arXiv:2606. 09390v1 Announce Type: cross Abstract: Body movement communicates intent at distances and in conditions where neither the face, nor speech can be captured.
arXiv:2608. 20114v1 Announce Type: new Abstract: Mobile manipulation requires a robot to predict how locomotion and arm motion jointly alter future observations and control.
Motion-Omni is an end‑to‑end framework that jointly generates spoken dialogue and full‑body motion, producing speech, facial expressions, and hand, upper‑body, and lower‑body movements directly from the hidden states of a language model. The system requires joint training of the language model, speech generator, and motion generator to maintain audio‑motion alignment, and it is supervised using a scalable, model‑agnostic pipeline that pseudo‑labels 422,856 speech‑motion pairs. With a Qwen2.5‑7B‑Instruct backbone, Motion‑Omni‑Q7 achieves near‑cascade performance on motion metrics while being 5.4× faster, and it outperforms other non‑teacher cascades on beat correlation, diversity, and word error rate.
arXiv:2608. 05782v1 Announce Type: cross Abstract: Wearable human activity recognition (HAR) is often limited by the scarcity of labeled sensor data, especially in low-resource, class-imbalanced, and subject-generalization settings.
arXiv:2609.14118v1 Announce Type: cross Abstract: Online understanding of who is talking to the camera wearer is a key capability for egocentric social interaction. However, existing talk-to-me (TTM)...
Muscle activity is fundamental to human movement, and understanding its patterns is critical for injury prevention and rehabilitation. Conventional muscle activity monitoring relies on specialized sen...
arXiv:2505. 11146v3 Announce Type: replace-cross Abstract: Fine-grained facial expression transfer from humans to humanoid agents presents a unique pattern recognition challenge due to the significant domain gap between biological facial dynamics and mechanical control spaces.
arXiv:2606. 30266v1 Announce Type: cross Abstract: Motion-language agents must possess the bidirectional capability to both understand human movement (motion-to-text, M2T) and generate it from natural language (text-to-motion, T2M).
arXiv:2505. 11146v4 Announce Type: replace-cross Abstract: Fine-grained facial expression transfer from humans to humanoid agents presents a unique pattern recognition challenge due to the significant domain gap between biological facial dynamics and mechanical control spaces.
Online understanding of who is talking to the camera wearer is a key capability for egocentric social interaction. However, existing talk-to-me (TTM) studies are commonly formulated as offline clip-le...
Pose2Muscle is a pose-driven framework that estimates discrete muscle activity states without requiring surface electromyography (sEMG) during inference. It reformulates muscle estimation as a structured prediction problem, using multi-scale spatio-temporal attention and a directed acyclic graph-based decoder to capture motion patterns and maintain multiple candidate hypotheses. The authors introduce the PoseEMG-43 dataset, comprising 2,992 movement instances from 43 daily-life actions performed by 14 participants, and demonstrate that Pose2Muscle outperforms baseline methods with high accuracy and correlation metrics.
arXiv:2604. 00767v2 Announce Type: replace Abstract: Wearable human activity recognition (HAR) has made steady progress, yet much of this progress remains grounded in fixed-window, closed-set classification benchmarks.
SocioGesture is a real‑time, adaptive system for recognizing social gestures in human‑robot interaction. It employs a compact, confidence‑aware body‑hand skeleton representation and a lightweight dual‑stream model that fuses body motion with hand articulation, enabling low‑latency onboard recognition. The model is trained with occlusion‑aware skeleton corruption to handle missing hands, occluded arms, and unstable keypoints, and it can expand its gesture vocabulary during deployment by saving uncertain interaction segments for offline labeling.