Deng Cai

Southern Medical University Shenzhen Hospital — China

Computer Science · Physical Sciences

73h-index24.5kcitations373works3.82yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Image and Video Retrieval Techniques(106), Image Retrieval and Classification Techniques(65), Advanced Neural Network Applications(61), Topic Modeling(59), Face and Expression Recognition(58)

Publications373 total

Balance Discriminability and Integrality for Robust Salient Object Detection
Lecture notes in computer science·2025
Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning
arXiv (Cornell University)·2025Open Access
Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model
arXiv (Cornell University)·2025Open Access
Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst
arXiv (Cornell University)·2025Open Access
CLRNetV2: A Faster and Stronger Lane Detector
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025· 4 cited
Simulation study on the two-phase unsaturated microscopic seepage based on digital core technology
Computational Particle Mechanics·2025· 1 cited
Revealing the core suppression effects of various Di (2-ethylhexyl) phthalate exposure on early meiosis progression in postnatal male mice via single-cell RNA sequencing
Ecotoxicology and Environmental Safety·2025· 3 citedOpen Access
NeRF-Det++: Incorporating Semantic Cues and Perspective-Aware Depth Supervision for Indoor Multi-View 3D Detection
IEEE Transactions on Image Processing·2025· 9 cited
LEViT: Locally Enhanced Vision Transformer for Efficient Object Re-identification
IEEE Transactions on Multimedia·2025
Vidsketch: Hand-Drawn Sketch-Driven Video Generation with Diffusion Control
SSRN Electronic Journal·2025· 2 citedOpen Access
Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst
2025Open Access
LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models
IEEE Transactions on Image Processing·2025· 3 cited
Huvidpo: Enhancing Video Generation Through Direct Preference Optimization for Human-Centric Alignment
SSRN Electronic Journal·2025· 1 citedOpen Access
Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning
2025Open Access
Challenges and Opportunities of Sichuan Opera Face Changing in Haidilao in Cultural Communication
Interdisciplinary Humanities and Communication Studies·2024Open Access
Innovative desalination strategies for the removal of emerging pollutants in aquatic systems
Separation and Purification Technology·2024· 6 cited
GCA-3D: Towards Generalized and Consistent Domain Adaptation of 3D Generators
arXiv (Cornell University)·2024Open Access
From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
arXiv (Cornell University)·2024· 4 citedOpen Access
Semi-supervised 3D Object Detection with PatchTeacher and PillarMix
arXiv (Cornell University)·2024Open Access
GLBench: A Comprehensive Benchmark for Graph with Large Language Models
arXiv (Cornell University)·2024· 2 citedOpen Access
page 1 of 19Next →

Frequent Co-authors

Xiaofei He(28), Jiawei Han(12), Wei‐Ying Ma(7), Jiajun Bu(6), Chun Chen(6), Ji-Rong Wen(6), Shipeng Yu(4), Ziyu Guan(4), Haifeng Liu(3), Xuelong Li(3), Lijun Zhang(3), Thomas S. Huang(3), Hujun Bao(3), Beidou Wang(3), Partha Niyogi(2), Jiawei Han(2), Yu Zhu(2), Qiaozhu Mei(2), ChengXiang Zhai(2), Minghao Chen(2)