مورد إلكتروني
TextANIMAR: Text-based 3D Animal Fine-Grained Retrieval
العنوان: | TextANIMAR: Text-based 3D Animal Fine-Grained Retrieval |
---|---|
بيانات النشر: | 2023-04-12 |
تفاصيل مُضافة: | Le, Trung-Nghia c, Tam V. Nguyen Le, Minh-Quan Nguyen, Trong-Thuan Huynh, Viet-Tham Do, Trong-Le Le, Khanh-Duy Tran, Mai-Khiem Hoang-Xuan, Nhat Nguyen-Ho, Thang-Long Nguyen, Vinh-Tiep Diep, Tuong-Nghiem Ho, Khanh-Duy Nguyen, Xuan-Hieu Tran, Thien-Phuc Yang, Tuan-Anh Tran, Kim-Phat Hoang, Nhu-Vinh Nguyen, Minh-Quang Nguyen, E-Ro Nguyen-Nhat, Minh-Khoi To, Tuan-An Huynh-Le, Trung-Truc Nguyen, Nham-Tan Luong, Hoang-Chau Phong, Truong Hoai Le-Pham, Nhat-Quynh Pham, Huu-Phuc Hoang, Trong-Vu Nguyen, Quang-Binh Nguyen, Hai-Dang Sugimoto, Akihiro Tran, Minh-Triet |
نوع الوثيقة: | Electronic Resource |
مستخلص: | 3D object retrieval is an important yet challenging task, which has drawn more and more attention in recent years. While existing approaches have made strides in addressing this issue, they are often limited to restricted settings such as image and sketch queries, which are often unfriendly interactions for common users. In order to overcome these limitations, this paper presents a novel SHREC challenge track focusing on text-based fine-grained retrieval of 3D animal models. Unlike previous SHREC challenge tracks, the proposed task is considerably more challenging, requiring participants to develop innovative approaches to tackle the problem of text-based retrieval. Despite the increased difficulty, we believe that this task has the potential to drive useful applications in practice and facilitate more intuitive interactions with 3D objects. Five groups participated in our competition, submitting a total of 114 runs. While the results obtained in our competition are satisfactory, we note that the challenges presented by this task are far from being fully solved. As such, we provide insights into potential areas for future research and improvements. We believe that we can help push the boundaries of 3D object retrieval and facilitate more user-friendly interactions via vision-language technologies. Comment: arXiv admin note: text overlap with arXiv:2304.05731 |
مصطلحات الفهرس: | Computer Science - Computer Vision and Pattern Recognition, text |
URL: | |
الإتاحة: | Open access content. Open access content |
أرقام أخرى: | COO oai:arXiv.org:2304.06053 1381617660 |
المصدر المساهم: | CORNELL UNIV From OAIster®, provided by the OCLC Cooperative. |
رقم الأكسشن: | edsoai.on1381617660 |
قاعدة البيانات: | OAIster |
الوصف غير متاح. |