Search

The forensic analysis of digital videos is becoming increasingly relevant to deal with forensic cases, propaganda, and fake news. The research community has developed numerous forensic tools to address various challenges, such as integrity verification, manipulation detection, and source characterization. Each tool exploits characteristic traces to reconstruct the video life-cycle. Among these traces, a significant source of information is provided by the specific way in which the video has been encoded. While several tools are available to analyze codec-related information for images, a similar approach has been overlooked for videos, since video codecs are extremely complex and involve the analysis of a huge amount of data. In this paper, we present a new tool designed for extracting and parsing a plethora of video compression information from H.264 encoded files, including macroblocks structure, prediction residuals, and motion vectors. We demonstrate how the extracted features can be effectively exploited to address various forensic tasks, such as social network identification, source characterization, and double compression detection. We provide a detailed description of the developed software, which is released free of charge to enable its use by the research community to create new tools for forensic analysis of video files. [ABSTRACT FROM AUTHOR]

Abstract The forensic analysis of digital videos is becoming increasingly relevant to deal with forensic cases, propaganda, and fake news. The research community has developed numerous forensic tools to address various challenges, such as integrity verification, manipulation detection, and source characterization. Each tool exploits characteristic traces to reconstruct the video life-cycle. Among these traces, a significant source of information is provided by the specific way in which the video has been encoded. While several tools are available to analyze codec-related information for images, a similar approach has been overlooked for videos, since video codecs are extremely complex and involve the analysis of a huge amount of data. In this paper, we present a new tool designed for extracting and parsing a plethora of video compression information from H.264 encoded files, including macroblocks structure, prediction residuals, and motion vectors. We demonstrate how the extracted features can be effectively exploited to address various forensic tasks, such as social network identification, source characterization, and double compression detection. We provide a detailed description of the developed software, which is released free of charge to enable its use by the research community to create new tools for forensic analysis of video files.

Computer vision has extensive applications in various sports domains, and cricket, a complex game with different event types, is no exception. Recognizing umpire signals during cricket matches is essential for fair and accurate decision-making in gameplay. This paper presents the Cricket Umpire Action Video dataset (CUAVd), a novel dataset designed for detecting umpire postures in cricket matches. As the umpire possesses the power to make crucial judgments concerning incidents that occur on the field, this dataset aims to contribute to the advancement of automated systems for umpire recognition in cricket. The proposed Attention-based Deep Convolutional GRU Network accurately detects and classifies various umpire signal actions in video sequences. The method achieved remarkable results on our prepared CUAVd dataset and publicly available datasets, namely HMDB51, Youtube Actions, and UCF101. The DC-GRU Attention model demonstrated its effectiveness in capturing temporal dependencies and accurately recognizing umpire signal actions. Compared to other advanced models like traditional CNN architectures, CNN-LSTM with Attention, and the 3DCNN+GRU model, the proposed model consistently outperformed them in recognizing umpire signal actions. It achieved a high validation accuracy of 94.38% in classifying umpire signal videos correctly. The paper also evaluated the models using performance metrics like F1-Measure and Confusion Matrix, confirming their effectiveness in recognizing umpire signal actions. The suggested model has practical applications in real-life situations such as sports analysis, referee training, and automated referee assistance systems where precise identification of umpire signals in videos is vital. [ABSTRACT FROM AUTHOR]

With an increasing number of people on the planet today, innovative human-computer interaction technologies and approaches may be employed to assist individuals in leading more fulfilling lives. Gesture-based technology has the potential to improve the safety and well-being of impaired people, as well as the general population. Recognizing gestures from video streams is a difficult problem because of the large degree of variation in the characteristics of each motion across individuals. In this article, we propose applying deep learning methods to recognize automated hand gestures using RGB and depth data. To train neural networks to detect hand gestures, any of these forms of data may be utilized. Gesture-based interfaces are more natural, intuitive, and straightforward. Earlier study attempted to characterize hand motions in a number of contexts. Our technique is evaluated using a vision-based gesture recognition system. In our suggested technique, image collection starts with RGB video and depth information captured with the Kinect sensor and is followed by tracking the hand using a single shot detector Convolutional Neural Network (SSD-CNN). When the kernel is applied, it creates an output value at each of the m $\times $ n locations. Using a collection of convolutional filters, each new feature layer generates a defined set of gesture detection predictions. After that, we perform deep dilation to make the gesture in the image masks more visible. Finally, hand gestures have been detected using the well-known classification technique SVM. Using deep learning we recognize hand gestures with higher accuracy of 93.68% in RGB passage, 83.45% in the depth passage, and 90.61% in RGB-D conjunction on the SKIG dataset compared to the state-of-the-art. In the context of our own created Different Camera Orientation Gesture (DCOG) dataset we got higher accuracy of 92.78% in RGB passage, 79.55% in the depth passage, and 88.56% in RGB-D conjunction for the gestures collected in 0-degree angle. Moreover, the framework intends to use unique methodologies to construct a superior vision-based hand gesture recognition system.

Dynamic facial expressions in videos express more realistic emotional states, and recognizing emotions from in-the-wild facial expression videos is a challenging task due to the changeable posture, partial occlusion and various light conditions. Although current methods have designed transformer-based models to learn spatial–temporal features, they cannot explore useful local geometry structures from both spatial and temporal views to capture subtle emotional features for the videos with varied poses and facial occlusion. To this end, we propose a novel multi-geometry embedded transformer (MGET), which adapts multi-geometry knowledge into transformers and excavates spatial–temporal geometry information as complementary to learn effective emotional features. Specifically, from a new perspective, we first design a multi-geometry distance learning (MGDL) to capture emotion-related geometry structure knowledge under Euclidean and Hyperbolic spaces. Especially based on the advantages of hyperbolic geometry, it finds the more subtle emotional changes among local spatial and temporal features. Secondly, we combine MGDL with transformer to design spatial–temporal MGETs, which capture important spatial and temporal multi-geometry features to embed them into their corresponding original features, and then perform cross-regions and cross-frame interaction on these multi-level features. Finally, MGET gains superior performance on DFEW, FERV39k and AFEW datasets, where the unweighted average recall (UAR) and weighted average recall (WAR) are 58.65%/69.91%, 41.91%/50.76% and 53.23%/55.40%, respectively, and the gained improvements are 2.55%/0.66%, 3.69%/2.63% and 3.66%/1.14% compared to M3DFEL, Logo-Forme and EST methods. • A multi-geometry embedded transformer is proposed for in-the-wild FER in videos. • MGDL captures multi-geometry structures under Euclidean and Hyperbolic spaces. • MGET combines MGDL with transformer to model multi-level spatial-temporal features. • MGET shows superior performance on in-the-wild video-based FER databases. [ABSTRACT FROM AUTHOR]