-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Review Kinship Verification SOTA #25
Comments
De The 5th Recognizing Families in the Wild Data Challenge: Predicting Kinship from Faces, temos onde Podemos ver que TeamCNU, à frente do vuvko, é o melhor. Seu resultado é o mesmo que citei no comentário anterior. Abaixo colo a referência X. Zhang, M. Xu, X. Zhou, and G. Guo. Supervised contrastive learning for facial kinship recognition. In Conference on Automatic Face and Gesture Recognition (FG), 2021. |
Supervised Contrastive Learning for Facial Kinship Recognition Não consegui o PDF, mas encontrei o repositório. Implementado em PyTorch! |
A survey on kinship verification (Wang et al, 2023) |
@tfvieira, parece bastante promissor para responder nossa RQ. |
Deep learning-based methods show good performance in solving extrinsic challenges. One of the extrinsic challenges lies in that ”Kinship verification databases are born with unbalanced data” [117]. A kinship dataset of N pairs of positive samples contains N(N - 1) potential negative pairs leading to a large unbalance. However, most of the current methods only use N negative pairs. No caso do SOTA, temos, na verdade, 2 * ( |
|
|
Via ChatGPT, fiz um brainstorming de perguntas de pesquisa para usarmos. A nossa atual pergunta reflete as perguntas nos itens 1 e 3. In the domain of kinship recognition within computer vision, there are numerous intriguing research questions that can drive forward the understanding and technological advancements in this field. Here are a few research questions that could form the basis of impactful studies: 1. Algorithmic Performance Across Different Kin Relationships:
2. Cross-Cultural and Cross-Racial Efficacy:
3. Temporal Dynamics in Kinship Recognition:
4. Influence of Environmental and Contextual Factors:
5. Advanced Feature Extraction Techniques:
6. Integration of Multimodal Data:
7. Ethical and Privacy Implications:
8. Comparison with Human Perception:
These research questions not only aim to push the technological boundaries of kinship recognition but also address the critical ethical, privacy, and societal concerns associated with this technology. Addressing these questions could lead to significant advancements in the field, contributing to more accurate, fair, and responsible kinship recognition systems. |
The text was updated successfully, but these errors were encountered: