• Alexander Robey (University of Pennsylvania)
• Chengzhi Mao (Columbia University)
• Dingcheng Yang (Tsinghua University)
• Emily Diana (University of Pennsylvania)
• Gaurang Sriramanan (University of Maryland, College Park)
• Hanxun Huang (The University of Melbourne)
• Haoxuanye Ji (Xi'an JiaoTong University)
• Jiachen Sun (University of Michigan)
• Julia Grabinski (University Siegen)
• Junyang Wu (Shanghai Jiao Tong university)
• Kibok Lee (Yonsei University)
• Muzammal Naseer (MBZUAI)
• Pengliang Ji (Beihang University)
• Peter Lorenz (Fraunhofer)
• Qihao Liu (Johns Hopkins University)
• Sahil Verma (University of Washington)
• Salah GHAMIZI (University of Luxembourg)
• ShengYun Peng (Georgia Institute of Technology)
• Simin Li (Beihang University)
• Won Park (Aura)
• Wufei Ma (Johns Hopkins University)
• Xianhang Li (University of California, Santa Cruz)
• Xinyu Zhang (Zhejiang University)
• Yulong Cao (University of Michigan, Ann Arbor )
• Zihao Xiao (Johns Hopkins University)
• Ziqi Zhang (Google)

Please follow the ICCV2023 author policies, as well as the ICCV2023 submission guidelines. It is also suggested to check the ICCV2023 Author FAQs. We accept two types of submissions, i.e., long papers and extended abstracts.

Long papers in the AROW workshop will be published by IEEE/CVF. The following guidelines must be respected:

• There will be a transfer of copyright to IEEE/CVF. The papers will then be available in paid form from IEEE or free of charge on the CVF website. The papers will not appear in individual proceedings for each workshop, but under the generic title "ICCV23 Workshops".
• The list of papers accepted for the workshops must be provided by August 07, 2023 and the authors must submit the final version of their papers by August 21, 2023 on an IEEE platform, if publishing with IEEE; the platform will be informed later before the deadline.
• The maximum number of pages for submissions is eight (excluding the references). Overlength papers will be desk-rejected without review. The papers should not exceed 5MB in size and the ICCV template [iccv2023AuthorKit.zip] is required. An example submission paper with detailed instructions can be found in this PDF.
• Each published paper must have at least one author registered for the workshop under an AUTHOR registration; Virtual Registrations will not cover paper submissions.
• The deadline for supplementary material (if applicable) is the same as the paper submission deadline.
• All submissions should be anonymized. The reviewing process is double-blind.

We also accept extended abstracts. Note, different from the long papers:

• Papers are limited to four pages excluding references.
• Extended abstracts will NOT be included in the official ICCV proceedings.

1. Invited talk

   Each workshop room will be equipped with A/V systems for presentation, including a HDMI cable to connect one machine (speaker's PC or Mac), 2 microphones on the podium, 2 wireless microphones, and video projectors. The aspect ratio of the screen will be 16:9. Please encourage presenters to attend the workshop in person and communicate with participants at the venue. If the presenters are not able to attend in person, remote presentation is also allowed. In this case, no registration is needed for invited speakers. Note, however, that remote presenters with IEEE/CVF workshop papers must have (at least one-day) workshops/tutorials pass registration. Please check out the authors note on the registration page: https://iccv2023.thecvf.com/registration-81.php

2. Poster presentation (95.4 cm x 138.8 cm, portrait format)

   Workshop poster sessions will be held in each workshop room, and poster panels will be provided and arranged inside the room. Note that the poster size for workshops is different from that for the main conference. The workshop poster panel size will be 95.4 cm x 138.8 cm (WxH, aspect ratio 0.69:1, portrait format). A0 paper in portrait would well fit the panel by some margin. Please make sure to notify this information to the workshop poster presenters. There will be an on-site printing service from which you can collect your printed poster. You will receive more information about the on-site printing service in a separate email later.

3. Workshop streaming

   If you plan to live-stream your workshop, a Wi-Fi network enough for streaming will be provided for each workshop room. However, we do not provide technical support for workshop streaming, and thus streaming of workshops should be managed by each organizer.

4. Workshop Rooms

   The workshop rooms are already announced on the ICCV webpage.

   We have updated some initial room assignments based on the registration survey, so please double-check your room code, although you have done it before.

   Each room of East or West, whose code starts with E or W, accommodates 160~190 seats. It will be equipped with A/V systems, including an HDMI cable to connect one machine (speaker's PC or Mac), 2 microphones on the podium, 2 wireless microphones, and video projectors (8K lumens). The screen's aspect ratio will be 16:9. One technician is assigned to two rooms to help you set up A/V systems.

   Each room of South, whose code starts with S, has 570 seats. It will also be equipped with A/V systems, including an HDMI cable to connect one machine (speaker's PC or Mac), 2 microphones on the podium, 4 wireless microphones, and video projectors (12K lumens). The screen's aspect ratio will be 16:9. One technician is assigned to help you set up A/V systems.

   Some workshops are assigned to the plenary room P01, the largest room, which will be provided with better equipment than the South rooms. Note that the number of seats in each room may decrease to get space for poster panels.

• Adversarial Examples with Specular Highlights

  Vanshika Vats (University of California Santa Cruz, IIIT Delhi)*; Koteswar Rao Jerripothula (IIIT Delhi)

• IPCert: Provably Robust Intellectual Property Protection for Machine Learning

  Zhengyuan Jiang (Duke university)*; Minghong Fang (The Ohio State University); Neil Zhenqiang Gong (Duke University)

• Fair Robust Active Learning by Joint Inconsistency

  Tsung-Han Wu (National Taiwan University)*; Hung-Ting Su (National Taiwan University); Shang-Tse Chen (National Taiwan University); Winston H. Hsu (National Taiwan University)

• Classification robustness to common optical aberrations

  Patrick Müller (University of Siegen)*; Alexander Braun (University of Applied Sciences Düsseldorf); Margret Keuper (University of Siegen, Max Planck Institute for Informatics)

• Defense-Prefix for Preventing Typographic Attacks on CLIP Best Paper Award

  Hiroki Azuma (The University of Tokyo)*; Yusuke Matsui (The University of Tokyo)

• Efficient Combination of Deep Learning Models for Caption Enrichment

  Hidetomo Sakaino (Weathernews Inc.)*; Nguyen X Nam (Bunbu); Bach Hoang Nguyen (Bunbusoft)

• PRAT: PRofiling Adversarial aTtacks

  rahul ambati (University of Central Florida)*; Naveed Akhtar (The University of Western Australia); Yogesh Rawat (University of Central Florida); Ajmal Mian (University of Western Australia)

• On the Adversarial Robustness of Multi-Modal Foundation Models

  Christian Schlarmann (University of Tübingen)*; Matthias Hein (University of Tübingen)

• BLACK-BOX ATTACKS ON IMAGE ACTIVITY PREDICTION AND ITS NATURAL LANGUAGE EXPLANATIONS

  Alina Elena Baia (Idiap Research Institute)*; Valentina Poggioni (University of Perugia); ANDREA CAVALLARO (Queen Mary University of London, UK)

• OMG-ATTACK: Self-Supervised On-Manifold Generation of Transferable Evasion Attacks

  Ofir Bar Tal (TAU); Adi Haviv (Tel Aviv University)*; Amit H Bermano (Tel-Aviv University)

• On the unreasonable vulnerability of transformers for image restoration and an easy fix

  Shashank Agnihotri (University of Siegen)*; Kanchana Vaishnavi Gandikota (University of Siegen); Julia Grabinski (University of Siegen); Paramanand Chandramouli (University of Siegen); Margret Keuper (University of Siegen, Max Planck Institute for Informatics)

• Targeted Adversarial Attacks on Generalizable Neural Radiance Fields

  Andras Horvath (Peter Pazmany Catholic University)*; Csaba Jozsa (Nokia Bell Labs)

• FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks PDF

  Hunmin Yang (KAIST)*; Jongoh Jeong (KAIST); Kuk-Jin Yoon (KAIST)

• Generalizability of Adversarial Robustness Under Distribution Shifts PDF

  Kumail Alhamoud (KAUST)*; Hasan Abed Al Kader Hammoud (King Abdullah University of Science and Technology ); Motasem Alfarra (KAUST); Bernard Ghanem (KAUST)

• Towards the Adversarial Robustness of Vision-Language Model with Chain-of-Thought Reasoning PDF

  Zefeng Wang (TUM); Zhen Han (LMU Munich); Jindong Gu (University of Oxford)*; Shuo Chen (LMU Munich); Volker Tresp (LMU)

• Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks PDF

  Tianrui Qin (SIAT); Xitong Gao (Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences)*; juanjuan zhao (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences); Kejiang Ye (Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences); Cheng-Zhong Xu (University of Macau)

• Adversarial Bayesian Augmentation for Single-Source Domain Generalization PDF

  Sheng Cheng (Arizona State University)*; Tejas Gokhale (Arizona State University); Yezhou Yang (Arizona State University)

• Weakly-supervised detection of diffusion-based image manipulations PDF Best Paper Award

  Elisabeta Oneata (Bitdefender)*; Dan Oneata (Politehnica University of Bucharest); Dragos Tantaru (Bitdefender)