发表的论文、专著、教材:
[1] Ruohong Huan, Guowei Zhong, Peng Chen, and Ronghua Liang. MulDeF: A Model-Agnostic Debiasing Framework for Robust Multimodal Sentiment Analysis. IEEE Transactions on Multimedia. DOI: 10.1109/TMM.2024.3521836.
[2] Ruohong Huan, Guowei Zhong, Peng Chen, and Ronghua Liang. UniMF: A Unified Multimodal Framework for Multimodal Sentiment Analysis in Missing Modalities and Unaligned Multimodal Sequences. IEEE Transactions on Multimedia. 2024, Vol. 26, 5753-5768.
[3] Ruohong Huan, Guowei Zhong, Peng Chen, and Ronghua Liang. TriSAT: Trimodal Representation Learning for Multimodal Sentiment Analysis. IEEE/ACM Transactions on Audio, Speech and Language Processing. 2024, Vol. 32, 4105-4120.
[4] Ruohong Huan, Xin Zhao, Nan Gao, Peng Chen, and Ronghua Liang. TLCSFI: A Pose-Guided Person Re-Identification Method with Two-Level Channel-Spatial Feature Integration. International Journal of Pattern Recognition and Artificial Intelligence. 2024, 38(14): 2455016-1-2455016-25.
[5] Ruohong Huan, Ai Bo, Jia Shu, Peng Chen and Ronghua Liang. Two-Domain joint attention mechanism based on sensor data for group activity recognition. IEEE Transactions on Instrumentation and Measurement, 2023, Vol.72, 1-15.
[6] Ruohong Huan, Ji Zhang, Chaojie Xie, Ronghua Liang, Peng Chen. MLFFCSP: a new anti-occlusion pedestrian detection network with multi-level feature fusion for small targets. Multimedia Tools and Applications, 2023,82(19): 29405–29430.
[7] Ruohong Huan, Shuaishuai Zheng, Chaojie Xie, Peng Chen, and Ronghua Liang. DOMOPT: A Detection-Based Online Multi-Object Pedestrian Tracking Network for Videos. International Journal of Pattern Recognition and Artificial Intelligence, 2023, 37(9):1-22.
[8] Ruohong Huan, Tianya Chen, Ziwei Zhan, Peng Chen, and Ronghua Liang. HPAN: A Hybrid Pose Attention Network for Person Re-Identification. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV). Xiamen, China, 10.13-10.15, 2023, published in 2024, pp. 198-211.
[9] Ruohong Huan, Chengxi Jiang, Luoqi Ge, Jia Shu, Ziwei Zhan, Peng Chen, Kaikai Chi, Ronghua Liang. Human complex activity recognition with sensor data using multiple features. IEEE Sensors Journal, 2022, 22(1): 757-775.
[10] Ruohong Huan, Ziwei Zhan, Luoqi Ge, Kaikai Chi, Peng Chen, Ronghua Liang. A hybrid CNN and BLSTM network for human complex activity recognition with multi-feature fusion. Multimedia Tools and Applications, 2021, 80(30): 36159-36182.
[11] Ruohong Huan, Jia Shu, Shenglin Bao, Ronghua Liang, Peng Chen, Kaikai Chi. Video multimodal emotion recognition based on Bi-GRU and attention fusion. Multimedia Tools and Applications, 2021, 80(6): 8213-8240.
[12] Ruohong Huan, Luoqi Ge, Peng Yang, Chaojie Xie, Kaikai Chi, Keji Mao, Yun Pan. SAR multi-target interactive motion recognition based on convolutional neural networks. IET Image Processing, 2020, 14(11): 2567-2578.
[13] Ruo-Hong Huan, Chao-Jie Xie, Feng Guo, Kai-kai Chi, Ke-ji Mao, Ying-Long Li, Yun Pan. Human action recognition based on HOIRM feature fusion and AP clustering BOW. PLoS ONE, 2019, 14(7): e0219910.
[14] Ruohong Huan, Shenglin Bao, Chu Wang, Yun Pan. Anti-occlusion particle filter object-tracking method based on feature fusion. IET Image Processing, 2018, 12(9): 1519-1530.
[15] Ruohong Huan, Chu Wang, Yun Pan, Feng Guo, Yifan Tao. New structure for multi-aspect SAR image target recognition with multi-level joint consideration. Multimedia Tools and Applications, 2016, Vol.75, 7519-7540.
科研成果及专利:
[1] 宦若虹,谢超杰,基于CSP模型的多级特征融合行人检测方法,2024.9.27,中国,ZL202110295911.1
[2] 宦若虹,鲍晟麟,葛罗棋,谢超杰,基于融合注意力网络的多模态情感识别方法,2023.1.31,中国,ZL201910324053.1
[3] 宦若虹,鲍晟麟,葛罗棋,谢超杰,基于双向门控循环单元网络和新型网络初始化的情感识别方法,2023.1.31,中国,ZL201910298018.7
[4] 宦若虹,葛罗棋,吴炜,基于数据分离多尺度特征结合的人体复杂行为识别方法,2022.4.5,中国,ZL202010258727.5
[5] 宦若虹,葛罗棋,吴炜,基于多特征融合CNN-BLSTM的人体复杂行为识别方法,2022.4.5,中国,ZL201911240544.4
[6] 宦若虹,王楚,陶一凡,陈月,杨鹏,一种抗遮挡的基于积分直方图的粒子滤波目标跟踪方法,2021.1.1, 中国,ZL201610419913.6
[7] 宦若虹,郭峰,王楚,一种基于HOIRM和局部特征融合的行为识别方法,2019.2.12,中国,ZL201610184680.6
[8] 宦若虹,陈月,陶一凡,杨鹏,一种基于地图信息和位置自适应修正的粒子滤波室内定位方法,2019.7.5,中国,ZL201611007033.4
[9] 宦若虹,陶一凡,陈月,杨鹏,鲍晟霖,基于多线性主成分分析和张量分析的SAR图像目标识别方法,2019.5.31,中国,ZL201611074915.2
[10] 宦若虹,陶一凡,陈月,杨鹏,鲍晟霖,基于小波变换空间变迹的SAR图像旁瓣抑制方法,2019.3.12,中国,ZL201710126873.0
[11] 宦若虹,陈月,陶一凡,杨鹏,一种基于特征增强和决策融合的行为识别方法,2018.12.18,中国,ZL201610182598.X
[12] 宦若虹,王楚,陈月,陶一凡,杨鹏,一种基于颜色与局部二值模式特征融合的抗遮挡粒子滤波目标跟踪方法,2018.9.7,中国,ZL201610454063.3
[13] 宦若虹,潘赟,於正强,王楚,一种结合相邻帧差法和混合高斯模型的运动目标检测方法,2017.6.13,中国,ZL201310586151.5
[14] 宦若虹,潘赟,王楚,郭峰,多层次结合的多视合成孔径雷达图像目标识别方法,2017.2.22,中国,ZL201410151472.7
[15] 宦若虹,唐晓梅,王浙沪,陈庆章,一种基于粒子位置调整的粒子滤波视频运动目标跟踪方法, 2014.3.26,中国,ZL201110204821.3
[16] 宦若虹,唐晓梅,王浙沪,陈庆章,一种基于累加直方图粒子滤波的视频运动目标跟踪方法, 2013.4.17,中国,ZL201110101737.9
[17] 宦若虹,王浙沪,唐晓梅,陈庆章,一种基于非负矩阵分解和隐马尔科夫模型的人体行为识别方法, 2013.4.24,中国,ZL201110181112.8
[18] 宦若虹,王浙沪,唐晓梅,陈庆章,一种视频监控中基于角度的徘徊轨迹检测方法, 2012.8.22,中国,ZL201110028707.X