Article Preview
TopWith the development of a variety of interactive design platforms and software, micro-videos with interactive functions have emerged in an endless stream. The development of the internet has promoted the development of micro-video with interactive functions in the field of internet advertising, television, and education. At present, micro videos integrated with interaction design have been spread on the network. For example, interaction design is applied in interactive movies, where the audience can choose the beginning and end of the movie by themselves. In such a case video has to adapt to multiple interactions in a video broadcast platform; in addition, an online teaching platform also provides learners with a combination of interaction design technology in courses with a series of short videos. Mainly through human interaction, learners interact with content and other learners using the interface interaction design, in such concrete forms as barrage, embedded, hyperlinks, etc. (Tian & Tsai 2021). Scholars in this field, as shown in Table 1, have made progress, which can be divided into two aspects: interaction design development in micro-video and application research of interaction design in micro-video (Gao, 2018). Interaction design-related technologies developed earlier in foreign countries, with high maturity, and are applied mostly in human-computer interaction, APP design, digital media, and other commercial fields. The integration of interaction design in different fields aims to enhance users' positive experience and create easy-to-use interactive products to a certain extent. Interaction design was first used in advertising to enhance public participation in products and attract consumers, so as to achieve the ideal marketing purpose.
Table 1. Research Topics and Methods of Related Research
Author/Year | Research Topic | Method/Model |
---|
Wu et. al., 2015
| Video classification
| Hybrid deep learning framework with two CNNs for spatial and short-term motion features
|
Yao et. al., 2015
| Video description generation
| Approach considering both local and global temporal structure
|
Xiong et. al., 2017
| Crowd counting
| ConvLSTM model to exploit temporal information
|
He et. al., 2019
| Video spatial-temporal modeling
| Novel spatial-temporal network (StNet) architecture
|
Isobe et. al., 2020
| Video super-resolution
| Comparison of 2D CNN, 3D CNN, and RNN for temporal modeling
|
Fu et. al., 2021
| Video language modeling
| VIOLET network with Masked Visual-token Modeling pre-training task
|
Nir et. al., 2022
| Semantic representation for cartoons/animation videos
| Method for refining semantic representation for specific animated content
|
Wang et. al., 2022
| Video spatial-temporal modeling
| Video Mobile-Former with 3D-CNNs and Transformer modules
|
Li et. al., 2022
| Video matting
| VMFormer, a Transformer-based end-to-end method
|
Zhao et. al., 2022
| Human modeling and rendering | Comprehensive neural approach based on dense multi-view videos |