Movie Tags Prediction and Segmentation Using Deep Learning

Khan, Umair Ali; Amor, Miguel Ángel Martínez del; Altowaijri, Saleh M.; Ahmed, Adnan; Rahman, Atiq Ur; Sama, Najm Us; Haseeb, Khalid; Islam, Naveed

doi:10.1109/access.2019.2963535

Cited by 19 publications

(9 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…He regards instinct as a kind of force, which is the force and inner drive that can arouse people's behavior and divides it into two categories: life instinct and death instinct [22]. Freud believed that desire is also a kind of energy, which is in the unconscious like instinct, and desire can also cause people to act to satisfy themselves [23]. There is no strict distinction between the concepts of desire and instinct in Freud.…”

Section: Discussionmentioning

confidence: 99%

The Subject Construction and Role Mental Model Construction of Erotic Movies Based on Lacan’s Desire Theory

Feng

2022

Occupational Therapy International

View full text Add to dashboard Cite

Jacques Lacan is a famous French psychoanalyst, but his influence has long gone beyond the scope of psychoanalysis and has affected almost all fields of “human science.” Film and psychoanalysis coincided almost simultaneously and influenced each other. But with the development of film, researchers found that film studies in the period of classic film and film semiotics have come to an end. It has certain theoretical value to explore the construction of the subject and the mental model of the erotic film based on Lacan’s desire theory. Method. The body in the film and video described in this paper includes both the material body as an aesthetic object and the spiritual body with aesthetic consciousness. The so-called artistic presentation of the body element means that the beauty of the body form displayed by the actor’s body in the film video is perceived by the audience, and the desire to stare is captured by the audience, thereby completing the audience’s entire body composed of eyes, body, and mind. The body is not only an aesthetic object but also an aesthetic subject, and the human cognitive system is not just a closed brain. Because the nervous system, body, and environment are constantly changing and interacting, true cognition is a unified system of all three. The main part of this paper uses Lacan’s psychoanalytic theory to deeply analyze the relationship between the characters shown in the film. From the cognitive impairment of the self to the failure of communication between characters, the language of uncertainty entangled by desire is removed, and the behavior and facial expressions of the movie characters are used as the analysis basis to fully interpret the inner world of the characters. This includes love, hatred, pain, struggle, and many other contradictory emotions. In addition, this paper also analyzes the metaphor of the relationship between the characters from the perspective of semiotics and discusses the description of the relationship between the characters from the lens language from the perspective of cinematography. The special meaning conveyed by the recurring elements in the film is emphasized, and the correlation between the pictures is explained from the less mentioned photographic aspect of the film. Results/Discussion. Looking at Lacan’s theory, the subject, the other, and desire are linked by the subject spirit, which is the core of the connection between the three, and only through the resistance and struggle of the subject spirit can the illusion of the subject be broken. Bewilderment and the suppression of the other and desire finally become the self. And the embodiment of this true self is particularly prominent in film art. Lacan’s purpose is not merely to dissolve the subject but to seek a stand in the midst of destruction, pursuing the ultimate transcendence of man’s desire for the external other and internal desire.

show abstract

Section: Discussionmentioning

confidence: 99%

The Subject Construction and Role Mental Model Construction of Erotic Movies Based on Lacan’s Desire Theory

Feng

2022

Occupational Therapy International

View full text Add to dashboard Cite

show abstract

“…The most common architectures for video classification are fundamentally based on the RNN and CNN architectures; classification accuracy is one of the most common evaluation metrics; UCF-101 and Sports-1M datasets are the choice for validation in most cases, multi-class classification problem is considered in almost all cases, SMART blocks outperform 3D convolutions in terms of spatiotemporal feature learning, and average fusion, kernel average fusion, weighted fusion, logistic regression fusion, and MKL fusion are all proven to be inferior compared to the multi-stream multi-class fusion technique. Moreover, a more applied form of classification in videos is to identify/recommend tags or thumbnails in videos, and this specific task is successfully caried out in [75][76][77][78][79].…”

Section: Summary Of Some Notable Deep Learning Framework Developmentsmentioning

confidence: 99%

On the Use of Deep Learning for Video Classification

et al. 2023

View full text Add to dashboard Cite

The video classification task has gained significant success in the recent years. Specifically, the topic has gained more attention after the emergence of deep learning models as a successful tool for automatically classifying videos. In recognition of the importance of the video classification task and to summarize the success of deep learning models for this task, this paper presents a very comprehensive and concise review on the topic. There are several existing reviews and survey papers related to video classification in the scientific literature. However, the existing review papers do not include the recent state-of-art works, and they also have some limitations. To provide an updated and concise review, this paper highlights the key findings based on the existing deep learning models. The key findings are also discussed in a way to provide future research directions. This review mainly focuses on the type of network architecture used, the evaluation criteria to measure the success, and the datasets used. To make the review self-contained, the emergence of deep learning methods towards automatic video classification and the state-of-art deep learning methods are well explained and summarized. Moreover, a clear insight of the newly developed deep learning architectures and the traditional approaches is provided. The critical challenges based on the benchmarks are highlighted for evaluating the technical progress of these methods. The paper also summarizes the benchmark datasets and the performance evaluation matrices for video classification. Based on the compact, complete, and concise review, the paper proposes new research directions to solve the challenging video classification problem.

show abstract

“…al. [55] proposed a deep learning based algorithm for movie tags prediction and segmentation. In this work, the authors constructed a tag vocabulary and created a dataset for the vocabulary.…”

Section: Related Workmentioning

confidence: 99%

Predicting Actions in Videos and Action-Based Segmentation Using Deep Learning

et al. 2021

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a technique to recognize multiple actions in a video using deep learning. The proposed approach is concerned with interpreting the overall context of a video and transforming it into one or more appropriate actions. In order to cope with multiple actions in a video, our proposed technique first determines the individual segments/shots in a video using intersections of color histograms. The segmented parts are then fed to the action recognition system comprising a combination of a Convolution Neural Network (CNN) and a Long-Short-Term Memory (LSTM) network trained on our action vocabulary. The segments are then labeled according to their predicted actions and a compact set of distinct actions is produced. Using the corpus generated by the shot detection phase, which includes the location of key frames in shots, and start/end timestamps of a shot, we can also perform video segmentation based on an action query. Hence, the proposed technique can be used for a number of tasks such as content censoring, on-demand scene retrieval, video summarizing, and query based scene/video retrieval, to name a few. The proposed technique also stands aprat from the existing approaches which either do not take into account the motion information for action prediction or do not perform action-based video segmentation. The experimental results presented in this paper show that the proposed technique not only finds the the complete set of actions present in the video, but can also find all the relevant parts in a video based on an action query.

show abstract

Movie Tags Prediction and Segmentation Using Deep Learning

Cited by 19 publications

References 46 publications

The Subject Construction and Role Mental Model Construction of Erotic Movies Based on Lacan’s Desire Theory

The Subject Construction and Role Mental Model Construction of Erotic Movies Based on Lacan’s Desire Theory

On the Use of Deep Learning for Video Classification

Predicting Actions in Videos and Action-Based Segmentation Using Deep Learning

Contact Info

Product

Resources

About