孔权｜武汉工程大学｜学者主页

2026

FindIt: A Format-Informed Visual Detection Benchmark for Generalist Multimodal LLMs

Eshika Khandelwal, Jingjing Pan, Ming-Fang Zhang, Quan Kong, Lorenzo Garattoni, Hildegard Kuehne

arXiv.org

2026

TrajTok: Learning Trajectory Tokens enables better Video Understanding

Chenhao Zheng, Jieyu Zhang, Jianing Zhang, Weikai Huang, Ashutosh Kumar, Quan Kong, O. Tuzel, Chun-Liang Li, Ranjay Krishna

arXiv.org

DOI

2026

CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering

Ming-Fang Zhang, Jingjing Pan, Ashutosh Kumar, Rajat Saini, M. Erdoğan, Hsuan-Kung Yang, Cai-Xin Kang, Yifei Huang, Yoichi Sato, Quan Kong

arXiv.org

DOI

2026

Vision-TTT: Efficient and Expressive Visual Representation Learning with Test-Time Training

Quan Kong, Y. Xiao, Yuhao Shen, Cong Wang

arXiv.org

DOI

2026

ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding

Quan Kong, Yuhao Shen, Yi-Cheng Ji, Huan Li, Cong Wang

arXiv.org

DOI

2026

Where to Look Matters: Learning Influential Views for VLM-based 3D Visual Grounding

Tsung-Chih Chiang, Hsuan-Kung Yang, Jou-Min Liu, Ting-Ru Liu, Chun-Wei Huang, Quan Kong, Chun-Yi Lee

2026

InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding

Ashutosh Kumar, Rajat Saini, J. Pan, M. Erdoğan, Ming-Fang Zhang, Betty Le Dem, N. Kobori, Quan Kong

arXiv.org

DOI

2025

Region-Adaptive Fusion for Infrared and Visible Images with DINO Guidance

Jialian Zhang, M.M. Zheng, Jinglei Li, Quan Kong, Q M Liao

International Conference on Computer, Artificial Intelligence and Control Engineering (CAICE)

DOI

2025

The 9th AI City Challenge

Zheng-Hang Tang, Shuo Wang, D. Anastasiu, Ming-Ching Chang, Anuj Sharma, Quan Kong, N. Kobori, Munkhjargal Gochoo, Ganzorig Batnasan, Munkh-Erdene Otgonbold, F. Alnajjar, Jun-Wei Hsieh, Tomasz Kornuta, Xiao-Long Li, Yi-Lin Zhao, Han Zhang, Subhashree Radhakrishnan, Arihant Jain, Ratnesh Kumar, Vidya N. Murali, Yu-Xing Wang, S. Pusegaonkar, Yi-Zhou Wang, Sujit Biswas, Xun-Lei Wu, Zhe-Dong Zheng, Pranamesh Chakraborty, Rama Chellappa

2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

DOI

2025

One Trajectory, One Token: Grounded Video Tokenization Via Panoptic Sub-Object Trajectory

Chenhao Zheng, Jie-Yu Zhang, Mohammadreza Salehi, Ziqi Gao, Vishnu Iyengar, N. Kobori, Quan Kong, Ranjay Krishna

IEEE International Conference on Computer Vision

DOI

2025

Synthetic Visual Genome

J. Park, Zixian Ma, Lin-Jie Li, Chenhao Zheng, Cheng-Yu Hsieh, Ximing Lu, K. Chandu, Quan Kong, N. Kobori, Ali Farhadi, Ye-Jin Choi, Ranjay Krishna

Computer Vision and Pattern Recognition

DOI

2025

GA3CE: Unconstrained 3D Gaze Estimation with Gaze-Aware 3D Context Encoding

Yuki Kawana, Shintaro Shiba, Quan Kong, N. Kobori

Computer Vision and Pattern Recognition

DOI

2024

Multi-Level Adaptive Attention Fusion Network for Infrared and Visible Image Fusion

Ziming Hu, Quan Kong, Qing Liao

IEEE Signal Processing Letters

DOI

2024

WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding

Quan Kong, Yuki Kawana, R. Saini, Ashutosh Kumar, Jingjing Pan, Tao Gu, Yohei Ozao, Istvan Balazs Opra, D. Anastasiu, Yoichi Sato, N. Kobori

European Conference on Computer Vision

DOI

2024

Reprojection Errors as Prompts for Efficient Scene Coordinate Regression

Ting-Ru Liu, Hsuan-Kung Yang, Jou-Min Liu, Chun-Wei Huang, Tsung-Chih Chiang, Quan Kong, N. Kobori, Chun-Yi Lee

European Conference on Computer Vision

DOI

2024

The 8th AI City Challenge

Shuo Wang, D. Anastasiu, Zheng-Hang Tang, Ming-Ching Chang, Yue Yao, Liang Zheng, M. Rahman, Meenakshi S. Arya, Anuj Sharma, Pranamesh Chakraborty, Sanjita Prajapati, Quan Kong, N. Kobori, Munkhjargal Gochoo, Munkh-Erdene Otgonbold, F. Alnajjar, Ganzorig Batnasan, Ping-Yang Chen, Jun-Wei Hsieh, Xun-Lei Wu, S. Pusegaonkar, Yi-Zhou Wang, Sujit Biswas, Rama Chellappa

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

DOI

2023

Infrared and Visible Image Fusion via Attention-Based Adaptive Feature Fusion

Lei Wang, Ziming Hu, Quan Kong, Qian Qi, Qing Liao

Entropy

DOI

2023

Remote Sensing Image Super-Resolution With Residual Split Attention Mechanism

Xitong Chen, Yuntao Wu, Tao Lü, Quan Kong, Jiaming Wang, Yu Wang

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

DOI

2023

DeCo: Decomposition and Reconstruction for Compositional Temporal Grounding via Coarse-to-Fine Contrastive Ranking

Lijin Yang, Quan Kong, Hsuan-Kung Yang, W. Kehl, Yoichi Sato, N. Kobori

Computer Vision and Pattern Recognition

DOI

2023

LAC - Latent Action Composition for Skeleton-based Action Segmentation

Di Yang, Yaohui Wang, A. Dantcheva, Quan Kong, L. Garattoni, G. Francesca, F. Brémond

IEEE International Conference on Computer Vision

DOI

2023

Self-Supervised Video Representation Learning via Latent Time Navigation

Di Yang, Yaohui Wang, Quan Kong, A. Dantcheva, L. Garattoni, G. Francesca, F. Brémond

AAAI Conference on Artificial Intelligence

DOI

2023

Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detection

S. Majhi, Rui Dai, Quan Kong, L. Garattoni, G. Francesca, F. Brémond

Computer Vision and Image Understanding

DOI

2022

基于CBAM-Res2Net的人群计数算法

陈江川，吴云韬，孔权

《武汉工程大学学报》

2022

NormFuse: Infrared and Visible Image Fusion With Pixel-Adaptive Normalization

Quan Kong, Huabing Zhou, Yuntao Wu

IEEE/CAA Journal of Automatica Sinica

DOI

2022

Hierarchical contrastive adaptation for cross-domain object detection

Ziwei Deng, Quan Kong, Naoto Akira, Tomoaki Yoshinaga

Machine Vision and Applications

DOI

2022

Efficient and Accurate Skeleton-Based Two-Person Interaction Recognition Using Inter-and Intra-Body Graphs

Yoshiki Ito, Quan Kong, Kenichi Morita, Tomoaki Yoshinaga

International Conference on Information Photonics

DOI

2021

Robust Unsupervised Multi-Object Tracking In Noisy Environments

Chao-Han Huck Yang, Mohit Chhabra, Yi-Chieh Liu, Quan Kong, Tomoaki Yoshinaga, Tomokazu Murakami

International Conference on Information Photonics

DOI

2021

Multi-Stream Adaptive Graph Convolutional Network Using Inter- and Intra-Body Graphs for Two-Person Interaction Recognition

Yoshiki Ito, Kenichi Morita, Quan Kong, Tomoaki Yoshinaga

IEEE Access

DOI

2021

A Multi-Modal Fusion Approach for Audio-Visual Scene Classification Enhanced by CLIP Variants

Soichiro Okazaki, Quan Kong, Tomoaki Yoshinaga

Workshop on Detection and Classification of Acoustic Scenes and Events

2020

Hitachi at TRECVID DSDI 2020

Soichiro Okazaki, Quan Kong, Martin Klinkigt, Tomoaki Yoshinaga

TREC Video Retrieval Evaluation

2020

Cycle-Contrast for Self-Supervised Video Representation Learning

Quan Kong, Wen-Peng Wei, Ziwei Deng, Tomoaki Yoshinaga, Tomokazu Murakami

Neural Information Processing Systems

2019

Active Generative Adversarial Network for Image Classification

Quan Kong, Bin Tong, Martin Klinkigt, Yuki Watanabe, Naoto Akira, Tomokazu Murakami

AAAI Conference on Artificial Intelligence

DOI

2019

MMAct: A Large-Scale Dataset for Cross Modal Human Action Understanding

Quan Kong, Ziming Wu, Ziwei Deng, Martin Klinkigt, Bin Tong, Tomokazu Murakami

IEEE International Conference on Computer Vision

DOI

2019

Towards Efficient Instance Segmentation with Hierarchical Distillation

Ziwei Deng, Quan Kong, Tomokazu Murakami

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

DOI

2018

Adversarial Zero-shot Learning With Semantic Augmentation

Bin Tong, Martin Klinkigt, Jun-Wen Chen, Xian-Kun Cui, Quan Kong, Tomokazu Murakami, Yoshiyuki Kobayashi

AAAI Conference on Artificial Intelligence

DOI

2016

Egocentric Video Search via Physical Interactions

Taiki Miyanishi, Jun-ichiro Hirayama, Quan Kong, Takuya Maekawa, H. Moriya, Takayuki Suyama

AAAI Conference on Artificial Intelligence

DOI

2014

Reusing training data with generative/discriminative hybrid model for practical acceleration-based activity recognition

Quan Kong, Takuya Maekawa

Computing

DOI

精选作品

期刊论文

FindIt: A Format-Informed Visual Detection Benchmark for Generalist Multimodal LLMs

TrajTok: Learning Trajectory Tokens enables better Video Understanding

CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering

Vision-TTT: Efficient and Expressive Visual Representation Learning with Test-Time Training

ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding

Where to Look Matters: Learning Influential Views for VLM-based 3D Visual Grounding

InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding

Region-Adaptive Fusion for Infrared and Visible Images with DINO Guidance

The 9th AI City Challenge

One Trajectory, One Token: Grounded Video Tokenization Via Panoptic Sub-Object Trajectory

Synthetic Visual Genome

GA3CE: Unconstrained 3D Gaze Estimation with Gaze-Aware 3D Context Encoding

Multi-Level Adaptive Attention Fusion Network for Infrared and Visible Image Fusion

WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding

Reprojection Errors as Prompts for Efficient Scene Coordinate Regression

The 8th AI City Challenge

Infrared and Visible Image Fusion via Attention-Based Adaptive Feature Fusion

Remote Sensing Image Super-Resolution With Residual Split Attention Mechanism

DeCo: Decomposition and Reconstruction for Compositional Temporal Grounding via Coarse-to-Fine Contrastive Ranking

LAC - Latent Action Composition for Skeleton-based Action Segmentation

Self-Supervised Video Representation Learning via Latent Time Navigation

Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detection

基于CBAM-Res2Net的人群计数算法

NormFuse: Infrared and Visible Image Fusion With Pixel-Adaptive Normalization

Hierarchical contrastive adaptation for cross-domain object detection

Efficient and Accurate Skeleton-Based Two-Person Interaction Recognition Using Inter-and Intra-Body Graphs

Robust Unsupervised Multi-Object Tracking In Noisy Environments

Multi-Stream Adaptive Graph Convolutional Network Using Inter- and Intra-Body Graphs for Two-Person Interaction Recognition

A Multi-Modal Fusion Approach for Audio-Visual Scene Classification Enhanced by CLIP Variants

Hitachi at TRECVID DSDI 2020

Cycle-Contrast for Self-Supervised Video Representation Learning

Active Generative Adversarial Network for Image Classification

MMAct: A Large-Scale Dataset for Cross Modal Human Action Understanding

Towards Efficient Instance Segmentation with Hierarchical Distillation

Adversarial Zero-shot Learning With Semantic Augmentation

Egocentric Video Search via Physical Interactions

Reusing training data with generative/discriminative hybrid model for practical acceleration-based activity recognition

会议论文

Arbitrary style transfer method based on semantic segmentation

研究方向