Call for Papers
We invite submissions on novel methodologies for LBQNNs, and their application to all important problems in computer vision. Topics of interest include but not limited to:
New methodologies (optimization and objective functions), and architectures for training quantized networks, including binary/ternary neural networks and low-bit networks.
Neural architecture search (NAS) or mixed-precision configuration search for LBQNNs.
Novel optimizer design for quantization.
LBQNNs for practical computer vision tasks: image classification, semantic, instance and panoptic segmentation, pose estimation, object detection, 3D and video recognition.
LBQNNs for generative models: GANs, VAEs, Diffusion model, etc.
LBQNNs for vision language models.
Hardware implementation and on-device deployment of LBQNNs.
LBQNNs in the wild: the real-world challenges and solutions for adopting low-bit quantization.
Submission Guidelines
Submissions have to be novel contributions covering any topic listed above. We don’t accept work that has been already published, that is concurrently submitted to other venues before the submission deadline, or that is presented at the main ICCV conference. We solicit submission of full papers, position papers, and papers describing open problems on one of the topics listed above. Papers must be submitted through the submission site on CMT. Papers submitted to the workshop can be submitted to future conferences if the acceptance notification comes after the workshop date.
Regular papers: Submissions must follow the ICCV anonymized paper format should adhere to ICCV submission guidelines, and they are limited to a maximum of 8 pages, excluding references. Shorter papers are welcome. They will undergo double-blind peer review. Authors may append to the paper supplementary material, such as appendices, proofs, and derivations; Like submissions, supplementary material must be anonymized. Looking at supplementary material is at the discretion of the reviewers.
Extended abstracts (NEW!): We encourage the submission of extended abstracts (2 pages plus references) that summarize previously published or unpublished work. Extended abstracts will undergo a light single-blind review process. Format for extended abstract shall also follow ICCV submission guidelines.
Previously published work: We welcome previously published papers from previous CV/ML conferences including CVPR 2021 which are within the scope of the workshop.
Unpublished work: We also encourage the submission of papers that summarize work in-progress. The idea of this type of submission is the dissemination of preliminary results or methods that fall within the overall scope of the workshop.
FAQ
Question: Will the paper included in ICCV proceedings?
Answer: No, the paper will NOT be included in ICCV proceedings and the paper published in the workshop can be submitted to future conferences. The accepted papers will be released on the workshop website.
Important Dates
All times below are due by 23:59 PM PST
Submission opens: Now
Regular paper submission due: Extended to August 14, 2023 (August 1, 2023)
Regular paper decisions: September 5, 2023
Camera ready paper due: September 12, 2023
(new) Extended abstract submission due: September 7, 2023
(new) Extended abstract decisions: September 21, 2023
Workshop date: October 2, 2023