HolisticSemGes: Semantic Grounding of Holistic Co-Speech Gesture Generation with Contrastive Flow-Matching

• URL: http://arxiv.org/abs/2603.26553v1
• Date: Fri, 27 Mar 2026 16:11:44 GMT
• Title: HolisticSemGes: Semantic Grounding of Holistic Co-Speech Gesture Generation with Contrastive Flow-Matching
• Abstract summary: We introduce a Contrastive Flow Matching-based co-speech gesture generation model.<n>It uses mismatched audio-text conditions as negatives, training the velocity field to follow the correct motion trajectory while repelling semantically incongruent trajectories.<n>Our model ensures cross-modal coherence by embedding text, audio, and holistic motion into a composite latent space via cosine and contrastive objectives.
• Score: 1.6916040234975798
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While the field of co-speech gesture generation has seen significant advances, producing holistic, semantically grounded gestures remains a challenge. Existing approaches rely on external semantic retrieval methods, which limit their generalisation capability due to dependency on predefined linguistic rules. Flow-matching-based methods produce promising results; however, the network is optimised using only semantically congruent samples without exposure to negative examples, leading to learning rhythmic gestures rather than sparse motion, such as iconic and metaphoric gestures. Furthermore, by modelling body parts in isolation, the majority of methods fail to maintain crossmodal consistency. We introduce a Contrastive Flow Matching-based co-speech gesture generation model that uses mismatched audio-text conditions as negatives, training the velocity field to follow the correct motion trajectory while repelling semantically incongruent trajectories. Our model ensures cross-modal coherence by embedding text, audio, and holistic motion into a composite latent space via cosine and contrastive objectives. Extensive experiments and a user study demonstrate that our proposed approach outperforms state-of-the-art methods on two datasets, BEAT2 and SHOW.

Related papers

• SiGnature: Explicit Motion Diffusion for Stylized Semantic Gesture [31.872713283587604]
  SiGnature is a framework for Stylized and Semantic Gesture generation.<n>It reconciles precise semantic control with high-fidelity style preservation.<n>It offers superior semantic motion control while maintaining smooth and natural co-speech gesture generation.
  arXiv  Detail & Related papers  (2026-06-14T16:18:26Z)
• AffordGrasp: Cross-Modal Diffusion for Affordance-Aware Grasp Synthesis [50.793806818677716]
  AffordGrasp produces physically stable and semantically faithful human grasps with high precision.<n>AffordGrasp integrates an affordance-aware latent representation of hand poses with a dual-conditioning diffusion process.<n>We evaluate AffordGrasp across four instruction-augmented benchmarks derived from HO-3D, OakInk, GRAB, and AffordPose.
  arXiv  Detail & Related papers  (2026-03-09T06:56:35Z)
• MIBURI: Towards Expressive Interactive Gesture Synthesis [62.45332399212876]
  Embodied Conversational Agents (ECAs) aim to emulate human face-to-face interaction through speech, gestures, and facial expressions.<n>Existing solutions for ECAs produce rigid, low-diversity motions that are unsuitable for human-like interaction.<n>We present MIBURI, the first online, causal framework for generating expressive full-body gestures and facial expressions synchronized with real-time spoken dialogue.
  arXiv  Detail & Related papers  (2026-03-03T18:59:51Z)
• Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning [56.6025512458557]
  Motion-language retrieval aims to bridge the semantic gap between natural language and human motion.<n>Existing approaches predominantly focus on aligning entire motion sequences with global textual representations.<n>We propose a novel Pyramidal Shapley-Taylor (PST) learning framework for fine-grained motion-language retrieval.
  arXiv  Detail & Related papers  (2026-01-29T16:00:12Z)
• SemGes: Semantics-aware Co-Speech Gesture Generation using Semantic Coherence and Relevance Learning [0.6249768559720122]
  We propose a novel approach for semantic grounding in co-speech gesture generation.<n>Our approach starts with learning the motion prior through a vector-quantized variational autoencoder.<n>Our method outperforms state-of-the-art approaches across two benchmarks in co-speech gesture generation.
  arXiv  Detail & Related papers  (2025-07-25T15:10:15Z)
• SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis [19.764460501254607]
  A good co-speech motion generation cannot be achieved without a careful integration of common rhythmic motion and rare yet essential semantic motion.<n>We propose SemTalk for holistic co-speech motion generation with frame-level semantic emphasis.
  arXiv  Detail & Related papers  (2024-12-21T10:16:07Z)
• Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis [55.45253486141108]
  RAG-Gesture is a diffusion-based gesture generation approach to produce semantically rich gestures.<n>We achieve this by using explicit domain knowledge to retrieve motions from a database of co-speech gestures.<n>We propose a control paradigm for guidance, that allows the users to modulate the amount of influence each retrieval insertion has over the generated sequence.
  arXiv  Detail & Related papers  (2024-12-09T18:59:46Z)
• Emphasizing Semantic Consistency of Salient Posture for Speech-Driven Gesture Generation [44.78811546051805]
  Speech-driven gesture generation aims at synthesizing a gesture sequence synchronized with the input speech signal. Previous methods leverage neural networks to directly map a compact audio representation to the gesture sequence. We propose a novel speech-driven gesture generation method by emphasizing the semantic consistency of salient posture.
  arXiv  Detail & Related papers  (2024-10-17T17:22:59Z)
• DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning [59.4644086610381]
  We propose a novel denoising objective that inherits from another perspective, i.e., the intra-sentence perspective. By introducing both discrete and continuous noise, we generate noisy sentences and then train our model to restore them to their original form. Our empirical evaluations demonstrate that this approach delivers competitive results on both semantic textual similarity (STS) and a wide range of transfer tasks.
  arXiv  Detail & Related papers  (2024-01-24T17:48:45Z)
• AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture Synthesis [0.0]
  We present an approach to pre-train partial gesture sequences using a generative adversarial network with a quantization pipeline. By learning the mapping of a latent space representation as opposed to directly mapping it to a vector representation, this framework facilitates the generation of highly realistic and expressive gestures.
  arXiv  Detail & Related papers  (2023-05-02T07:59:38Z)
• Robust Unsupervised Cross-Lingual Word Embedding using Domain Flow Interpolation [48.32604585839687]
  Previous adversarial approaches have shown promising results in inducing cross-lingual word embedding without parallel data. We propose to make use of a sequence of intermediate spaces for smooth bridging.
  arXiv  Detail & Related papers  (2022-10-07T04:37:47Z)

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.