``` HCMIW@ECCV2026 | Human-Centered Multimodal Intelligence in the Wild
ECCV 2026 Workshop

The 1st Workshop on
Human-Centered Multimodal Intelligence in the Wild

Foundation models and beyond for human-centered multimodal perception, reasoning, and real-world deployment

Date: September 8, 2026 · Afternoon
Location: Malmö, Sweden
In Room: Quality View Oresundssalen - 1

Overview

The emergence of multimodal foundation models (MLLMs) has catalyzed a paradigm shift in human-centered vision. While traditional systems often struggle with the open-world complexity of human behavior, the integration of large-scale pre-training with cross-modal reasoning offers paths toward truly adaptive intelligence. This workshop addresses the critical transition from constrained benchmarks to in-the-wild deployment, where visual intelligence must navigate the ambiguity of human intent and the noise of unstructured environments.

The Human-Centered Multimodal Intelligence in the Wild (HCMIW) workshop bridges the gap between theoretical MLLMs and practical, human-aligned applications. We focus on the synergy between robust perception and sophisticated reasoning, aiming to redefine how vision systems interpret human presence across heterogeneous sensors and dynamic contexts.

To address these challenges, HCMIW invites contributions across five critical axes:

  • MLLMs for Human-Centric Tasks: Novel paradigms for detection, tracking, and activity understanding, with emphasis on efficient adaptation and from-scratch training tailored for real-world constraints.
  • Perception in Adverse Conditions: Advancing robustness against in-the-wild variables, including extreme lighting, rapid motion, severe occlusions, and complex human-object interactions.
  • Heterogeneous Sensor Fusion: Beyond RGB—leveraging infrared, event-based cameras, LiDAR, and thermal sensing to build multi-spectral understanding of human activity.
  • Generalization & Domain Transfer: Strategies for bridging the gap between massive general-purpose datasets and specialized, high-stakes human-centric domains.
  • Next-Generation Benchmarking: Developing wild-first datasets and evaluation metrics that prioritize human-facing performance, safety, and reliability over static accuracy.

News and Updates

  • NEW Sep 7, 2026: Online participation is available via Zoom. View meeting details →
  • Aug 27, 2026: Proceedings submission due.
  • Jul 14, 2026: Camera ready due.
  • Jul 06, 2026: Decision notification has been released to authors.
  • Jun 24, 2026: We have extended the submission deadline to Jul 15, 2026, 23:59 GMT+2.
  • Jun 01, 2026: Paper submission is open at OpenReview.

Topics of Interest

We welcome submissions and discussions related to, but not limited to, the following themes:

  • Foundation models for human-centric perception, understanding, and reasoning.
  • Multimodal learning for human behavior understanding, interaction analysis, and activity recognition.
  • Perception in adverse conditions, including low light, occlusion, motion blur, and sensor noise.
  • Cross-modal grounding across RGB, thermal, infrared, depth, event cameras, LiDAR, and audio.
  • Generalization, adaptation, robustness, and reliability in real-world human-centered systems.
  • Benchmarks, datasets, evaluation protocols, and deployment-oriented analysis for in-the-wild scenarios.

Invited Speakers

Program

This is the program for our workshop. All event times shown in the schedule are local time in Malmö, Sweden.

Date: September 8, 2026
Room: Quality View Oresundssalen - 1

Online Participation

Zoom Meeting: ECCV2026-HCMIW

Date & Time: September 8, 2026, 14:00 (Stockholm Time)

Join the Zoom Meeting:
Join Zoom Meeting

Meeting Chat:
Open Zoom Meeting Chat

Meeting ID: 723 3872 9838
Passcode: 2SHFkp

Join via SIP:
72338729838@zoomcrc.com

Tentative Schedule

September 8, 2026 · Afternoon Session

14:00–14:10
Opening Remarks
14:10–14:40
Keynote 1 — Invited Speaker #1
14:40–15:10
Keynote 2 — Invited Speaker #2
15:10–16:10
Coffee Break & Poster Session
16:10–16:40
Keynote 3 — Invited Speaker #3
16:40–16:55
Contributed Talk
16:55–17:05
Closing Remarks

Call for Papers

Important Dates

Paper submission deadline: Jul 01, 2026, 23:59 GMT+2Jul 15, 2026, 23:59 GMT+2
Notification to authors: Aug 01, 2026, 23:59 GMT+2
Camera-ready deadline: Aug 14, 2026, 23:59 GMT+8

Submission Instructions

We are following the ECCV paper format: ECCV 2026 Author Guidelines.

LaTeX/Word templates: ECCV 2026 Paper Template.

Submitted papers must be between 4 and 14 pages, excluding references. Papers outside this range will not be accepted by Springer for publication. Submissions should follow the ECCV paper style guide and present mature work with full experiments and analyses supporting the proposed ideas.

The page limit includes figures and tables in the ECCV style. A paper should be submitted using the above templates. The length should match that intended for final publication.

Blind review: We adopt double-blind review for this workshop. Submitted papers and supplementary materials should not reveal any information about the author.

Dual submission: We do not accept paper submissions that have been published, including at the ECCV main conference, or are under review for other conferences or workshops. Accepted papers are expected to be published in ECCV proceedings.

Submission Website

Submission site: https://openreview.net/group?id=thecvf.com/ECCV/2026/Workshop/HCMIW

Organizers

```