Deyi Ji

Deyi Ji

Auto-generated profile, based on publicly available information

Deyi Ji

Tencent, Beijing, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
19 November 2020
Verified
Book Chapter
Closed access
PDF file
HHHanzhe Hu
Hanzhe Hu
DJDeyi Ji
Deyi Ji
WGWeihao Gan
Weihao Gan
SBShuai Bai
Shuai Bai
WWWei Wu
Wei Wu
JYJunjie Yan
Junjie Yan

26 May 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
LZLanyun Zhu
Lanyun Zhu
TCTianrun Chen
Tianrun Chen
DJDeyi Ji
Deyi Ji
PXPeng Xu
Peng Xu
JYJieping Ye
Jieping Ye
JLJared Liu
Jared Liu
Despite the rapid advancements in few-shot segmentation (FSS), most of existing methods in this domain are hampered by their reliance on the limited and biased information from only a small number of labeled samples. This limitation inherently restricts their capability to achieve sufficiently high levels of performance. To address this issue, this paper proposes a pioneering framework named LLaFS++, which, for the first time, applies large language models (LLMs) into FSS and achieves notable success. LLaFS++ leverages the extensive prior knowledge embedded by LLMs to guide the segmentation process, effectively compensating for the limited information contained in the few-shot labeled samples and thereby achieving superior results. To enhance the effectiveness of the text-based LLMs in FSS scenarios, we present several innovative and task-specific designs within the LLaFS++ framework. Specifically, we introduce an input instruction that allows the LLM to directly produce segmentation results represented as polygons, and propose a region-attribute corresponding table to simulate the human visual system and provide multi-modal guidance. We also synthesize pseudo samples and use curriculum learning for pretraining to augment data and achieve better optimization, and propose a novel inference method to mitigate potential oversegmentation hallucinations caused by the regional guidance information. Incorporating these designs, LLaFS++ constitutes an effective framework that achieves state-of-the-art results on multiple datasets including PASCAL-$5^{i}$, COCO-$20^{i}$, and FSS-1000. Our superior performance showcases the remarkable potential of applying LLMs to process few-shot vision tasks.

21 January 2026 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
DJDeyi Ji
Deyi Ji
LZLanyun Zhu
Lanyun Zhu
SGSiqi Gao
Siqi Gao
QZQi Zhu
Qi Zhu
YZYiru Zhao
Yiru Zhao
FZFeng Zhao
Feng Zhao
In this paper, we address the challenge of Multi-Object Tracking (MOT) in moving Unmanned Aerial Vehicle (UAV) scenarios, where irregular flight trajectories, such as hovering, turning left/right, and moving up/down, lead to significantly greater complexity compared to fixed-camera MOT. Specifically, changes in the scene background not only render traditional frame-to-frame object IoU association methods ineffective but also introduce significant view shifts in the objects, which complicates tracking. To overcome these issues, we propose a novel HomView-MOT framework, which for the first time, harnesses the view homography inherent in changing scenes to solve MOT challenges in moving environments, incorporating homographic matching and view-centric concepts. We introduce a Fast Homography Estimation (FHE) algorithm for rapid computation of homography matrices between video frames, enabling object View-Centric ID Learning (VCIL) and leveraging multi-view homography to learn cross-view ID features. Concurrently, our Homographic Matching Filter (HMF) maps object bounding boxes from different frames onto a common view plane for a more realistic physical IoU association. Extensive experiments have proven that these innovations allow HomView-MOT to achieve state-of-the-art performance on prominent UAV MOT datasets VisDrone and UAVDT.

30 January 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
DJDeyi Ji
Deyi Ji
FZFeng Zhao
Feng Zhao
HLHongtao Lu
Hongtao Lu
FWFeng Wu
Feng Wu
JYJieping Ye
Jieping Ye
We propose to re-emphasize the low-level texture information in deep networks for semantic segmentation and related knowledge distillation tasks. Low-level texture feature/knowledge is also of vital importance for characterizing the local structural pattern and global statistical property, such as boundary, smoothness, regularity and color contrast, which may not be well addressed by highlevel deep features. In this paper, we are intended to take full advantage of both structural and statistical texture knowledge and propose a novel Structural and Statistical Texture Knowledge Distillation (SSTKD) framework for semantic segmentation. Specifically, Contourlet Decomposition Module (CDM) is introduced to decompose low-level features with iterative Laplacian pyramid and directional filter bank to mine the structural texture knowledge, and Texture Intensity Equalization Module (TIEM) is proposed to extract and enhance statistical texture knowledge with the corresponding Quantization Congruence Loss (QDL). Moreover, we further put forward the Co-occurrence TIEM (C-TIEM) and generic segmentation frameworks, namely STLNet++ and U-SSNet, to enable existing segmentation networks to harvest the structural and statistical texture information more effectively. Extensive experimental results on three segmentation tasks demonstrate the effectiveness of the proposed methods, showing they achieve state-of-the-art performances on seven popular benchmark datasets, respectively.

27 October 2025
Verified
Conference Paper
Open access
YJYanbiao Ji
Yanbiao Ji
DLDan Luo
Dan Luo
CLChang Liu
Chang Liu
SWShaokai Wu
Shaokai Wu
JTJing Tong
Jing Tong
YDYue Ding
Yue Ding

27 February 2026 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
YZYing Zang
Ying Zang
RCRunlong Cao
Runlong Cao
JZJianqi Zhang
Jianqi Zhang
YHYidong Han
Yidong Han
ZCZiyu Cao
Ziyu Cao
TCTianrun Chen
Tianrun Chen
Sketches, with their expressive potential, enable humans to convey the essence of an object through a rough contour. This work leverages expressive power for the first time to improve segmentation performance in challenging tasks such as camouflaged object detection (COD). We propose a sketch guided interactive segmentation framework that allows users to intuitively annotate objects with freehand sketches rather than relying on traditional bounding boxes or points commonly used in models such as the SAM. Our method introduces dedicated network architectural enhancements and a novel sketch augmentation strategy to fully exploit sketch input, leading to significant accuracy gains compared with text- or box-based annotations. Furthermore, our model's output can directly train other neural networks, achieving performance comparable to that of pixel-level annotations while reducing the annotation time by up to 120× and thereby lowering the barrier for large-scale dataset creation and model training. To support future research, werelease KOSCamo+, the first freehand sketch dataset for COD, along with code and a labeling tool. These contributions open promising avenues for expanding sketch-based interaction to broader segmentation tasks and exploring multimodal annotation strategies that combine sketches, text, and other lightweight user inputs.