Teng Wang 王腾
Teng Wang is currently a researcher at Tencent ARC Lab. He obtained his Ph.D. degree from the University of Hong Kong (HKU) in 2024, fortunately supervised by Prof. Ping Luo and Prof. Feng Zheng. Before that, he obtained his B.E. and M.E. degrees from Sun Yat-sen University (SYSU) under the supervision of Prof. Huicheng Zheng. Hiring! We are hiring self-motivated research interns to join the Multimodal Foundation Model team. Please feel free to drop me an email if you are interested. ResearchMy research interests include:
Selected Publications* equal contribution
Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models
Two in One Go: Single-stage Emotion Recognition with Decoupled Subject-context Transformer
Transferable decoding with visual entities for zero-shot image captioning
Knowledge-aware prompt tuning for generalizable vision-language models
Set-level guidance attack: Boosting adversarial transferability of vision-language pre-training models
Pi-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline
Accelerating Vision-Language Pretraining with Free Language Modeling
Show, Tell and Rephrase: Diverse Video Captioning via Two-Stage Progressive Training
VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix
End-to-end dense video captioning with parallel decoding
Event-centric hierarchical representation for dense video captioning Arxiv
UniAV: Unified Audio-Visual Perception for Multi-Task Video Localization
Video understanding with large language models: A survey
Caption anything: Interactive image description with diverse multimodal controls
Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos
Academic service
Journal reviewer for IJCV, IEEE TNNLS, IEEE TIP, IEEE TMM, IEEE TCSVT Experience
Research Intern at Tencent ARC Lab, 2022. Research Intern at Tencent Data Platform, 2021. Research Intern at Tencent AI Lab, 2019. Competitions & Awards
Rank 1 in Make-up Temporal Video Grounding Track of PIC challenge at ACM MM 2022 Rank 1 in Make-up Dense Video Captioning Track of PIC challenge at ACM MM 2022 Rank 2 in Generic Event Boundary Captioning Track of LOVEU Challenge at CVPR 2022 Rank 2 in Event Dense-Captioning Track of ActivityNet Challenge at CVPR 2020, CVPR2021, CVPR2022 Rank 3 in TinyAction Challenge at CVPR 2021 |