Dense Motion Captioning

• URL: http://arxiv.org/abs/2511.05369v1
• Date: Fri, 07 Nov 2025 15:55:10 GMT
• Title: Dense Motion Captioning
• Authors: Shiyao Xu, Benedetta Liberatori, Gül Varol, Paolo Rota,
• Abstract summary: We introduce Dense Motion Captioning, a novel task that aims to temporally localize and caption actions within 3D human motion sequences.<n>We present CompMo, the first large-scale dataset featuring richly annotated, complex motion sequences with precise temporal boundaries.<n>We also present DEMO, a model that integrates a large language model with a simple motion adapter, trained to generate dense, temporally grounded captions.
• Score: 23.084589115674586
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent advances in 3D human motion and language integration have primarily focused on text-to-motion generation, leaving the task of motion understanding relatively unexplored. We introduce Dense Motion Captioning, a novel task that aims to temporally localize and caption actions within 3D human motion sequences. Current datasets fall short in providing detailed temporal annotations and predominantly consist of short sequences featuring few actions. To overcome these limitations, we present the Complex Motion Dataset (CompMo), the first large-scale dataset featuring richly annotated, complex motion sequences with precise temporal boundaries. Built through a carefully designed data generation pipeline, CompMo includes 60,000 motion sequences, each composed of multiple actions ranging from at least two to ten, accurately annotated with their temporal extents. We further present DEMO, a model that integrates a large language model with a simple motion adapter, trained to generate dense, temporally grounded captions. Our experiments show that DEMO substantially outperforms existing methods on CompMo as well as on adapted benchmarks, establishing a robust baseline for future research in 3D motion understanding and captioning.

Related papers

• BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation [31.077229364298443]
  Text-guided dynamic 3D character generation has advanced rapidly, yet producing high-quality motion that faithfully reflects rich textual descriptions remains challenging.<n>Existing methods tend to generate limited sub-actions or incoherent motion due to fixed-length temporal inputs and discrete frame-wise representations that fail to capture rich motion semantics.<n>We address these limitations by representing motion with continuous differentiable B-spline curves, enabling more effective motion generation without modifying the capabilities of the underlying generative model.
  arXiv  Detail & Related papers  (2026-02-21T15:40:37Z)
• LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens [19.167250154665812]
  We propose LLaMo, a framework that extends pretrained large language models through a modality-specific Mixture-of-Transformers architecture.<n>We encode human motion into a causal continuous latent space and maintain the next-token prediction paradigm in the decoder-only backbone.<n>Our experiments demonstrate that LLaMo achieves high-fidelity text-to-motion generation and motion-to-text captioning in general settings.
  arXiv  Detail & Related papers  (2026-02-12T20:02:21Z)
• FrankenMotion: Part-level Human Motion Generation and Composition [41.84042766842064]
  We construct a high-quality motion dataset with atomic, temporally-aware part-level text annotations.<n>Our dataset captures asynchronous and semantically distinct part movements at fine temporal resolution.<n>Based on this dataset, we introduce a diffusion-based part-aware motion generation framework, namely FrankenMotion.
  arXiv  Detail & Related papers  (2026-01-15T23:50:07Z)
• UniHM: Universal Human Motion Generation with Object Interactions in Indoor Scenes [26.71077287710599]
  We propose UniHM, a unified motion language model that leverages diffusion-based generation for scene-aware human motion.<n>UniHM is the first framework to support both Text-to-Motion and Text-to-Human-Object Interaction (HOI) in complex 3D scenes.<n>Our approach introduces three key contributions: (1) a mixed-motion representation that fuses continuous 6DoF motion with discrete local motion tokens to improve motion realism; (2) a novel Look-Up-Free Quantization VAE that surpasses traditional VQ-VAEs in both reconstruction accuracy and generative performance; and (3) an enriched version of
  arXiv  Detail & Related papers  (2025-05-19T07:02:12Z)
• Segment Any Motion in Videos [80.72424676419755]
  We propose a novel approach for moving object segmentation that combines long-range trajectory motion cues with DINO-based semantic features.<n>Our model employs Spatio-Temporal Trajectory Attention and Motion-Semantic Decoupled Embedding to prioritize motion while integrating semantic support.
  arXiv  Detail & Related papers  (2025-03-28T09:34:11Z)
• MoChat: Joints-Grouped Spatio-Temporal Grounding LLM for Multi-Turn Motion Comprehension and Description [13.12764192547871]
  MoChat is a model capable of fine-grained-temporal grounding of human motion. We group spatial information of each skeleton frame based on human anatomical structure. Various annotations are generated for jointly training.
  arXiv  Detail & Related papers  (2024-10-15T08:49:59Z)
• HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects [86.86284624825356]
  HIMO is a dataset of full-body human interacting with multiple objects. HIMO contains 3.3K 4D HOI sequences and 4.08M 3D HOI frames.
  arXiv  Detail & Related papers  (2024-07-17T07:47:34Z)
• Infinite Motion: Extended Motion Generation via Long Text Instructions [51.61117351997808]
  "Infinite Motion" is a novel approach that leverages long text to extended motion generation. Key innovation of our model is its ability to accept arbitrary lengths of text as input. We incorporate the timestamp design for text which allows precise editing of local segments within the generated sequences.
  arXiv  Detail & Related papers  (2024-07-11T12:33:56Z)
• Seamless Human Motion Composition with Blended Positional Encodings [38.85158088021282]
  We introduce FlowMDM, the first diffusion-based model that generates seamless Human Motion Compositions (HMC) without postprocessing or redundant denoising steps. We achieve state-of-the-art results in terms of accuracy, realism, and smoothness on the Babel and HumanML3D datasets.
  arXiv  Detail & Related papers  (2024-02-23T18:59:40Z)
• FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing [56.29102849106382]
  FineMoGen is a diffusion-based motion generation and editing framework. It can synthesize fine-grained motions, with spatial-temporal composition to the user instructions. FineMoGen further enables zero-shot motion editing capabilities with the aid of modern large language models.
  arXiv  Detail & Related papers  (2023-12-22T16:56:02Z)
• DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion [70.33381660741861]
  We present DiverseMotion, a new approach for synthesizing high-quality human motions conditioned on textual descriptions. We show that our DiverseMotion achieves the state-of-the-art motion quality and competitive motion diversity.
  arXiv  Detail & Related papers  (2023-09-04T05:43:48Z)
• Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language [4.86658723641864]
  We propose a novel text-to-motion retrieval task, which aims at retrieving relevant motions based on a specified natural description. Inspired by the recent progress in text-to-image/video matching, we experiment with two widely-adopted metric-learning loss functions.
  arXiv  Detail & Related papers  (2023-05-25T08:32:41Z)
• Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding [61.57847727651068]
  Temporal sentence grounding aims to localize a target segment in an untrimmed video semantically according to a given sentence query. Most previous works focus on learning frame-level features of each whole frame in the entire video, and directly match them with the textual information. We propose a novel Motion- and Appearance-guided 3D Semantic Reasoning Network (MA3SRN), which incorporates optical-flow-guided motion-aware, detection-based appearance-aware, and 3D-aware object-level features.
  arXiv  Detail & Related papers  (2022-03-06T13:57:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.