The study presents a vision‑language model pipeline that estimates dynamic, triaxial, bilateral external hand forces during manual material handling tasks using only RGB video and known box mass. By combining text‑guided ROI localization, pretrained vision‑transformer features, and transformer‑based temporal regression, the model achieved root mean square errors of about 4.7–5.6 N for horizontal and mediolateral forces and 10.6–11.0 N for vertical forces across various camera setups. The approach demonstrated that including the handled object as a second ROI and using multi‑camera capture improved peak‑force estimation, showing the feasibility of sensor‑free force estimation for occupational exposure assessment.
By Mohammad Sadra Rajabi, Aanuoluwapo Ojelade, Sunwook Kim, Maury A. Nussbaum
arXiv:2606. 28104v1 Announce Type: cross Abstract: Vision-based assessment can provide convenient and cost-effective evaluation in Traditional Chinese Medicine (TCM) rehabilitation training, where action quality assessment (AQA) from computer vision offers a promising solution.
By Francis Xiatian Zhang, Hao Yao, Shengxuan Chen, Hong Zhu, Hongxiao Jia, Sisi Zheng, Hubert P. H. Shum
Estimating physical pressure from vision is essential for understanding contact-rich hand-object interaction. However, prior vision-based pressure estimation methods are largely limited to planar surfaces and single image input, making them difficult to apply to dynamic hand-object interaction with diverse objects.
arXiv:2608.16081v2 Announce Type: replace
Abstract: Open-weight and frontier vision-language models (VLMs) perform well on general image understanding, but their ability to interpret fine-grained han...
By Taegang Kim, Saleh Afroogh, Junfeng Jiao
Universal Manipulation Interface (UMI) enables scalable real-world robot data collection without hardware-specific teleoperation, yet leveraging UMI data to train large-scale Vision-Language-Action (VLA) models remains fundamentally challenging. We identify two critical mismatches: wrist-mounted fisheye views, with severe radial distortion and local gripper-centric perspectives, are out-of-distribution for pretrained VLMs; and human-collected trajectories frequently violate kinematic limits, incur collisions, or exceed controller bandwidth, teaching VLA policies physically infeasible actions.
arXiv:2608.13014v2 Announce Type: replace
Abstract: Understanding hand-object interaction from egocentric vision is essential for modeling how people physically engage with the surrounding world. Yet...
By Andela Ilic, Rachel Schuchert, Yijing Jiang, Christian Holz
arXiv:2511. 20615v2 Announce Type: replace-cross Abstract: This study aimed to explore the application of deep neural networks for whole-body human posture prediction during dynamic load-reaching activities.
By Seyede Niloofar Hosseini, Ali Mojibi, Mahdi Mohseni, Navid Arjmand, Alireza Taheri
arXiv:2606. 04708v1 Announce Type: cross Abstract: Universal Manipulation Interface (UMI) enables scalable real-world robot data collection without hardware-specific teleoperation, yet leveraging UMI data to train large-scale Vision-Language-Action (VLA) models remains fundamentally challenging.
By Siyuan Yang, Linzheng Guo, Ouyang Lu, Zhaxizhuoma, Daoran Zhang, Xinmiao Wang, Ting Xiao, Fangzheng Yan, Zhijun Chen, Yan Ding, Chao Yu, Chenjia Bai, Xuelong Li
TouchSight is a monocular egocentric vision framework that predicts dense full-hand contact forces from video. It uses 500 hours of pressure‑glove recordings and hand‑object interaction data, and introduces TwinTouch‑20H, a dataset of 20 hours of paired visual data where generative models render gloved recordings as bare‑hand observations while preserving tactile labels. The system outperforms prior methods on OakInk2, generalizes qualitatively to natural bare‑hand egocentric videos from unseen datasets, and improves consistently as glove supervision scales.
By Danyan Zhou, Jinxuan Lu, Jiawei Lin, Tianxing Chen, Chuqiao Lyu, Wenbo Ding
TouchSight is a monocular egocentric vision framework that predicts dense full-hand contact forces without tactile sensors. It uses 500 hours of pressure-glove data and a 20-hour TwinTouch-20H dataset where generative models render gloved recordings as bare-hand videos, bridging the appearance gap. The system outperforms previous methods on OakInk2, generalizes to unseen natural bare-hand egocentric videos, and improves as glove supervision increases.
EventEgoHands++ is a new framework for reconstructing 3D hand meshes from egocentric event-based cameras. It introduces a Hand Detector that provides instance-level bounding boxes and masks for left and right hands, and an Adaptive Attention module that uses these detections to model spatial relationships and interactions. The authors extend the synthetic N-HOT3D dataset and create EEH‑R, a large real-world event-based egocentric hand dataset with about 1 million annotated frames, and show that their method outperforms existing baselines on both synthetic and real data.
By Ryosei Hara, Wataru Ikeda, Masashi Hatano, Mariko Isogawa
arXiv:2606. 12988v1 Announce Type: cross Abstract: This paper introduces a new methodology for real-time prediction of ergonomic and non-ergonomic human poses using volumetric video data in three dimensions.
By Manex Atxa, Bruno Simoes, Julen Balzategui