My name is Pengpeng Zeng. I am a fourth-year PhD student at University of Electronic Science and Technology of China, advised by Prof.Jingkuan Song, Prof.Lianli Gao and Prof.Heng Tao SHEN.

My research interests are Machine Learning, Deep Learning, Computer Vision and Reinforcement Learning etc.

Email：is.pengpengzeng@gmail.com

[Google Scholar] [GitHub] [DBLP]

UMP: Unified Modality-aware Prompt Tuning for Text-Video Retrieval

SPT: Spatial Pyramid Transformer for Image Captioning

Visual Commonsense-aware Representation Network for Video Captioning

Adaptive Fine-Grained Predicates Learning for Scene Graph Generation

Dual-branch Hybrid Learning Network for Unbiased Scene Graph Generation

Memory-based Augmentation Network for Video Captioning

Learning Visual Question Answering on Controlled Semantic Noisy Labels

Complementarity-aware Space Learning for Video-Text Retrieval

Video Question Answering with Prior Knowledge and Object-sensitive Learning

Hierarchical Representation Network with Auxiliary Tasks for Video Captioning and Video Question Answering

Text-Instance Graph: Exploring Relational Semantics for Text-based Visual Question Answering

Relation-aware Aggregation Network with Auxiliary Guidance for Text-based Person Search

Generalized Pyramid Co-Attention with Learnable Aggregation Net for Video Question Answering

Rich Visual Knowledge-based Augmentation Network for Visual Question Answering

MPT: Multi-grained Prompt Tuning for Text-Video Retrieval

ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrieval

Depth-Aware Sparse Transformer for Video-Language Learning

Progressive Tree-Structured Prototype Network for End-to-End Image Captioning

Dynamic Scene Graph Generation via Temporal Prior Inference

S2 Transformer for Image Captioning

Support-set based Multi-modal Representation Enhancement for Video Captioning

Learning To Generate Scene Graph From Head To Tail

Conceptual and Syntactical Cross-modal Alignment with Cross-level Consistency for Image-Text Matching

Hierarchical Representation Network with Auxiliary Task for Video Captioning

Structured Two-stream Attention Network for Video Question Answering

Examine before You Answer: Multi-task Learning with Adaptive-attentions for Multiple-choice VQA

From Pixels to Objects: Cubic Visual Attention for Visual Question Answering