Yiming Wang
My research enthusiasm is on image/video understanding that facilitates automation for social good, covering diverse topics related to 2D/3D perception, semantic scene understanding and scene dynamic analysis.
I obtained the PhD in Electronic Engineering in 2018 from Queen Mary University of London (UK) under the supervision of Prof. Andrea Cavallaro, working on vision-based multi-agent navigation. Since 2018, I worked as a post-doc researcher in the Pattern Analysis and Computer Vision/Visual Geometry Modelling (PAVIS/VGM) research line led by Dr. Alessio Del Bue at Istituto Italiano di Tecnologia (IIT), working on topics related to active 3D vision through both research and industrial Projects. Currently I work as a researcher in the Deep Visual Learning (DVL) unit led by Prof. Elisa Ricci in Fondazione Bruno Kessler (FBK), working on multimodal scene dynamic analysis under a series of EU Projects.
News
Tweets
12-04-2024: 🎉 Our Workshop on Green FOundation MOdels (GreenFOMO) is accepted to ECCV 2024!
04-04-2024: 🎉 1 CVPR highlight poster + 2 CVPR posters: a very brilliant job to all co-authors!
22-01-2024: 🤖 Glad to join the International Journal of Social Robotics as Associate Editor!
17-01-2024: 🖼️ serving as Area Chair for ECCV 2024!
19-12-2023: 🤖 Joining the organisation committe of RO-MAN 2024 as a Virtual Organisation Chair.
21-09-2023: 🎉 Our amazing paper "Vocabulary-free Image Classification" is accepted by NeurIPS!
16-08-2023: 🎉 Glad to announce that our survey paper on "Video anomaly detection in dymanic scenes with moving cameras" is published on AI Reviews!
31-07-2023: 💚 Happy to receive my first grant in career and look forward to making a green impact with LoCa AI.
26-04-2023: 🎉 Proud to have our paper "Leveraging commonsense for object localisation in partial scenes" accepted in TPAMI!
15-03-2023: 🤖 Glad to announce the CfP to our Special Issue "Social and Cognitive Interactions in the Open World" on International Journal of Social Robotics!
17-02-2023: 🎉 Our paper "PI-Trans: Parallel-ConvMLP and Implicit-Transformation Based GAN for Cross-View Image Translation" is accepted in ICASSP 2023!
Check more Past News!