|
I am currently a first-year PhD Student of Multimedia Lab at Shanghai Jiao Tong University (SJTU), advised by Prof. Guangtao Zhai and Prof. Wenjun Zhang. Previously, I received my M.E. degree from East China University of Science and Technology in June 2023, and B.S. degree in EE from Wenzhou University in June 2020. I'm generally interested in image/video quality assessment, large multimodal models, especially all-round evaluation, and AI4Humanity (Oracle bone character processing). My ultimate goal is to build models with human-like general intelligence that can seamlessly understand, generate, and reason across multiple modalities. I'm always eager to communicate and cooperate, so feel free to contact me!!! Email: zijian.chen@sjtu.edu.cn Email / Google Scholar / Github / Zhihu / Team Web |
|
|
|
* denotes equal contribution, and † denotes corresponding author. |
|
Zijian Chen, Yuan Tian, Yuze Sun, Wei Sun, Zicheng Zhang, Weisi Lin, Guangtao Zhai†, Wenjun Zhang arXiv, 2025. (NEW) project page / Code / arXiv In this paper, we propose a novel concept, LMM-JND, to quantify the perceptual redundancy characteristic for LMMs and a well-designed pipeline for its determination. We also construct a large-scale dataset, named VPA-JND, which contains 21.5k reference images with over 489k stimuli across 12 distortion types, to facilitate LMM-JND studies. |
|
Zeyu Zhang*, Zijian Chen*, Zicheng Zhang, Yuze Sun, Yuan Tian, Ziheng Jia, Chunyi Li, Xiaohong Liu, Xiongkuo Min, Guangtao Zhai arXiv, 2025. (NEW) arXiv In this paper, we construct PuzzleBench, a dynamic and scalable benchmark comprising 11,840 VQA samples, which features six carefully designed puzzle tasks targeting three core LMM competencies, visual recognition, logical reasoning, and context understanding. |
|
Jinhao Li*, Zijian Chen*, Runze Jiang, Tingzhu Chen†, Changbo Wang†, Guangtao Zhai† ACM MM, 2025. (Oral Presentation) project page / arXiv In this paper, we present the Oracle-P15K, a structure-aligned OBI dataset for OBI generation and denoising, consisting of 14,542 images infused with domain knowledge from OBI experts. Based on this, we propose a diffusion model-based pseudo OBI generator, called OBIDiff, to achieve realistic and controllable OBI generation. |
|
* denotes equal contribution, and † denotes corresponding author. |
|
* denotes equal contribution, and † denotes corresponding author. |
|
Zijian Chen, Wei Sun, Jun Jia, Ru Huang, Fangfang Lu, Ying Chen, Xiongkuo Min, Guangtao Zhai†, Wenjun Zhang IEEE Transactions on Circuits and Systems for Video Technology, 2025. (NEW) In this paper, we propose a unified deep neural network that explicitly disentangles the luminance and chrominance channels, and simultaneously recovers intensity gradients and color discontinuity from detection-free measurement in an end-to-end manner. |
|
Zijian Chen, Wei Sun†, Yuan Tian, Jun Jia, Zicheng Zhang, Jiarui Wang, Ru Huang, Xiongkuo Min†, Guangtao Zhai†, Wenjun Zhang NeurIPS, 2024. (Spotlight Presentation) project page / dataset extraction code: s277 / 中文版速递: 知乎 In this work, we construct GAIA, a Generic AI-generated Action dataset, by conducting a large-scale subjective evaluation from a novel causal reasoning-based perspective, resulting in 971,244 ratings among 9,180 video-action pairs, and evaluate a suite of popular text-to-video models on their ability to generate visually rational actions. |
|
Zijian Chen, Wei Sun†, Haoning Wu, Zicheng Zhang, Jun Jia, Ru Huang, Xiongkuo Min†, Guangtao Zhai†, Wenjun Zhang IEEE Transactions on Circuits and Systems for Video Technology, 2025. (NEW) paper / dataset / code In this work, we construct the AI-Generated Image Naturalness (AGIN) dataset and propose the Joint Objective Image Naturalness evaluaTor (JOINT) to automatically assess the naturalness of AIGIs that align with human opinions. |
|
Zijian Chen, Wei Sun, Jun Jia, Fangfang Lu, Zicheng Zhang, Jing Liu, Ru Huang, Xiongkuo Min†, Guangtao Zhai† IEEE Transactions on Circuits and Systems for Video Technology, 2024. project page / dataset In this work, we build the Banding Artifact Noticeable Database (BAND-2k), which consists of 2,000 banding images generated by 15 compression and quantization schemes. |
|
Zijian Chen, Wei Sun, Zicheng Zhang, Ru Huang, Fangfang Lu, Xiongkuo Min, Guangtao Zhai†, Wenjun Zhang IEEE International Symposium on Circuits and Systems (ISCAS), 2024. project page In this paper, we develop a no-reference banding evaluator for banding detection and quality assessment by leveraging its frequency characteristics. |
|
* denotes equal contribution, and † denotes corresponding author. |
|
Zijian Chen, Tingzhu Chen†, Wenjun Zhang, Guangtao Zhai† ICLR, 2025. (NEW) project page / dataset extraction code: 7adv / 中文版速递: 知乎 In this work, we introduce OBI-Bench, a holistic benchmark crafted to systematically evaluate large multi-modal models (LMMs) on whole-process oracle bone inscriptions (OBI) processing tasks demanding expert-level domain knowledge and deliberate cognition. |
|
Jinhao Li, Zijian Chen, Tingzhu Chen†, Zhiji Liu, Changbo Wang Displays, 2025. (NEW) project page In this work, we propose OBIFormer, a fast attentive framework for high-precision Oracle bone inscriptions denoising. |
|
* denotes the sole student author. |
|
Ru Huang (Master's Advisor), Zijian Chen*, Guangtao Zhai, Jianhua He, Xiaoli Chu IET Intelligent Transport Systems, 2023. In this work, we propose a novel architecture, named spatial-temporal correlation graph convolutional networks (STCGCN), for traffic prediction. |
|
Ru Huang (Master's Advisor), Zijian Chen*, Guangtao Zhai, Jianhua He, Xiaoli Chu IEEE Transactions on Network Science and Engineering, 2022. In this work, we introduce an unbiased graphlet estimation strategy to obtain both urelement and higher-order statistics for network analysis. |
|
|
|
|
|
|
|
|
|
|
|
Updated in Jun. 2025 Thanks Jon Barron for this amazing website template. |