SHORT BIO
I am now an associate professor at Zhejiang Sci-Tech University. I collaborated with Professor Hua Huang Intelligent Media Computing Lab at Beijing Normal University when I was a Posdoc researcher. I received my Ph.D. degree in Computer Science from Beijing Institute of Technology (BIT), where I was advised by Professor Wei Liang. I worked at Media Computing and Intelligent Systems Lab. I was a visiting researcher at the Design Computing and Extended Reality (DCXR) Group at George Mason University, and was advised by Professor Lap-Fai(Craig) Yu.
Email: wangyujia[At]bnu[Dot]edu[Dot]cn; wangyujia[At]bit[Dot]edu[Dot]cn
Research Interests: Human Computer Interaction, Multimedia, Computer Graphics, and Computer Vision.
NEWS!
◆ [2025.11] Our paper “Large-scale Omnidirectional Person Positioning” has been accepted by IEEE TPAMI.
◆ [2025.07] Our paper “Audio-Visual LLM for Augmenting Accessibility of 360° Video” has been accepted by IEEE TCSVT.
◆ [2025.04] Our paper “Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection” has been accepted by CVPR 2025.
◆ [2025.04] Our paper “UNIALIGN: Scaling Multimodal Alignment within One Unified Model” has been accepted by CVPR 2025.
◆ [2024.11] Our paper “Audio–visual deepfake detection using articulatory representation learning” has been accepted by CVIU.
◆ [2024.07] Our paper “AutoSFX: Automatic Sound Effect Generation for Videos” has been accepted by ACM MM 2024.
◆ [2024.07] Our paper “ArtSpeech: Adaptive Text-to-Speech Synthesis with Articulatory Representations” has been accepted by ACM MM 2024.
◆ [2022.02] Our paper “VCoach: Enabling Personalized Boxing Training in Virtual Reality” has been conditionally accepted by IEEE VR Poster 2022.
◆ [2022.02] Our paper “Moving Soon? Rearranging Furniture using Mixed Reality” has been conditionally accepted by IEEE VR Poster 2022.
◆ [2021.01] Our paper “Climaxing VR Character with Scene-Aware Aesthetic Dress Synthesis” has been conditionally accepted by IEEE VR 2021.
◆ [2020.08] Our paper “Toward Automatic Audio Description Generation for Accessible Videos” has been conditionally accepted by ACM CHI 2021.
◆ [2020.07] Our paper “Scene-Aware Background Music Synthesis” has been accepted by ACM MM 2020.
◆ [2020.07] Our paper “Photo Stand-Out: Photography with Virtual Character” has been accepted by ACM MM 2020.
◆ [2019.08] Our paper “Comic-Guided Speech Synthesis” has been conditionally accepted by ACM SIGGRAPH Asia 2019.
◆ [2019.05] Our paper “A Deep Coarse-to-Fine Network for Head Pose Estimation from Synthetic Data” has been accepted by Pattern Recognition.
◆ [2018.11] Our paper “3D Face Synthesis Driven by Personality Impression” has been accepted by AAAI 2019.
