Facial expression recognition (FER) remains a challenging task due to label ambiguity caused by the subjective nature of facial expressions and noisy samples. Additionally, class imbalance, which is common in real-world datasets, further complicates FER. Although many studies have shown impressive improvements, they typically address only one of these issues, leading to suboptimal results. To tackle both challenges simultaneously, we propose a novel framework called Navigating Label Ambiguity (NLA), which is robust under real-world conditions. The motivation behind NLA is that dynamically estimating and emphasizing ambiguous samples at each iteration helps mitigate noise and class imbalance by reducing the model's bias toward majority classes. To achieve this, NLA consists of two main components: Noise-aware Adaptive Weighting (NAW) and consistency regularization. Specifically, NAW adaptively assigns higher importance to ambiguous samples and lower importance to noisy ones, based on the correlation between the intermediate prediction scores for the ground truth and the nearest negative. Moreover, we incorporate a regularization term to ensure consistent latent distributions. Consequently, NLA enables the model to progressively focus on more challenging ambiguous samples, which primarily belong to the minority class, in the later stages of training. Extensive experiments demonstrate that NLA outperforms existing methods in both overall and mean accuracy, confirming its robustness against noise and class imbalance. To the best of our knowledge, this is the first framework to address both problems simultaneously.

In surveillance environments, detecting anomalies requires understanding the contextual dynamics of the environment, human behaviors, and movements within a scene. Effective anomaly detection must address both the where and what of events, but existing approaches such as unimodal action-based methods or LLM-integrated multimodal frameworks have limitations. These methods either rely on implicit scene information, making it difficult to localize where anomalies occur, or fail to adapt to surveillance specific challenges such as view changes, subtle actions, low light conditions, and crowded scenes. As a result, these challenges hinder accurate detection of what occurs. To overcome these limitations, our system takes advantage of features from a lightweight scene classification model to discern where an event occurs, acquiring explicit location-based context. To identify what events occur, it focuses on atomic actions, which remain underexplored in this field and are better suited to interpreting intricate abnormal behaviors than conventional abstract action features. To achieve robust anomaly detection, the proposed Temporal-Semantic Relationship Network (TSRN) models spatio-temporal relationships among multimodal features and employs a Segment-selective Focal Margin loss (SFML) to effectively address class imbalance, outperforming conventional MIL-based methods. Experimental results on public datasets demonstrate that the proposed system effectively reduces false alarms while maintaining robustness and practicality for real-world surveillance applications.

Despite poor image quality, occlusions, and small training datasets, recent pedestrian attribute recognition (PAR) methods have achieved considerable performance. However, leveraging only spatial information of different attributes limits their reliability and generalizability. This paper introduces a multi-perspective approach to reduce over-dependence on spatial clues of a single perspective and exploits other aspects available in multiple perspectives. In order to tackle image quality and occlusions, we exploit different spatial clues present across images and handpick the best attribute-specific features to classify. Precisely, we extract the class-activation energy of each attribute and correlate it with the corresponding energy present across other images using the proposed Self-Attentive Cross Relation Module. In the next stage, we fuse this correlation information with similar clues accumulated from the other images. Lastly, we train a classification neural network using combined correlation information with two different losses. We have validated our method on four widely used PAR datasets, namely Market1501, PETA, PA-100k, and Duke. Our method achieves superior performance over most existing methods, demonstrating the effectiveness of a multi-perspective approach in PAR.

Existing video anomaly detection methods and datasets suffer from restricted anomaly categories containing single-source (CCTV) videos recorded in controlled environment, inadequate annotations, and lack of adequate supervision. To mitigate these problems, we introduce a new dataset ( RareAnom ) containing 17 rare types of real-world anomalies (2200 videos) recorded using multiple sources (e.g., CCTV , handheld cameras, dash-cams, and mobile phones) with rich temporal annotations. A new fully unsupervised anomaly detection and classification method has been proposed. It has three stages: training of a 3D Convolution Autoencoder using pseudo-labelled video segments, anomaly detection using latent features, and classification. Unlike the existing datasets, we have benchmarked RareAnom using three levels of supervision: fully, weakly, and unsupervised. It has been compared with UCF-Crime and XD-Violence datasets. The proposed anomaly detection and classification method beats the latest unsupervised methods by 4.49%, 8.66%, and 6.77% on RareAnom, UCF-Crime, and XD-violence datasets, respectively.

Detection and localization of road accidents in real-time is an integral part of the Intelligent Transportation System (ITS). Even though the existing road accident detection methods show promising results, the process suffers from some drawbacks. For example, existing methods require a large number of sample videos for feature learning. Moreover, features such as temporal gradients or flow fields are time-consuming. To address these issues, we introduce a new method that uses objects and their positions to detect accidents in real-time. Apart from localization of the accident events in videos, we perform a high-level post processing to describe the severity and context of an accident. Firstly, we divide an input video into pre-accident, accident and post-accident stages to extract object interactions. These interaction proposals are then filtered using a refinement algorithm. We then adopt an iterative training procedure to classify normal and accident interactions. We also highlight the damaged zone using heat maps. Finally, we generate high-level textual descriptions to quantify the context and severity of an accident. We have trained the proposed model using offline setups. However, it can be deployed online to detect road accident events in real-time by taking the video inputs directly from the CCTV camera. Moreover, with a minimal supervision, the model can be retrained for online surveillance. Extensive experiments carried out on UCF Crime and CADP datasets reveal that the proposed framework achieves state-of-the-art performance when compared with the recently proposed accident event detection methods in terms of AUC (UCF Crime: 69.70% and CADP: 72.59%) and FAR (UCF Crime: 0.8 and CADP: 2.2). The high-level description of the accident is an added advantage that will certainly help the traffic police to react in a timely manner.

Visual surveillance produces a significant amount of raw video data that can be time consuming to browse and analyze. In this work, we present a video synopsis methodology called "scene adaptive online video synopsis via dynamic tube rearrangement using octree (SSOcT)" that can effectively condense input surveillance videos. Our method entailed summarizing the input video by analyzing scene characteristics and determining an effective spatio-temporal 3D structure for video synopsis. For this purpose, we first analyzed the attributes of each extracted tube with respect to scene geometry and complexity. Then, we adaptively grouped the tubes using an online grouping algorithm that exploits these scene characteristics. Finally, the tube groups were dynamically rearranged using the proposed octree-based algorithm that efficiently inserted and refined tubes containing high spatio-temporal movements in real time. Extensive video synopsis experimental results are provided, demonstrating the effectiveness and efficiency of our method in summarizing real-world surveillance videos with diverse scene characteristics.

Visual saliency on stereoscopic 3D (S3D) images has been shown to be heavily influenced by image quality. Hence, this dependency is an important factor in image quality prediction, image restoration and discomfort reduction, but it is still very difficult to predict such a nonlinear relation in images. In addition, most algorithms specialized in detecting visual saliency on pristine images may unsurprisingly fail when facing distorted images. In this paper, we investigate a deep learning scheme named Deep Visual Saliency (DeepVS) to achieve a more accurate and reliable saliency predictor even in the presence of distortions. Since visual saliency is influenced by low-level features (contrast, luminance and depth information) from a psychophysical point of view, we propose seven low-level features derived from S3D image pairs and utilize them in the context of deep learning to detect visual attention adaptively to human perception. During analysis, it turns out that the low-level features play a role to extract distortion and saliency information. To construct saliency predictors, we weight and model the human visual saliency through two different network architectures, a regression and a fully convolutional neural networks (CNNs). Our results from thorough experiments confirm that the predicted saliency maps are up to 70 % correlated with human gaze patterns, which emphasize the need for the hand-crafted features as input to deep neural networks in S3D saliency detection.

We explore a no-reference sharpness assessment model for predicting the perceptual sharpness of ultrahigh-definition (UHD) videos through analysis of visual resolution variation in terms of viewing geometry and scene characteristics. The quality and sharpness of UHD videos are influenced by viewer perception of the spatial resolution afforded by the UHD display, which depends on viewing geometry parameters including display resolution, display size, and viewing distance. In addition, viewers may perceive different degrees of quality and sharpness according to the statistical behavior of the visual signals, such as the motion, texture, and edge, which vary over both spatial and temporal domains. The model also accounts for the resolution variation associated with fixation and foveal regions, which is another important factor affecting the sharpness prediction of UHD video over the spatial domain and which is caused by the nonuniform distribution of the photoreceptors. We calculate the transition of the visually salient statistical characteristics resulting from changing the display's screen size and resolution. Moreover, we calculated the temporal variation in sharpness over consecutive frames in order to evaluate the temporal sharpness perception of UHD video. We verify that the proposed model outperforms other sharpness models in both spatial and temporal sharpness assessments.

Since ultra-high-definition (UHD) display has larger resolution and various display size, it is necessary to measure image sharpness considering variation in visual resolution caused by diverse viewing geometry. In this paper, we propose a no-reference perceptual sharpness assessment model of UHD images. The proposed model analyzes viewing geometry in terms of display resolution and viewing environment. Then, we measure the local adaptive sharpness score in accordance with the textural motion blur, texture, and edge. In addition, we propose a spatial pooling method associated with foveal regions, which is caused by nonuniform distribution of the photoreceptors on a human retina. Through the rigorous experiments, we demonstrate that the proposed model can measure the sharpness of UHD images more accurately than other image sharpness assessment methods.

By analyzing the statistical behaviors on human visual attention, we discover a clue that the fixation behaviors are highly correlated with how much the viewers feel visual discomfort on stereoscopic images differently from conventional subjective assessments. In order to quantify the correlation between visual attention and discomfort, we explore a novel methodology termed transition of visual attention (ToVA) according to various disparities, which accounts depth attributes of 3D images by eye-tracker experiments. Moreover, the saliency entropy is defined to quantify the distribution of fixations for 3D images. Then, we measure ToVA in terms of the relative saliency entropy using Kullback-Leibler divergence. In order to evaluate the effectiveness of ToVA, a successful example application is also provided, whereby ToVA is applied to obtaining subjective results of measuring discomfort experienced when viewing 3D displays rather than relying on the conventional subjective test by using scoring system.

In this paper, we investigate a unique approach for characterizing the process of human 3D perception by reflecting psychological observation to quality assessment. When a human being perceives the 3D structure, the brain classifies the scene into the binocular- or monocular-vision region depending on the availability of binocular depth perception in the unit of a certain region. Furthermore, we include the 3D perception on the quality assessment, and propose a human 3D perception based stereo image quality pooling model.

Through statistical analysis of the behaviors of human visual attention, we discovered that fixation behaviors are highly correlated with the degree to which the viewer experiences visual quality/discomfort with stereoscopic images. To quantify the correlation between visual attention and quality/discomfort with respect to various distortions and disparities, we explore a novel methodology called transition of visual attention (ToVA) that accounts for diverse low-level luminance, chrominance, and depth attributes of 3D images in eye-tracker experiments. Moreover, saliency entropy is defined in order to quantify the distribution of fixations for 3D images. Using saliency entropy, we interpret perceptual factors in accordance with the non-uniform resolution of the human eye and the stereoscopic limits caused by foveation and Panum's fusional area. We then measure ToVA in terms of relative saliency entropy using Kullback-Leibler divergence. To evaluate the effectiveness of ToVA, a successful example application is also provided for which ToVA is applied to obtain subjective measurements of the quality and discomfort experienced when viewing 3D displays, rather than relying on conventional subjective tests using a scoring system.

We describe a new 3D saliency prediction model that accounts for diverse low-level luminance, chrominance, motion, and depth attributes of 3D videos as well as high-level classifications of scenes by type. The model also accounts for perceptual factors, such as the nonuniform resolution of the human eye, stereoscopic limits imposed by Panum's fusional area, and the predicted degree of (dis) comfort felt, when viewing the 3D video. The high-level analysis involves classification of each 3D video scene by type with regard to estimated camera motion and the motions of objects in the videos. Decisions regarding the relative saliency of objects or regions are supported by data obtained through a series of eye-tracking experiments. The algorithm developed from the model elements operates by finding and segmenting salient 3D space-time regions in a video, then calculating the saliency strength of each segment using measured attributes of motion, disparity, texture, and the predicted degree of visual discomfort experienced. The saliency energy of both segmented objects and frames are weighted using models of human foveation and Panum's fusional area yielding a single predictor of 3D saliency.

We propose the energy efficient MAC algorithm in this pa per. In the proposed algorithm, each node sets the contention window size with respect to the residual energy, the harvesting energy and the transmit power. This algorithm makes the sensor nodes consume their energy efficiently. To achieve this goal, we use the game theory and the cross-layer optimization. Introducing the non-cooperative game, we can formulate the utility function easily. In this paper, we can allocate the optimal power by the cross-layer optimization on the PHY and the MAC.