Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟰𝟰𝟭 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos by Fudan University, Shanghai Follow me for a similar post: Ashish Patel  ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 This paper is published arxiv2022. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 ➡️ Current benchmarks for facial expression recognition (FER) mainly focus on static images, while there are limited datasets for FER in videos. ➡️ It is still ambiguous to evaluate whether performances of existing methods remain satisfactory in real-world application-oriented scenes. ➡️ For example, the "Happy" expression with high intensity in Talk-Show is more discriminating than the same expression with low intensity in Official-Event. ➡️ To fill this gap, we build a large-scale multi-scene dataset, coined as FERV39k. We analyze the important ingredients of constructing such a novel dataset in three aspects: (1) multi-scene hierarchy and expression class, (2) generation of candidate video clips, (3) trusted manual labelling process. ➡️ Based on these guidelines, we select 4 scenarios subdivided into 22 scenes, annotate 86k samples automatically obtained from 4k videos based on the well-designed workflow, and finally build 38,935 video clips labeled with 7 classic expressions. ➡️ Experiment benchmarks on four kinds of baseline frameworks were also provided and further analysis on their performance across different scenes and some challenges for future research were given. ➡️ Besides, we systematically investigate key components of DFER by ablation studies. The baseline framework and our project are available on url. #computervision #artificialintelligence #technology