Zhongjiang He

Zhongjiang He

Auto-generated profile, based on publicly available information

Zhongjiang He

China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 October 2023
Verified
Conference Paper
Open access
XZXianghao Zang
Xianghao Zang
WGWei Gao
Wei Gao
GLGe Li
Ge Li
HFHan Fang
Han Fang
CBChao Ban
Chao Ban
HSHao Sun
Hao Sun
This paper investigates a baseline approach for text-based person search by using a transformer-based framework. Existing methods usually treat the visual and textual features as independent entities for speeding up the model inference process. However, the attention to the same images should be changed according to different texts. In this paper, we use a commonly employed framework with a fused feature as the baseline, which overcomes the misalignment problem introduced by fixed features. A thorough investigation is conducted in this paper. Moreover, we propose Cross-View Matching (CVM) to provide challenging, positive text-image pairs that enable the model to learn cross-view meta-information. Furthermore, we suggest a novel evaluation process to reduce the inference time and GPU memory demand. The experiments are conducted on CUHK-PEDES, ICFG-PEDES, and RSTPReid benchmarks. Through extensive parameter analysis, the potentials of a transformer-based framework are fully explored. Although the proposed scheme is a simple framework, it achieves significant performance improvements compared with other state-of-the-art methods.

26 October 2023
Verified
Conference Paper
Open access
HFHan Fang
Han Fang
ZYZhifei Yang
Zhifei Yang
XZXianghao Zang
Xianghao Zang
CBChao Ban
Chao Ban
ZHZhongjiang He
Zhongjiang He
LZLanxiang Zhou
Lanxiang Zhou
Recently, masked video modeling has been widely explored and improved the model's understanding ability of visual regions at a local level. However, existing methods usually adopt random masking and follow the same reconstruction paradigm to complete the masked regions, which do not leverage the correlations between cross-modal content. In this paper, we present MAsk for Semantics COmpleTion (MASCOT) based on semantic-based masked modeling. Specifically, after applying attention-based video masking to generate high-informed and low-informed masks, we propose Informed Semantics Completion to recover masked semantics information. The recovery mechanism is achieved by aligning the masked content with the unmasked visual regions and corresponding textual context, which makes the model capture more text-related details at a patch level. Additionally, we shift the emphasis of reconstruction from irrelevant backgrounds to discriminative parts to ignore regions with low-informed masks. Furthermore, we design co-learning to incorporate video cues under different masks and learn more aligned representation. Our MASCOT performs state-of-the-art performance on four text-video retrieval benchmarks, including MSR-VTT, LSMDC, ActivityNet, and DiDeMo.

28 October 2024
Verified
Conference Paper
Open access
YLYaqi Li
Yaqi Li
HFHan Fang
Han Fang
ZFZerun Feng
Zerun Feng
KMKaijing Ma
Kaijing Ma
CBChao Ban
Chao Ban
HZHuayu Zhang
Huayu Zhang
Recent text-to-image (T2I) synthesis models have demonstrated intriguing abilities to produce high-quality images based on text prompts. However, current models still face Text-Image Misalignment problem (e.g., attribute errors and relation mistakes) for compositional generation. Existing models attempted to condition T2I models on grounding inputs to improve controllability while ignoring the explicit supervision from the layout conditions. To tackle this issue, we propose Grounded jOint lAyout aLignment (GOAL), an effective framework for T2I synthesis. Two novel modules, discriminative semantic alignment (DSAlign) and masked attention alignment (MAAlign), are proposed and incorporated in this framework to improve the text-image alignment. DSAlign leverages discriminative tasks at the region-wise level to ensure low-level semantic alignment. MAAlign provides high-level attention alignment by guiding the model to focus on the target object. We also build a dataset GOAL2K for model fine-tuning, which composes 2000 semantically accurate image-text pairs and their layout annotations. Comprehensive evaluations on T2I-Compbench, NSR-1K, and Drawbench demonstrate the superior generation performance of our method. Especially, there are improvements of 19%, 13%, and 12% in color, shape, and texture metrics for T2I-Compbench. Additionally, Q-Align metrics demonstrate that our method can generate images of higher quality.

16 September 2025
Verified
Book Chapter
Closed access
PDF file
ZHZhongjiang He
Zhongjiang He
YYYe Yuan
Ye Yuan
AZAn Zhao
An Zhao
HFHan Fang
Han Fang
HSHao Sun
Hao Sun
ZMZhanyu Ma
Zhanyu Ma

15 June 2026
Verified
Conference Paper
Open access
JLJiang Liu
Jiang Liu
YLYuhang Liu
Yuhang Liu
JYJuan Yang
Juan Yang
QRQianhao Ren
Qianhao Ren
YWYutong Wang
Yutong Wang
HSHao Sun
Hao Sun

9 November 2026
Verified
Conference Paper
Open access
HLHao Li
Hao Li
HFHan Fang
Han Fang
ZPZixin Pan
Zixin Pan
XWXin Wei
Xin Wei
HSHongbo Sun
Hongbo Sun
HSHao Sun
Hao Sun