龚涛｜中国科学技术大学｜学者主页

2026

SAPL: Semantic-Agnostic Prompt Learning in CLIP for Weakly Supervised Image Manipulation Localization

Xing-Hao Wang, Changtao Miao, Dianmo Sheng, Tao Gong, Qi Chu, Neng-Hai Yu, Quan-Chen Zou, De-Yue Zhang, Xiang-Zheng Zhang

arXiv.org

DOI

2026

Flora: Effortless Context Construction to Arbitrary Length and Scale

Tianxiang Chen, Zhentao Tan, Xiaofan Bo, Yue Wu, Tao Gong, Qi Chu, Jieping Ye

Proceedings of the AAAI Conference on Artificial Intelligence

DOI

2026

SPIDER: Multi-Layer Semantic Token Pruning and Adaptive Sub-Layer Skipping in Multimodal Large Language Models

Tianxiang Chen, Zhentao Tan, Zi Ye, Yue Wu, Xiaobing Tu, Jinkui Ren, Xiantao Zhang, Tao Gong, Qi Chu, Nenghai Yu, Xipeng Qiu, Jieping Ye

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2026

EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders

Xinghao Wang, Dong Li, Wei Yu, Yingwei Pan, Tao Gong, Qi Chu, Nenghai Yu, Ting Yao

Lecture notes in computer science

DOI

2026

ANFI: Rethinking Neighbor Feature Interaction in Person Re-ID

Xulin Li, Yan Lu, Bin Liu, Jiaze Li, Qinhong Yang, Tao Gong, Qi Chu, Nenghai Yu

Lecture notes in computer science

DOI

2026

When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors

Chenghao Yang, Yuning Zhang, Zhoufutu Wen, Tao Gong, Jiaheng Liu, Qi Chu, Nenghai Yu

Annual Meeting of the Association for Computational Linguistics (ACL)

DOI

2026

Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs

Xuan-Pu Zhao, Zhentao Tan, Dianmo Sheng, Tian-Xiang Chen, Yao Liu, Yue Wu, Tao Gong, Qi Chu, Neng-Hai Yu

arXiv.org

DOI

2026

Thinking Like a Forensic Expert: A Multimodal Reasoning Chain for Training-Free Image Manipulation Localization

Rui Chen, Bin Liu, Changtao Miao, Xinghao Wang, Yi Li, Tao Gong, Qi Chu, Nenghai Yu

Proceedings - International Conference on Image Processing

DOI

2026

AnomalySegVLM: End-to-End Anomaly Localization via a Learnable Segmentation Token in Vision-Language Model

Xixuan Hou, Qi Chu, Tao Gong, Nenghai Yu

Communications in computer and information science

DOI

2026

Diff-IML : Towards the Diffusion-Based Real-World Image Manipulation Localization

Dayong Wang, Wanyi Zhuang, Qi Chu, Tao Gong, Bin Liu, Nenghai Yu

IEEE International Conference on Acoustics Speech and Signal Processing

DOI

2026

MagicPaint: Operate Anything for Image Inpainting with Diffusion Model

Qinhong Yang, Dongdong Chen, Qi Chu, Tao Gong, Qiankun Liu, Zhentao Tan, Xulin Li, Huamin Feng, Nenghai Yu

Proceedings of the AAAI Conference on Artificial Intelligence

DOI

2025

图像分类任务中的注意力机制研究综述

林国军，龚涛，林通

《电讯技术》

DOI

2025

Mixture-of-Noises Enhanced Forgery-Aware Predictor for Multi-Face Manipulation Detection and Localization

Changtao Miao, Qi Chu, Tao Gong, Zhentao Tan, Zhenchao Jin, Wanyi Zhuang, Man Luo, Honggang Hu, Nenghai Yu

ACM International Conference on Multimedia (ACM MM)

DOI

2025

Context-Aware Weakly Supervised Image Manipulation Localization With SAM Refinement

Xing-Hao Wang, Tao Gong, Qi Chu, Bin Liu, Neng-Hai Yu

IEEE Signal Processing Letters

DOI

2025

MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation

Chenghao Yang, Yinbo Luo, Zhoufutu Wen, Qi Chu, Tao Gong, Long-Xiang Liu, Kai-Yuan Zhang, Jian-Peng Jiao, Ge Zhang, Wen-Hao Huang, Neng-Hai Yu

Conference on Empirical Methods in Natural Language Processing

DOI

2025

Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning

Ajian Liu, Haocheng Yuan, Xiao Guo, Hui Ma, Wanyi Zhuang, Changtao Miao, Yan Hong, Chuanbiao Song, Jun Lan, Qi Chu, Tao Gong, Yan-Yan Liang, Wei-Qiang Wang, Jun Wan, Xiao-Ming Liu, Zhen Lei

arXiv.org

DOI

2025

DDL: A Dataset for Interpretable Deepfake Detection and Localization in Real-World Scenarios

Chang-Tao Miao, Yi Zhang, Weize Gao, Man Luo, Wei-Wei Feng, Zhi-Ya Tan, Jian-Shu Li, Ajian Liu, Yunfeng Diao, Qi Chu, Tao Gong, Zhe Li, Weibin Yao, Joey Tianyi Zhou

arXiv.org

DOI

2025

Multi-spectral Class Center Network for Face Manipulation Localization

Changtao Miao, Qi Chu, Zhentao Tan, Zhenchao Jin, Tao Gong, Wanyi Zhuang, Yue Wu, Bin Liu, Honggang Hu, Nenghai Yu

ACM Transactions on Multimedia Computing Communications and Applications

DOI

2025

Training-Free In-Context Forensic Chain for Image Manipulation Detection and Localization

Rui Chen, Bin Liu, Changtao Miao, Xing-Hao Wang, Yi Li, Tao Gong, Qi Chu, Neng-Hai Yu

arXiv.org

DOI

2025

Towards Anytime Retrieval: A Benchmark for Anytime Person Re-Identification

Xulin Li, Yan Lu, Bin Liu, Jiaze Li, Qinhong Yang, Tao Gong, Qi Chu, Mang Ye, Nenghai Yu

International Joint Conference on Artificial Intelligence

DOI

2025

GuardTrace-VL: Detecting Unsafe Multimodel Reasoning via Iterative Safety Supervision

Yu Xiang, Jun-Chi Chen, Zhen-Chao Jin, Changtao Miao, Hao-Jie Yuan, Qi Chu, Tao Gong, Neng-Hai Yu

arXiv.org

DOI

2025

MFFI: Multi-Dimensional Face Forgery Image Dataset for Real-World Scenarios

Chang-Tao Miao, Yi Zhang, Man Luo, Wei-Wei Feng, Kai-Yuan Zheng, Qi Chu, Tao Gong, Jian-Shu Li, Yunfeng Diao, Wei Zhou, Joey Tianyi Zhou, Xiao-Shuai Hao

ACM Multimedia

DOI

2025

FE-CLIP: Frequency Enhanced CLIP Model for Zero-Shot Anomaly Detection and Segmentation

Tao Gong, Qi Chu, Bin Liu, Wei Zhou, Nenghai Yu

IEEE/CVF International Conference on Computer Vision (ICCV)

DOI

2025

Exploiting Feature Gating and Injection For Multi-modal Manipulation Detection and Grounding

Jiazhen Wang, Bin Liu, Tao Gong, Zhiwei Zhao, Changtao Miao, Yangyang Wang, Qi Chu, Nenghai Yu

Lecture notes in computer science

DOI

2025

Towards Good Generalizations for Diffusion Generated Image Detection Using Multiple Reconstruction Contrastive Learning

Wanyi Zhuang, Qi Chu, Tao Gong, Changtao Miao, Nenghai Yu

ACM International Conference on Multimedia (ACM MM)

DOI

2024

Bootstrapping Audio-Visual Video Segmentation by Strengthening Audio Cues

Tianxiang Chen, Zhentao Tan, Tao Gong, Qi Chu, Yue Wu, Bin Liu, Nenghai Yu, Le Lü, Jieping Ye

IEEE Transactions on Circuits and Systems for Video Technology

DOI

2024

MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small-Target Detection

Tianxiang Chen, Zi Ye, Zhentao Tan, Tao Gong, Yue Wu, Qi Chu, Bin Liu, Nenghai Yu, Jieping Ye

IEEE Transactions on Geoscience and Remote Sensing

DOI

2024

Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection

Tian-Xiang Chen, Zhentao Tan, Tao Gong, Yue Wu, Qi Chu, Bin Liu, Jie-Ping Ye, Neng-Hai Yu

Conference on Empirical Methods in Natural Language Processing

DOI

2024

Towards More Unified In-Context Visual Understanding

Dianmo Sheng, Dongdong Chen, Zhentao Tan, Qiankun Liu, Qi Chu, Jianmin Bao, Tao Gong, Bin Liu, Shengwei Xu, Nenghai Yu

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI

2024

Inclusion 2024 Global Multimedia Deepfake Detection: Towards Multi-dimensional Facial Forgery Detection

Yi Zhang, Weize Gao, Changtao Miao, Man Luo, Jian-Shu Li, Wenzhong Deng, Zhe Li, Bingyu Hu, Weibin Yao, Wenbo Zhou, Tao Gong, Qi Chu

arXiv.org

DOI

2024

MFMS: Learning Modality-Fused and Modality-Specific Features for Deepfake Detection and Localization Tasks

Yi Zhang, Changtao Miao, Man Luo, Jianshu Li, Wenzhong Deng, Weibin Yao, Zhe Li, Bingyu Hu, Weiwei Feng, Tao Gong, Qi Chu

ACM International Conference on Multimedia (ACM MM)

DOI

2024

Detect Text Forgery with Non-forged Image Features: A Framework for Detection and Grounding of Image-Text Manipulation

Yang-Yang Wang, Changtao Miao, Qi Chu, Tao Gong, Dianmo Sheng, Jiazhen Wang, Bin Liu, Neng-Hai Yu

Chinese Conference on Pattern Recognition and Computer Vision

DOI

2022

StrongSORT: Make DeepSORT Great Again

Yunhao Du, Zhicheng Zhao, Yang Song, Yanyun Zhao, Fei Su, Tao Gong, Hongying Meng

IEEE transactions on multimedia

DOI

2021

基于优化特征表达的目标检测与跟踪算法研究

龚涛

《中国科学技术大学》

2021

Temporal ROI Align for Video Object Recognition

Tao Gong, Kai Chen, Xin-Jiang Wang, Q. Chu, Feng Zhu, Da-Hua Lin, Neng-Hai Yu, Huamin Feng

AAAI Conference on Artificial Intelligence

DOI

2021

Towards Generalizable and Robust Face Manipulation Detection via Bag-of-feature

Changtao Miao, Qi Chu, Weihai Li, Tao Gong, Wanyi Zhuang, Nenghai Yu

IEEE International Conference on Visual Communications and Image Processing (VCIP)

DOI

2021

Mining Contextual Information Beyond Image for Semantic Segmentation

Zhenchao Jin, Tao Gong, Dongdong Yu, Qi Chu, Jian Wang, Changhu Wang, Jie Shao

IEEE/CVF International Conference on Computer Vision (ICCV)

DOI

2021

Seesaw Loss for Long-Tailed Instance Segmentation

Jiaqi Wang, Wenwei Zhang, Yuhang Zang, Yuhang Cao, Jiangmiao Pang, Tao Gong, Kai Chen, Ziwei Liu, Chen Change Loy, Dahua Lin

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI

2020

Side-Aware Boundary Localization for More Precise Object Detection

Jiaqi Wang, Wenwei Zhang, Yuhang Cao, Kai Chen, Jiangmiao Pang, Tao Gong, Jianping Shi, Chen Change Loy, Dahua Lin

Lecture notes in computer science

DOI

2019

A Large Scale Urban Surveillance Video Dataset for Multiple-Object Tracking and Behavior Analysis

Guojun Yin, Bin Liu, Huihui Zhu, Tao Gong, Neng-Hai Yu

arXiv.org

精选作品

期刊论文

SAPL: Semantic-Agnostic Prompt Learning in CLIP for Weakly Supervised Image Manipulation Localization

Flora: Effortless Context Construction to Arbitrary Length and Scale

SPIDER: Multi-Layer Semantic Token Pruning and Adaptive Sub-Layer Skipping in Multimodal Large Language Models

EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders

ANFI: Rethinking Neighbor Feature Interaction in Person Re-ID

When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors

Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs

Thinking Like a Forensic Expert: A Multimodal Reasoning Chain for Training-Free Image Manipulation Localization

AnomalySegVLM: End-to-End Anomaly Localization via a Learnable Segmentation Token in Vision-Language Model

Diff-IML : Towards the Diffusion-Based Real-World Image Manipulation Localization

MagicPaint: Operate Anything for Image Inpainting with Diffusion Model

图像分类任务中的注意力机制研究综述

Mixture-of-Noises Enhanced Forgery-Aware Predictor for Multi-Face Manipulation Detection and Localization

Context-Aware Weakly Supervised Image Manipulation Localization With SAM Refinement

MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation

Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning

DDL: A Dataset for Interpretable Deepfake Detection and Localization in Real-World Scenarios

Multi-spectral Class Center Network for Face Manipulation Localization

Training-Free In-Context Forensic Chain for Image Manipulation Detection and Localization

Towards Anytime Retrieval: A Benchmark for Anytime Person Re-Identification

GuardTrace-VL: Detecting Unsafe Multimodel Reasoning via Iterative Safety Supervision

MFFI: Multi-Dimensional Face Forgery Image Dataset for Real-World Scenarios

FE-CLIP: Frequency Enhanced CLIP Model for Zero-Shot Anomaly Detection and Segmentation

Exploiting Feature Gating and Injection For Multi-modal Manipulation Detection and Grounding

Towards Good Generalizations for Diffusion Generated Image Detection Using Multiple Reconstruction Contrastive Learning

Bootstrapping Audio-Visual Video Segmentation by Strengthening Audio Cues

MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small-Target Detection

Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection

Towards More Unified In-Context Visual Understanding

Inclusion 2024 Global Multimedia Deepfake Detection: Towards Multi-dimensional Facial Forgery Detection

MFMS: Learning Modality-Fused and Modality-Specific Features for Deepfake Detection and Localization Tasks

Detect Text Forgery with Non-forged Image Features: A Framework for Detection and Grounding of Image-Text Manipulation

StrongSORT: Make DeepSORT Great Again

基于优化特征表达的目标检测与跟踪算法研究

Temporal ROI Align for Video Object Recognition

Towards Generalizable and Robust Face Manipulation Detection via Bag-of-feature

Mining Contextual Information Beyond Image for Semantic Segmentation

Seesaw Loss for Long-Tailed Instance Segmentation

Side-Aware Boundary Localization for More Precise Object Detection

A Large Scale Urban Surveillance Video Dataset for Multiple-Object Tracking and Behavior Analysis

预印本

TextFake: Benchmarking AI-Generated Image Detection on Text-Rich Images

MFEN:Multi-Frequency Expert Network for Visible-Infrared Person Re-ID

PlanGuard: A Guardrail for Multi-Step Plan Safety in Embodied Agents

Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation

TimeSteer: Inference-Time Speech Scheduling in Joint Audio-Visual Diffusion Models

Yesterday's Shield, Today's Spear: A Self-Evolving Safety Guardrail in Production

Semantic Relation-Enhanced CLIP Adapter for Domain Adaptive Zero-Shot Learning

Frame-Difference Guided Dynamic Region Perception for CLIP Adaptation in Text-Video Retrieval

MultiModal-GPT: A Vision and Language Model for Dialogue with Humans

研究方向