Fourteenth International Workshop on Assistive Computer Vision and Robotics

8th September 2026 - AM, Malmö (Sweden)

Important: All accepted papers must be covered by a full registration by August 10; otherwise, they will not be included in the proceedings.

The workshop will be held in TBD.

Program

09:00 Opening Remarks
09:05 Keynote 1 - KATERINA FRAGKIADAKI - Human-Robot Interaction and Collaboration through Sim-to-Real Learning and Guided Generative Planning
09:35 ORAL SESSION 1
10:05 Abstracts
10:35 POSTER SESSION AND COFFEE BREAK
11:30 Keynote 2 - DIMA DAMEN - What do we need to model about the human to be truly assistive?
12:00 ORAL SESSION 2
12:30 Doctoral Consortium
13:00 Closing Remarks

Oral Session 1* (8 minutes presentation + 2 minutes Q&A)

  • Zeno Testa*. SLU-2K: A Question-Based Benchmark for Semantic Evaluation of Sign Language Translation
  • Sergei Kurashkin*. Do VLMs See What Blind Users Show Them? A Distribution-Shift and Evaluation-Protocol Audit on VizWiz
  • Francesco Agnelli*. Forecasting 3D Hand Motion with Spatial and Frequency Anisotropic Residual Diffusion

Abstracts* (6 minutes presentation + 2 minutes Q&A)

  • Elena Camuffo*. MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment
  • Tymofii Matiichyk*. Occupancy detection as a mechanism for avoiding unsafe or misaligned interventions
  • Prodromos Boutis*. Controller-Free Mixed Reality Teleoperation with Integrated Depth Assistance, Proportional Motion Calibration, and Reinforcement Learning for Confined-Space Robot Manipulation
  • Vivek Chavan*. A Framework for Egocentric and Exocentric Procedural Understanding via Temporal Segmentation and Semantic Abstraction

Poster Session

Poster size: see here: https://iccv.thecvf.com/Conferences/2026/PosterPrinting

The poster session will be held in Exhall II. Authors should use the poster boards corresponding to the assigned poster numbers below.

# Paper
5 Georgina Nuthall. EmPath: Follower-Aware Local Path Planning for Robot-Assisted Navigation of Blind and Visually Impaired Users
9 Xiao Wang. MistyPilot: Enabling Social-Robot Control through Multi-Agent LLM Skill Orchestration
13 Sergei Kurashkin. Do VLMs See What Blind Users Show Them? A Distribution-Shift and Evaluation-Protocol Audit on VizWiz
14 Justine Buss. Open-Vocabulary Annotation for Pedestrian Scene Understanding under Domain Shift
17 Gomer Otterspeer. Keypoints Optional: A Frozen V-JEPA Backbone for Sign Segmentation
18 Julia Tomas-Barba. Language-Conditioned Object Highlighting for Simulated Prosthetic Vision
20 Mikołaj Klimek. Visual Fall Detection from a Mobile Quadruped Robot in Uncontrolled Environments
22 Alessia Saggese. EYE: Enhanced YOLO for Empty-shelf detection
24 Tuğçe Kızıltepe. ODE-Based Transformer Decoders for Iterative Sign Language Translation
26 Francesco Agnelli. Forecasting 3D Hand Motion with Spatial and Frequency Anisotropic Residual Diffusion
27 Zeno Testa. SLU-2K: A Question-Based Benchmark for Semantic Evaluation of Sign Language Translation

Oral Session 2* (8 minutes presentation + 2 minutes Q&A)

  • Julia Tomas-Barba*. Language-Conditioned Object Highlighting for Simulated Prosthetic Vision
  • Xiao Wang*. MistyPilot: Enabling Social-Robot Control through Multi-Agent LLM Skill Orchestration
  • Georgina Nuthall*. EmPath: Follower-Aware Local Path Planning for Robot-Assisted Navigation of Blind and Visually Impaired Users

Doctoral Consortium* (10 minutes presentation including questions)

  • Andreas Kriegler. Synthetic Data and Generic Representations for Open World 6D Object Pose Estimation
  • Alexandre Symeonidis-Herzig. Photorealistic Sign Language Production with Non-Manual Features
  • Zhanyu Tuo. RPGD: RANSAC-P3P Gradient Descent for Extrinsic Calibration in 3D Human Pose Estimation

All papers that will be presented as oral/abstract/doctoral will also be presented as poster