Semantic Motion Anchors:
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures
Announce Type: replace Abstract: Learning a shared representation between spoken text and gesture is central to co-speech gesture retrieval, synthesis, and understanding, but remains challenging for semantically meaningful gestures whose communicative intent is not captured by motion alone. Direct contrastive alignment between transcripts and continuous motion embeddings often overemphasizes low-level kinematics and misses the symbolic content of semantic gestures. We propose semantic motion...
Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures
arXiv:2605.30608v1 Announce Type: new Abstract: Learning a shared representation between spoken text and gesture is central to co-speech gesture retrieval, synthesis, and understanding, but remains challenging for semantically meaningful gestures whose communicative intent is not captured by motion alone. Direct contrastive alignment between transcripts and continuous motion embeddings often overemphasizes low-level kinematics and misses the symbolic content of semantic gestures. We propose...
Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures
Announce Type: replace Abstract: Learning a shared representation between spoken text and gesture is central to co-speech gesture retrieval, synthesis, and understanding, but remains challenging for semantically meaningful gestures whose communicative intent is not captured by motion alone. Direct contrastive alignment between transcripts and continuous motion embeddings often overemphasizes low-level kinematics and misses the symbolic content of semantic gestures. We propose semantic motion...
PHASOR: Phase-Anchored Universal Action Representations for Humanoid Embodiments
Announce Type: replace Abstract: Learning a good action embedding space is fundamental to scalable robot policy learning, yet existing methods treat action latents as task-specific intermediates rather than first-class representations. The resulting latents are unstructured, embodiment-specific, and weakly tied to motion semantics, limiting interpretability, controllability, and transferability across robots. We position the action embedding space itself as a first-class design target, with...
PHASOR: Phase-Anchored Universal Action Representations for Humanoid Embodiments
arXiv:2606.01851v1 Announce Type: new Abstract: Learning a good action embedding space is fundamental to scalable robot policy learning, yet existing methods treat action latents as task-specific intermediates rather than first-class representations. The resulting latents are unstructured, embodiment-specific, and weakly tied to motion semantics, limiting interpretability, controllability, and transferability across robots.
RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling
arXiv:2606.06309v1 Announce Type: new Abstract: Video generation models based on Diffusion Transformers (DiTs) have achieved remarkable performance in video synthesis, yet they suffer from high inference latency and computational costs due to the quadratic complexity of 3D attention. Existing acceleration methods primarily reduce computational complexity within each individual denoising steps through techniques such as sparse attention and KV-caching. However, they rigidly adhere to the...
Physics-Informed Video Generation via Mixture-of-Experts Latent Alignment
arXiv:2606.04737v1 Announce Type: new Abstract: Large-scale video generation models have made remarkable progress in semantic consistency and visual quality, producing videos that are increasingly coherent and visually convincing. Nevertheless, the dynamics induced by pixel-level fitting do not naturally accommodate the regularities that govern real-world motion and interaction, resulting in persistent shortcomings in physical plausibility. To address this limitation, we propose...
FlatVPR: Plug-and-play Geo-linear Residual Adapter for Geometric Rectification of Foundation Model Feature Manifolds
Announce Type: new Abstract: This paper proposes ``FlatVPR,'' a novel geometric rectification paradigm that effectively bridges the trade-off between map lightweightness and localization accuracy in visual place recognition (VPR) by enforcing a feature manifold structure where any descriptor between two adjacent anchors $\mathbf{z}_A$ and $\mathbf{z}_B$ can be accurately reconstructed via linear interpolation $\hat{\mathbf{z}}_{pseudo} = (1-t)\mathbf{z}_A + t\mathbf{z}_B$, where $t \in...
AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation
arXiv:2602.04672v4 Announce Type: replace Abstract: Reconstructing dynamic hand-object interactions from monocular videos is critical for dexterous manipulation data collection and creating realistic digital twins for robotics and VR. However, current methods face two prohibitive barriers: (1) reliance on neural rendering often yields fragmented, non-simulation-ready geometries under heavy occlusion, and (2) dependence on brittle Structure-from-Motion (SfM) initialization leads to frequent...