Titlebook: Deep Learning for Video Understanding; Zuxuan Wu,Yu-Gang Jiang Book 2024 The Editor(s) (if applicable) and The Author(s), under exclusive

ORBIT

Overview of Video Understanding,tal media, video owns the unique charm of conveying rich and vivid information, making it more and more popular on various social platforms. At the same time, video understanding techniques, which aim to recognize the objects and actions within videos and analyze their temporal evolution, are gainin

discord

令人悲傷

血友病

Deep Learning for Video Localization,wever, video recognition is limited in understanding the overall event that exists in a video, without a fine-grained analysis of video segments. To compensate for the limitations of video recognition, video localization provides an accurate and comprehensive understanding of videos by predicting wh

Ancestor

BLANC

Unsupervised Feature Learning for Video Understanding,of large-scale training datasets. Vast amounts of annotated data have led to the growth in the performance of supervised learning; nevertheless, manual collection and annotation are demanding of time and labor. Subsequently, research interests have been aroused in unsupervised feature learning that

epidermis

Efficient Video Understanding,a result, the development of efficient deep video models and training strategies is necessary for practical video understanding applications. In this chapter, we will delve into the design choices for creating compact video understanding models, such as CNNs and Transformers. Furthermore, we will ex

偽造

Conclusion and Future Directions,hapters. Furthermore, this chapter will also look into the future of deep-learning-based video understanding by briefly discussing several promising directions, e.g., the construction of large-scale video foundation models, the application of large language models (LLMs) in video understanding, etc.

alcohol-abuse

商業(yè)上