Meng Cheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Meng Cheng has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Hanli Wang
Tongji University, Shanghai, China
2 shared publications Pengjie Tang
College of Electronics & Information Engineering, and Jiangxi Engineering Laboratory of IoT Technologies for Crop Growth, Jinggangshan University, Ji’an, Jiangxi, P. R. China
1 shared publicationQinyu Li
Department of Computer Science & Technology, the Key Laboratory of Embedded Systemand Service Computing (Ministry of Education), and Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, P. R. China
1 shared publicationYu Long
Department of Computer Science and Technology, Tongji University, Shanghai, China
1 shared publication
Latest Publications
- 11 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (4) , 2158-2169
Meta-Learning-Based Incremental Few-Shot Object Detection
Recent years have witnessed meaningful progress in the task of few-shot object detection. However, most of the existing models are not capable of incremental learning with a few samples, i.e. , the detector can’t detect novel-class objects by using only a few samples of novel classes (without revisiting the original training samples) while maintaining the performances on base classes. This is largely because of catastrophic forgetting, which is a general phenomenon in few-shot learning that the incorporation of the unseen information ( e.g. , novel-class objects) will lead to a serious loss of the knowledge learnt before ( e.g. , base-class objects). In this paper, a new model is proposed for incremental few-shot object detection, which takes CenterNet as the fundamental framework and redesigns it by introducing a novel meta-learning method to make the model adapted to unseen knowledge while overcoming forgetting to a great extent. Specifically, a meta-learner is trained with the base-class samples, providing the object locator of the proposed model with a good weight initialization, and thus the proposed model can be fine-tuned easily with few novel-class samples. On the other hand, the filters correlated to base classes are preserved when fine-tuning the proposed model with the few samples of novel classes, which is a simple but effective solution to mitigate the problem of forgetting. The experiments on the benchmark MS COCO and PASCAL VOC datasets demonstrate that the proposed model outperforms the state-of-the-art methods by a large margin in the detection performances on base classes and all classes while achieving best performances when detecting novel-class objects in most cases. The project page can be found in https://mic.tongji.edu.cn/e6/d5/c9778a190165/page.htm .
- 11 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (4) , 2158-2169
Meta-Learning-Based Incremental Few-Shot Object Detection
Recent years have witnessed meaningful progress in the task of few-shot object detection. However, most of the existing models are not capable of incremental learning with a few samples, i.e. , the detector can’t detect novel-class objects by using only a few samples of novel classes (without revisiting the original training samples) while maintaining the performances on base classes. This is largely because of catastrophic forgetting, which is a general phenomenon in few-shot learning that the incorporation of the unseen information ( e.g. , novel-class objects) will lead to a serious loss of the knowledge learnt before ( e.g. , base-class objects). In this paper, a new model is proposed for incremental few-shot object detection, which takes CenterNet as the fundamental framework and redesigns it by introducing a novel meta-learning method to make the model adapted to unseen knowledge while overcoming forgetting to a great extent. Specifically, a meta-learner is trained with the base-class samples, providing the object locator of the proposed model with a good weight initialization, and thus the proposed model can be fine-tuned easily with few novel-class samples. On the other hand, the filters correlated to base classes are preserved when fine-tuning the proposed model with the few samples of novel classes, which is a simple but effective solution to mitigate the problem of forgetting. The experiments on the benchmark MS COCO and PASCAL VOC datasets demonstrate that the proposed model outperforms the state-of-the-art methods by a large margin in the detection performances on base classes and all classes while achieving best performances when detecting novel-class objects in most cases. The project page can be found in https://mic.tongji.edu.cn/e6/d5/c9778a190165/page.htm .
- 10 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 24 (15209210) , 715-727
Emotion Expression With Fact Transfer for Video Description
Translating a video into natural language is a fundamental but challenging task in visual understanding, since there is a great gap between visual content and linguistic sentence. More attention has been paid to this research field and a number of state-of-the-art results are achieved in recent years. However, the emotions in videos are usually overlooked, leading to the generated description sentences being boring and colorless. In this work, we construct a new dataset for video description with emotion expression, which consists of two parts: a re-annotated subset of the MSVD dataset with emotion embedded and another subset annotated with long sentences and rich emotions based on a video emotion recognition dataset. A fact transfer based framework is designed, which incorporates a fact stream and an emotion stream to generate sentences with emotion expression for video description. In addition, we propose a novel approach for sentence evaluation by balancing facts and emotions. A group of experiments are conducted, and the experimental results demonstrate the effectiveness of the proposed methods, including the idea of dataset construction for video description with emotion expression, model training and testing, and the emotion evaluation metric. The project page (including the code and dataset) can be found in https://mic.tongji.edu.cn/ce/70/c9778a183920/page.htm .
- 10 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 24 (15209210) , 715-727
Emotion Expression With Fact Transfer for Video Description
Translating a video into natural language is a fundamental but challenging task in visual understanding, since there is a great gap between visual content and linguistic sentence. More attention has been paid to this research field and a number of state-of-the-art results are achieved in recent years. However, the emotions in videos are usually overlooked, leading to the generated description sentences being boring and colorless. In this work, we construct a new dataset for video description with emotion expression, which consists of two parts: a re-annotated subset of the MSVD dataset with emotion embedded and another subset annotated with long sentences and rich emotions based on a video emotion recognition dataset. A fact transfer based framework is designed, which incorporates a fact stream and an emotion stream to generate sentences with emotion expression for video description. In addition, we propose a novel approach for sentence evaluation by balancing facts and emotions. A group of experiments are conducted, and the experimental results demonstrate the effectiveness of the proposed methods, including the idea of dataset construction for video description with emotion expression, model training and testing, and the emotion evaluation metric. The project page (including the code and dataset) can be found in https://mic.tongji.edu.cn/ce/70/c9778a183920/page.htm .