CVPR 2021 Tutorial on
Fine-Grained Visual Analysis with Deep LearningTime: June 19th Virtual Event Location: the Zoom Link
Fine-Grained Visual Analysis (FGVA) is a longstanding and fundamental problem in computer vision and pattern recognition, which underpins a diverse set of real-world applications, such as automatic biodiversity monitoring, climate change evaluation, intelligent retail, intelligent transportation, and positive social-economical impacts have already been observed on conservation, promote economic growth, and improve social operation efficiency. The task of FGVA targets analyzing visual objects from subordinate categories, e.g., species of birds, models of cars, stock keeping units of products or actions of gymnastics. The small inter-class yet large intra-class variations as a result of its very fine-grained nature makes it a challenging problem.
Riding on the boom of deep learning, recent years have witnessed remarkable progress of FGVA using deep learning techniques.
This tutorial aims at promoting discussions among researchers investigating innovative deep learning based Fine-Grained Visual Analysis approaches and deploying cutting-edge fine-grained visual technologies to real-world applications. Specifically, we will stimulate discussions on recent advances, ongoing developments, and novel applications of various deep learning based Fine-Grained Visual Analysis topics, e.g.,
fine-grained image retrieval, fine-grained image recognition, long-tailed visual recognition, fine-grained video understanding, etc.
| Time | Session | Speakers |
| {{tableData[currentCountry][0]}} | Opening Remarks | Xiu-Shen Wei and Jian Yang |
| {{tableData[currentCountry][1]}} | Part I: Introduction of FGVA (40min) | Serge Belongie |
| {{tableData[currentCountry][2]}} | Part II: Fine-Grained Image Recognition (1) (35min) | Xiu-Shen Wei |
| {{tableData[currentCountry][3]}} | Part III: Fine-Grained Image Recognition (2) (50min) | Pitor Koniusz and Lei Wang |
| Break | ||
| {{tableData[currentCountry][4]}} | Part IV: Fine-Grained Image Retrieval (35min) | Yi-Zhe Song |
| {{tableData[currentCountry][5]}} | Part V: Long-Tailed Visual Recognition (35min) | Jiashi Feng and Bingyi Kang |
| {{tableData[currentCountry][6]}} | Part VI: Fine-Grained Video Understanding (35min) | Dian Shao |
| Session | Speakers | Slides | Recordings |
| Opening Remarks | Xiu-Shen Wei and Jian Yang | slides | video |
| Part I: Introduction of FGVA | Serge Belongie | slides | video |
| Part II: Fine-Grained Image Recognition (1) | Xiu-Shen Wei | slides | video |
| Part III: Fine-Grained Image Recognition (2) | Pitor Koniusz | slides | video |
| Part III: Fine-Grained Image Recognition (2) | Lei Wang | slides | video |
| Part IV: Fine-Grained Image Retrieval | Yi-Zhe Song | slides | video |
| Part V: Long-Tailed Visual Recognition | Jiashi Feng and Bingyi Kang | slides | video |
| Part VI: Fine-Grained Video Understanding | Dian Shao | slides | video |
A Survey Paper of Fine-Grained Image Analysis published on IEEE TPAMI.
