default author photo

Yi-Gang Cen

Beijing Jiaotong University

No.3 of Shangyuan Residence Haidian District

Beijing, 100089

China

  • Beijing Jiaotong University

SCHOLARLY PAPERS

7

DOWNLOADS

205

TOTAL CITATIONS

1

Scholarly Papers (7)

Actions:
Email selected abstracts
1.

Integrating Spatial Features and Dynamically Learned Temporal Features Via Contrastive Learning for Video Temporal Grounding in Llm

Downloads 80 (844,901)

Integrating Spatial Features and Dynamically Learned Temporal Features Via Contrastive Learning for Video Temporal Grounding in Llm

Number of pages: 28 Posted: 08 May 2025
Peifu Wang, Yixiong Liang, Yi-Gang Cen, Lihui Cen, Zhe Qu, Jingling Liu and Shichao Kan
Central South University, Central South University, Beijing Jiaotong University, Central South University, Central South University, Central South University and Central South University
Downloads 64 (986,385)

Abstract:

Loading...

Large language model, Video temporal grounding, Video temporal localization, Contrastive learning

Integrating Spatial Features and Dynamically Learned Temporal Features Via Contrastive Learning for Video Temporal Grounding in Llm

Number of pages: 28 Posted: 08 May 2025
Peifu Wang, Yixiong Liang, Yi-Gang Cen, Lihui Cen, Zhe Qu, Jingling Liu and Shichao Kan
Central South University, Central South University, Beijing Jiaotong University, Central South University, Central South University, Central South University and Central South University
Downloads 16 (1,559,710)

Abstract:

Loading...

Large language model, Video temporal grounding, Video temporal localization, Contrastive learning

2.

Cross-Scene Visual Context Parsing with Large Vision-Language Model

Number of pages: 23 Posted: 03 Aug 2024
Guoqing Zhang, Shichao Kan, Lu Shi, Wanru Xu, Gaoyun An and Yi-Gang Cen
Beijing Jiaotong University, Central South University, Beijing Jiaotong University, Beijing Jiaotong University, Beijing Jiaotong University and Beijing Jiaotong University
Downloads 65 (916,100)

Abstract:

Loading...

Scene Graph Generation, Large Vision-Language Model, Image Caption, Visual Context Parsing, Instruction Tuning

3.

Patch Spatio-Temporal Relation Prediction for Video Anomaly Detection

Number of pages: 10 Posted: 12 Jul 2024
Hao Shen, Lu Shi, Yi-Gang Cen, Wanru Xu, Linna Zhang and Gaoyun An
Beijing Jiaotong University, Beijing Jiaotong University, Beijing Jiaotong University, Beijing Jiaotong University, Guizhou University and Beijing Jiaotong University
Downloads 20 (1,448,301)
Citation 1

Abstract:

Loading...

Video anomaly detection, Self-supervised learning, Pretext task

4.

Semantics-Oriented and Order-Robust Description Modeling for Grounded Conversation Generation

Number of pages: 34 Posted: 16 Mar 2026
Can Zhang, Yi-Gang Cen, Linna Zhang, Lihui Cen, Yixiong Liang, Zhe Qu and Shichao Kan
Central South University, Beijing Jiaotong University, Guizhou University, Central South University, Central South University, Central South University and Central South University
Downloads 14 (1,526,714)

Abstract:

Loading...

Grounded Conversation Generation, Large Vision-Language Models, multimodal learning

5.

PADCap: Perspective-Adaptive Fitting and Decorrelated Difference Tokens Enhanced LLMs for Change Captioning

Number of pages: 25 Posted: 20 Apr 2026
Yutao Liu, Wanru Xu, Zhenjiang Miao, Lili Wan, Yi-Gang Cen, Kunpeng Xing, Wangsheng He and Kaijie Zhang
affiliation not provided to SSRN, affiliation not provided to SSRN, Beijing Jiaotong University, affiliation not provided to SSRN, Beijing Jiaotong University, affiliation not provided to SSRN, affiliation not provided to SSRN and affiliation not provided to SSRN
Downloads 11 (1,548,648)

Abstract:

Loading...

Change Captioning, Perspective-Adaptive Fitting, Self-Supervised Decorrelation, Large Language Model

6.

IVCP: Instruction-Guided Video Context Prompting for Video Action Recognition

Number of pages: 27 Posted: 14 Apr 2026
Shichao Kan, Wentao Li, Peifu Wang, Yi-Gang Cen, Linna Zhang and Lihui Cen
Central South University, Central South University, Central South University, Beijing Jiaotong University, Guizhou University and Central South University
Downloads 9 (1,561,096)

Abstract:

Loading...

Video Understanding, Multimodal learning, Prompt learning, Action recognition

7.

CUSFusion: An Infrared and Visible Image Fusion Framework Based on Compensating U-Net and Salience

Number of pages: 16 Posted: 13 Dec 2025
Ruofei Liang, Xiaole Ma, Yi-Gang Cen, Jian Zhang, Linna Zhang, Yue Zhang and Shaohai Hu
affiliation not provided to SSRN, Beijing Jiaotong University, Beijing Jiaotong University, Beijing Jiaotong University, Guizhou University, Henan Normal University and Beijing Jiaotong University
Downloads 6 (1,571,455)

Abstract:

Loading...

Image fusion, Cross-Modality Compensation Blocks (CMCBs), Residual Enhancement Block (REB), mask, saliency-guided target detection