Overview

Welcome to our DexHAND@ECCV26.

We are very happy to organize DexHAND workshop. This year's workshop will be held at ECCV26. See you in Malmö, Sweden.

During this workshop, we will focus on hands—including visual hands (e.g., hand perception, pose estimation) and dexterous hands (e.g., robotic manipulation, control), with a special focus on how visual hands enable and enhance fine-grained dexterous hand control, action, and manipulation . Specifically, vision could provide the essential perception capabilities by observing, and enable learning by mimicking human hands for accurate dexterous hand acting with objects. Observing and acting as dexterous hands could drive innovation in real-time perception, 3D vision, video analysis, and embodied AI, establishing dexterous hand manipulation as a key domain for testing and generalizing computer vision technologies. We will explore hands in the context of VLA models and world models through the talks of invited speakers, the presentation of accepted papers, and workshop challenges.

During the workshop, we will explore multimodal LLMs for hand-related tasks through the talks of invited speakers, the presentation of accepted papers, and workshop challenges.

Invited Speakers

TBD

Schedule

TBD

Call for Papers

Important Dates

2026/05/22	Paper Submission Start
2026/07/15 23:59 in GMT	Full Length Paper and its Supplementary Materials Submission Deadline
2026/08/03	Full Length Paper Author Notification
2026/08/10 23:59 in GMT	Full Length Paper Camera-ready Submission Deadline
2026/08/21 23:59 in GMT	Extended Abstracts & Posters Submission Deadline
2026/08/25	Extended Abstracts & Posters Submission Notification
2026/09/01 23:59 in GMT	Extended Abstracts & Posters Camera-ready Submission Deadline

Topics

We will cover all hand-related topics. The relevant topics include and not limited to:

• Hand pose and shape estimation
• Hand modeling, rendering, generation
• Hand detection/segmentation
• Hand gesture/action recognition
• Hand/object interactions
• Robotic grasping and manipulation
• Multimodal sensor (e.g.,, vision, tactile and language) fusion for hand
• Hand motion planning and control
• Vision-Language-Action (VLA) models for dexterous hands
• World models with hand
• Self-/un-/weakly-supervised learning
• Generalization and adaptation
• Egocentric vision for hand

Submission Guidelines

Full Length Paper Submission Website: OpenReview

Extended Abstracts and Posters Submission Website: OpenReview Non-Proceedings

We accept full length papers, extended abstracts and posters in our workshop. The full length submissions should be anonymized and will be one-round peer reviewed. The accepted full length papers will be included in the ECCV2026 conference proceedings, while others will only be presented in the workshop. We welcome papers that are accepted to the ECCV2026 main conference or previous conferences, and extended abstracts that in progress, to show the posters in our workshop.

Call for full length papers

Full length submissions should follow ECCV 2026 Submissions Policies (no more than 14 pages) and use the official ECCV 2026 template. Note that the submissions violate the double-blind policy or the dual-submission policy will be rejected without review.

Call for extended abstracts and posters

Extended abstracts are not subject to the ECCV rules, and can use other templates. They should be shorter than the equivalent of 4 pages in CVPR template format. Note that extended abstracts are not anonymized, and will not be peer reviewed. Accepted extended abstracts will only publish on our website, show in our workshop and not appear in the ECCV26 conference proceedings. Posters can be simply submitted with PDF and their brief information like paper title, authors and conference name.

Organizers