for Versatile Motion Editingcited by 15
  35. 2025PersonaBooth: Personalized Text-to-Motion Generationcited by 14
  36. 2026TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Controlcited by 14
  37. 2023Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrasescited by 13
  38. 2024A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generationcited by 13

50 most cited of 198 All 198 (JSON)