An Attention-based Hybrid 2D/3D CNN-LSTM for Human Action Recognition

Bayoudh, Khaled; Hamdaoui, Fayçal; Mtibaa, Abdellatif

doi:10.1109/iccit52419.2022.9711631

Cited by 6 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to conventional images, DL algorithms were developed to have the ability to analyze video frames that record human-face movements to indicate specific diseases. Three-dimensional Convolutional Neural Network (3D-CNN) is an adaptation from conventional CNN, extracting information provided by successive video frames [19]. 3D-CNN was adopted for detecting specific diseases (neurological) that cause dysfunction in the human face.…”

Section: Machine-learning Techniquesmentioning

confidence: 99%

Image-Based Face Recognition Techniques Used in Disease Detection Approaches: A Survey

Ghalib Ahmed Salman,

Inas Jawad Kadhim,

Ahmed Husham Al-Badri

2024

View full text Add to dashboard Cite

Facial diseases lead to noticeable changes on the human face, and some of them extend beyond internal effects or organ-based disorders. Indeed, certain types of facial diseases result in visually noticeable abnormalities on the human face. These alterations in facial patterns can serve as potential indicators for corresponding diseases, particularly in the fields of endocrinology and metabolism, Muscles-Nervous disorders, Chromosomes, and Genetic disorders, among others. Technologies used in Face Recognition (FR) have been developed over the past few decades; however, only a limited amount of research has been applied in recent years to FR-based disease detection for clinical purposes. FR applications relying on Artificial Neural Network (ANN) techniques have recorded higher accuracy rates in diagnosing facial diseases. This field of recognition holds promising potential for optimizing facial diagnosis approaches and supporting medical staff in evaluating detections. In practice, only a few research ideas have been translated into medical products, emphasizing the need to identify and integrate future applications. As a primary focus, this paper centers on the key applications and technologies for detecting various types of facial diseases, along with a discussion of prospects.

show abstract

Section: Machine-learning Techniquesmentioning

confidence: 99%

Image-Based Face Recognition Techniques Used in Disease Detection Approaches: A Survey

Ghalib Ahmed Salman,

Inas Jawad Kadhim,

Ahmed Husham Al-Badri

2024

View full text Add to dashboard Cite

show abstract

“…In another work, Nair and Megalingam [46] reviewed HAR methods. Bayoudh et al [47] proposed a method based on a hybrid 2D/3D CNN, an LSTM network, and a visual attention mechanism for HAR. Liang et al [48] used the DCT of image frames as input to a CNN.…”

Section: State Of the Artmentioning

confidence: 99%

Deep Learning Approach for Human Action Recognition Using a Time Saliency Map Based on Motion Features Considering Camera Movement and Shot in Video Image Sequences

Alavigharahbagh,

Hajihashemi,

Machado

et al. 2023

Information

View full text Add to dashboard Cite

In this article, a hierarchical method for action recognition based on temporal and spatial features is proposed. In current HAR methods, camera movement, sensor movement, sudden scene changes, and scene movement can increase motion feature errors and decrease accuracy. Another important aspect to take into account in a HAR method is the required computational cost. The proposed method provides a preprocessing step to address these challenges. As a preprocessing step, the method uses optical flow to detect camera movements and shots in input video image sequences. In the temporal processing block, the optical flow technique is combined with the absolute value of frame differences to obtain a time saliency map. The detection of shots, cancellation of camera movement, and the building of a time saliency map minimise movement detection errors. The time saliency map is then passed to the spatial processing block to segment the moving persons and/or objects in the scene. Because the search region for spatial processing is limited based on the temporal processing results, the computations in the spatial domain are drastically reduced. In the spatial processing block, the scene foreground is extracted in three steps: silhouette extraction, active contour segmentation, and colour segmentation. Key points are selected at the borders of the segmented foreground. The last used features are the intensity and angle of the optical flow of detected key points. Using key point features for action detection reduces the computational cost of the classification step and the required training time. Finally, the features are submitted to a Recurrent Neural Network (RNN) to recognise the involved action. The proposed method was tested using four well-known action datasets: KTH, Weizmann, HMDB51, and UCF101 datasets and its efficiency was evaluated. Since the proposed approach segments salient objects based on motion, edges, and colour features, it can be added as a preprocessing step to most current HAR systems to improve performance.

show abstract

A survey of video-based human action recognition in team sports

Yin,

Sinnott,

Jayaputera

2024

Artif Intell Rev

View full text Add to dashboard Cite

Over the past few decades, numerous studies have focused on identifying and recognizing human actions using machine learning and computer vision techniques. Video-based human action recognition (HAR) aims to detect actions from video sequences automatically. This can cover simple gestures to complex actions involving multiple people interacting with objects. Actions in team sports exhibit a different nature compared to other sports, since they tend to occur at a faster pace and involve more human-human interactions. As a result, research has typically not focused on the challenges of HAR in team sports. This paper comprehensively summarises HAR-related research and applications with specific focus on team sports such as football (soccer), basketball and Australian rules football. Key datasets used for HAR-related team sports research are explored. Finally, common challenges and future work are discussed, and possible research directions identified.

show abstract

An Attention-based Hybrid 2D/3D CNN-LSTM for Human Action Recognition

Cited by 6 publications

References 23 publications

Image-Based Face Recognition Techniques Used in Disease Detection Approaches: A Survey

Image-Based Face Recognition Techniques Used in Disease Detection Approaches: A Survey

Deep Learning Approach for Human Action Recognition Using a Time Saliency Map Based on Motion Features Considering Camera Movement and Shot in Video Image Sequences

A survey of video-based human action recognition in team sports

Contact Info

Product

Resources

About