Humor is an important part of personal communication. How to create a computational model to recognize humor is still a very challenging task in natural language processing and linguistics. In this survey, we applied some rules to leave 29 articles spanning 10 years (2012 to 2023). The main elements covered by this survey include: recent state-of-the-art detection methods using deep learning from years 2012-2023, (2) summarizing features for humor detection from a linguistic perspective, (3) humor detection datasets, evaluation metrics, data domains and languages, (4) some tricks used in humor detection (e.g. Attention mechanism, multimodal), (5) recognizing open problems and highlight the feasible opportunities for future research directions. To the best of our knowledge, this is the first systematic survey for humor detection using deep learning. The survey can be used to assist novice and prominent researchers to understand the concept of humor, popular method and future research direction and so on.
Abstract Humor is an important part of personal communication. How to create a computational model to recognize humor is still a very challenging task in natural language processing [...]
'''In multi-object tracking of Intelligent Transportation System, there are objects of different sizes in images or videos, especially pedestrian and traffic lights with low resolution in the image. Meantime, objects are subject to occlusion or loss in object tracking. All of the above-mentioned situations may lead to unsatisfactory multi-object tracking results. Attracted by the effect of deep convolution neural networks, the paper proposes a multi-object tracking network, CNN-Based Multi-Object Tracking Networks with Position Correction and IMM (CNN_PC_IMM) to solve those problems. Our proposed method consists of object detection module and object tracking module. Compared to other networks, our proposed network has several main contributions that play an essential role in achieving state-of-the-art object tracking performance. In the detection phase, the feature fusion technique is used. We add a scale branch to the YOLOv3 network to increase the accuracy of small object prediction and import a residual structure to enhance gradient propagation and avoid gradient disappearance and explosion for the whole network. In addition, we determine the size of the anchor box based on the size of the object in the dataset to better detect and track the objects. In the tracking phase, IMM is used to calculate the motion state information of the object at a certain moment. Next, the optimization algorithm is proposed to fine-tune object position when the tracking object is occluded due to dense multi-object in traffic scenes or lost due to incomplete object information. Finally, experimental results and analysis are performed on the MOT16 benchmark dataset with several popular tracking algorithms used to compare the performance with the proposed algorithm in the paper. It is demonstrated that the proposed network has better performance on MOPA, MOTP, ML.
Abstract '''In multi-object tracking of Intelligent Transportation System, there are objects of different sizes in images or videos, especially pedestrian and traffic lights [...]
Humor detection using deep learning in 10 years: A survey 
