Call for Papers

 We are pleased to invite paper submissions and challenge
 participation for the 
Multi-Faceted Analysis for Video Understanding  (MAVU) Workshop
 at WACV 2027.

MAVU will bring together researchers working on video understanding
across aerial/drone, surveillance, and egocentric perspectives. Topics
include long-video understanding and reasoning, video question
answering, multimodal reasoning, video retrieval and forensic search,
drone and aerial video analysis, surveillance video understanding,
human action recognition and crowd analysis, egocentric vision, aerial
perception, and efficient video models for UAVs and edge devices.

WORKSHOP INFORMATION
Date: January 4 or 5, 2027 (full-day workshop)
Location: WACV 2027, Disney Springs, Buena Vista, Florida, USA
Paper submission deadline: October 20, 2026, 11:59 p.m. PST
Decision notification: October 30, 2026
Camera-ready submission deadline: November 20, 2026, 11:59 p.m. PST

We welcome short papers of up to 4 pages, including references, and
full papers of up to 8 pages, excluding references. Submissions should
follow the WACV main conference format. Accepted full papers will be
included in the WACV proceedings.

Workshop website:
https://zyaocoder.github.io/MAVU-workshop-2027/

OpenReview submission portal:
https://openreview.net/group?id=thecvf.com/WACV/2027/Workshop/MAVU

Please note that all authors must have an OpenReview profile. 
AI CHALLENGE: VIDEO QUESTION ANSWERING ON DRONE VIDEOS

The MAVU Workshop will also host an AI challenge on Video Question
Answering for drone videos. The challenge is designed to benchmark
advances in video understanding, spatiotemporal reasoning, and remote
sensing.

Given a drone video and a natural-language, multiple-choice question,
participants must predict the correct answer. The questions require
models to understand objects, scenes, events, spatial relationships,
and temporal changes across video frames.

Challenge highlights:

    4,000 question-answer pairs from 1,014 drone videos
    Videos collected across 18 cities worldwide
    Average video length of approximately 15 seconds
    BIMBA as the baseline model
    Overall multiple-choice accuracy as the primary evaluation metric
    Additional accuracy reporting for individual reasoning tasks

Top-performing teams will be recognized during the MAVU
Workshop. Selected teams will also be invited to present their
solutions and findings at WACV 2027.

Codabench challenge platform:
https://www.codabench.org/competitions/18274/#/pages-tab

Challenge details:
https://zyaocoder.github.io/MAVU-workshop-2027/#challenge

We warmly invite researchers, students, and practitioners to submit
their work, participate in the challenge, and join us at WACV 2027.

WORKSHOP ORGANIZERS
Mooi Choo Chuah, Full Professor, Lehigh University
Chen Chen, Associate Professor, University of Central Florida
Shuai Zhang, Senior Staff Engineer, Qualcomm
Ning Bi, VP of Engineering, Qualcomm
Fatih Porikli, VP, Technology, Qualcomm
For questions, please contact:
mavu-wacv27-organizers@googlegroups.com
Best regards,
The MAVU 2027 Organizing Committee