由IEEE举办的计算机视觉和模式识别领域的顶级会议——CVPR（IEEE Conference on Computer Vision and Pattern Recognition）即将于6月开幕。

      国际计算机视觉与模式识别会议（CVPR）是IEEE一年一度的学术性会议，会议的主要内容是计算机视觉与模式识别技术。CVPR是世界顶级的计算机视觉会议（三大顶会之一，另外两个是ICCV和ECCV），同时也是在谷歌学术指标2022排名中总学科排名第4，是人工智能领域中是最具影响力的国际学术会议之一。近年来每年有约1500名参加者，收录的论文数量一般300篇左右。本会议每年都会有固定的研讨主题，而每一年都会有公司赞助该会议并获得在会场展示的机会。

      本届会议期间，由暨南大学广东智慧教育研究院发起的“CVPR2023研讨会@视觉语言推理前沿：关于组合性，提示性与因果性”将于6月18日正式举行。研讨会包含regular paper和long paper两个论文投稿区，Regular paper track接收上限为4页的短文章，适合对当前取得局部研究成果的工作进行宣传，接收后可以基于原文内容进行拓展投稿正会或期刊（截至日期4月10日）；而Long paper track接收上限为8页的文章，并允许提交附加材料（截至日期5月7日）。

      此外本次研讨会也开设了基于几何计算和证明问题背景下的两个跨模态推理挑战赛。 为避免线下验证时的几何题目验证数据泄露，推理挑战赛采用在线模型验证形式，参赛队伍需提交其代码和模型进行在线验证。另外由于比赛侧重于考察跨模态视觉语言模型本身的推理能力，因此严禁使用Wolfram等相关外挂科学计算软件进行辅助。

      论文投稿区现已开放，跨模态推理挑战赛将于近日开放，欢迎各位投稿和组织队伍参赛！官网详细资讯请见下方。

     Topics

     Call for Papers

    This workshop pays more attention to their limitations of existing notions on Compositionality, Prompts, and Causality. In the sense of visual language reasoning, compositionality demonstrates how human represents and organizes visual events for reasoning better; prompt-based methods build a cross-modal bridge to leverage a large language model for reasoning on new visual concepts in a vocabulary; and causality prevents the chain of reasoning from spurious features and other confounding factors. They are very important whereas have seldom been investigated together and worked out in VLPs, covering a non-exhaustive list of topics such as:

Large-scale visual-language pretraining (VLP) models, visual-language representation learning and reasoning (VLR) (Especially, how VLP and VLR are connected with compositionality, prompts and causality);

Causal inference theory, algorithms and models applied for vision, language, and vision-language area;

Prompt engineering, tuning and other prompting methods for vision, language, and vision-language area;

Compositional representation learning for vision, language, and vision-language area;

The relationships and interplay among compositionality, prompts and causality;

New benchmarks that evaluate vision-language reasoning in terms of compositionality and causality

Our submission includes the regular-paper track and the long-paper track. CVPR officially does not allow regular workshop papers with more than 4 pages. To this end, our long-paper accepts the submitted manuscripts with more than 4 pages, and supplementary materials are also allowed in the long-paper track. Regular papers are submitted via the CMT paper submission website,

Regular-paper track: https://cmt3.research.microsoft.com/NFVLR202

        Long-paper track: Release after regular-paper track deadline.

      Long papers are submitted via the openreview system. Note that, only regular papers would be selected to publish in IEEE Xplore and the CVF open-access archive.

Geometric-MPS Challenge

Geometry math-word problem solving (MPS) is a classic cross-modal reasoning problem composed of text and diagram input, promoting challenging multi-modal numerical reasoning tasks. Our workshop challenge includes two competition tracks about solving plane-geometriy MPS problems based on calculation and proving tasks. It encourages the community to develop reasoning algorithms for geometry MPS problems. To this, the challenge does not encourage the usage of gigantic large language pre-training systems and particulary, forbid the implementation of Wolfram and other comparable softwares. For a fairly evaluating the reasoning abilities across all candidates, we only release the train and val datasets for the compeitions, and our test dataset would be kept under wrap in the online evaluation server until the challenge finished. The codes and pre-trained candidate models should be submitted and evaluated online by our evaluation server.

Our competition website is coming with our online evaluation service and more details, would be avaiable in the next week.

研讨会主页见：https://nfvlr-workshop.github.io/