Hoda Mohammadzade

M. Mehrdad Morsali, Hoda Mohammadzade, Saeed Bagheri Shouraki

This paper presents a context-aware framework for feature selection and classification procedures to realize a fast and accurate audio event annotation and classification. The context-aware design starts with exploring feature extraction techniques to find an appropriate combination to select a set resulting in remarkable classification accuracy with minimal computational effort. The exploration for feature selection also embraces an investigation of audio Tempo representation, an advantageous feature extraction method missed by previous works in the environmental audio classification research scope. The proposed annotation method considers outlier, inlier, and hard-to-predict data samples to realize context-aware Active Learning, leading to the average accuracy of 90% when only 15% of data possess initial annotation. Our proposed algorithm for sound classification obtained average prediction accuracy of 98.05% on the UrbanSound8K dataset. The notebooks containing our source codes and implementation results are available at https://github.com/gitmehrdad/FACE.

Ramtin Malekpour, M. Mehrdad Morsali, Hoda Mohammadzade

Video synopsis is an efficient method for condensing surveillance videos. This technique begins with the detection and tracking of objects, followed by the creation of object tubes. These tubes consist of sequences, each containing chronologically ordered bounding boxes of a unique object. To generate a condensed video, the first step involves rearranging the object tubes to maximize the number of non-overlapping objects in each frame. Then, these tubes are stitched to a background image extracted from the source video. The lack of a standard dataset for the video synopsis task hinders the comparison of different video synopsis models. This paper addresses this issue by introducing a standard dataset, called SynoClip, designed specifically for the video synopsis task. SynoClip includes all the necessary features needed to evaluate various models directly and effectively. Additionally, this work introduces a video synopsis model, called FGS, with low computational cost. The model includes an empty-frame object detector to identify frames empty of any objects, facilitating efficient utilization of the deep object detector. Moreover, a tube grouping algorithm is proposed to maintain relationships among tubes in the synthesized video. This is followed by a greedy tube rearrangement algorithm, which efficiently determines the start time of each tube. Finally, the proposed model is evaluated using the proposed dataset. The source code, fine-tuned object detection model, and tutorials are available at https://github.com/Ramtin-ma/VideoSynopsis-FGS.

Niloufar Fakhfour, Mohammad ShahverdiKondori, Sajjad Hashembeiki et al.

In this paper, we tackle the problem of video alignment, the process of matching the frames of a pair of videos containing similar actions. The main challenge in video alignment is that accurate correspondence should be established despite the differences in the execution processes and appearances between the two videos. We introduce an unsupervised method for alignment that uses global and local features of the frames. In particular, we introduce effective features for each video frame by means of three machine vision tools: person detection, pose estimation, and VGG network. Then the features are processed and combined to construct a multidimensional time series that represent the video. The resulting time series are used to align videos of the same actions using a novel version of dynamic time warping named Diagonalized Dynamic Time Warping(DDTW). The main advantage of our approach is that no training is required, which makes it applicable for any new type of action without any need to collect training samples for it. Additionally, our approach can be used for framewise labeling of action phases in a dataset with only a few labeled videos. For evaluation, we considered video synchronization and phase classification tasks on the Penn action and subset of UCF101 datasets. Also, for an effective evaluation of the video synchronization task, we present a new metric called Enclosed Area Error(EAE). The results show that our method outperforms previous state-of-the-art methods, such as TCC, and other self-supervised and weakly supervised methods.

Sara Khalili, Hoda Mohammadzade, Mohammad Mahdi Ahmadi

One of the possible dangers that older people face in their daily lives is falling. Occlusion is one of the biggest challenges of vision-based fall detection systems and degrades their detection performance considerably. To tackle this problem, we synthesize specifically-designed occluded videos for training fall detection systems using existing datasets. Then, by defining a new cost function, we introduce a framework for weighted training of fall detection models using occluded and un-occluded videos, which can be applied to any learnable fall detection system. Finally, we use both a non-deep and deep model to evaluate the effect of the proposed weighted training method. Experiments show that the proposed method can improve the classification accuracy by 36% for a non-deep model and 55% for a deep model in occlusion conditions. Moreover, it is shown that the proposed training framework can also significantly improve the detection performance of a deep network on normal un-occluded samples.

Alireza Nourbakhsh, Hoda Mohammadzade

Time Series Alignment is a critical task in signal processing with numerous real-world applications. In practice, signals often exhibit temporal shifts and scaling, making classification on raw data prone to errors. This paper introduces a novel approach for Multiple Time Series Alignment (MTSA) leveraging Deep Learning techniques. While most existing methods primarily address Multiple Sequence Alignment (MSA) for protein and DNA sequences, there remains a significant gap in alignment methodologies for numerical time series. Additionally, conventional approaches typically focus on pairwise alignment, whereas our proposed method aligns all signals in a multiple manner (all the signals are aligned together at once). This innovation not only enhances alignment efficiency but also significantly improves computational speed. By decomposing into piece-wise linear sections, we introduce varying levels of complexity into the warping function. Additionally, our method ensures the satisfaction of three warping constraints: boundary, monotonicity, and continuity conditions. The utilization of a deep convolutional network allows us to employ a new loss function, addressing some limitations of Dynamic Time Warping (DTW). Experimental results on the UCR Archive 2018, comprising 129 time series datasets, demonstrate that employing our approach to align signals significantly enhances classification accuracy and warping average and also reduces the run time across the majority of these datasets.

Mohammad Ali Etemadi Naeen, Hoda Mohammadzade, Saeed Bagheri Shouraki

Anomaly detection in surveillance videos remains a challenging task due to the diversity of abnormal events, class imbalance, and scene-dependent visual clutter. To address these issues, we propose a robust deep learning framework that integrates human-centric preprocessing with spatio-temporal modeling for multi-class anomaly classification. Our pipeline begins by applying YOLO-World - an open-vocabulary vision-language detector - to identify human instances in raw video clips, followed by ByteTrack for consistent identity-aware tracking. Background regions outside detected bounding boxes are suppressed via Gaussian blurring, effectively reducing scene-specific distractions and focusing the model on behaviorally relevant foreground content. The refined frames are then processed by an ImageNet-pretrained InceptionV3 network for spatial feature extraction, and temporal dynamics are captured using a bidirectional LSTM (BiLSTM) for sequence-level classification. Evaluated on a five-class subset of the UCF-Crime dataset (Normal, Burglary, Fighting, Arson, Explosion), our method achieves a mean test accuracy of 92.41% across three independent trials, with per-class F1-scores consistently exceeding 0.85. Comprehensive evaluation metrics - including confusion matrices, ROC curves, and macro/weighted averages - demonstrate strong generalization and resilience to class imbalance. The results confirm that foreground-focused preprocessing significantly enhances anomaly discrimination in real-world surveillance scenarios.

Hassan Keshvarikhojasteh, Hoda Mohammadzade, Hamid Behroozi

Temporal Action Localization (TAL) task which is to predict the start and end of each action in a video along with the class label of the action has numerous applications in the real world. But due to the complexity of this task, acceptable accuracy rates have not been achieved yet, whereas this is not the case regarding the action recognition task. In this paper, we propose a new network based on Gated Recurrent Unit (GRU) and two novel post-processing methods for TAL task. Specifically, we propose a new design for the output layer of the conventionally GRU resulting in the so-called GRU-Split network. Moreover, linear interpolation is used to generate the action proposals with precise start and end times. Finally, to rank the generated proposals appropriately, we use a Learn to Rank (LTR) approach. We evaluated the performance of the proposed method on Thumos14 and ActivityNet-1.3 datasets. Results show the superiority of the performance of the proposed method compared to state-of-the-art. Specifically in the mean Average Precision (mAP) metric at Intersection over Union (IoU) of 0.7 on Thumos14, we get 27.52% accuracy which is 5.12% better than that of state-of-the-art methods.

Mohammad Akyash, Hoda Mohammadzade, Hamid Behroozi

In recent years, neural networks achieved much success in various applications. The main challenge in training deep neural networks is the lack of sufficient data to improve the model's generalization and avoid overfitting. One of the solutions is to generate new training samples. This paper proposes a novel data augmentation method for time series based on Dynamic Time Warping. This method is inspired by the concept that warped parts of two time series have similar temporal properties and therefore, exchanging them between the two series generates a new training sample. The proposed method selects an element of the optimal warping path randomly and then exchanges the segments that are aligned together. Exploiting the proposed approach with recently introduced ResNet reveals improved results on the 2018 UCR Time Series Classification Archive. By employing Gradient-weighted Class Activation Mapping (Grad-CAM) and Multidimensional Scaling (MDS), we manifest that our method extract more discriminant features out of time series.

Benyamin Ghojogh, Saeed Sharifian, Hoda Mohammadzade

Designing search algorithms for finding global optima is one of the most active research fields, recently. These algorithms consist of two main categories, i.e., classic mathematical and metaheuristic algorithms. This article proposes a meta-algorithm, Tree-Based Optimization (TBO), which uses other heuristic optimizers as its sub-algorithms in order to improve the performance of search. The proposed algorithm is based on mathematical tree subject and improves performance and speed of search by iteratively removing parts of the search space having low fitness, in order to minimize and purify the search space. The experimental results on several well-known benchmarks show the outperforming performance of TBO algorithm in finding the global solution. Experiments on high dimensional search spaces show significantly better performance when using the TBO algorithm. The proposed algorithm improves the search algorithms in both accuracy and speed aspects, especially for high dimensional searching such as in VLSI CAD tools for Integrated Circuit (IC) design.

Hoda Mohammadzade, Amirhossein Sayyafan, Benyamin Ghojogh

The variation of pose, illumination and expression makes face recognition still a challenging problem. As a pre-processing in holistic approaches, faces are usually aligned by eyes. The proposed method tries to perform a pixel alignment rather than eye-alignment by mapping the geometry of faces to a reference face while keeping their own textures. The proposed geometry alignment not only creates a meaningful correspondence among every pixel of all faces, but also removes expression and pose variations effectively. The geometry alignment is performed pixel-wise, i.e., every pixel of the face is corresponded to a pixel of the reference face. In the proposed method, the information of intensity and geometry of faces are separated properly, trained by separate classifiers, and finally fused together to recognize human faces. Experimental results show a great improvement using the proposed method in comparison to eye-aligned recognition. For instance, at the false acceptance rate of 0.001, the recognition rates are respectively improved by 24% and 33% in Yale and AT&T datasets. In LFW dataset, which is a challenging big dataset, improvement is 20% at FAR of 0.1.

Benyamin Ghojogh, Saeed Bagheri Shouraki, Hoda Mohammadzade et al.

This paper proposes a fusion-based gender recognition method which uses facial images as input. Firstly, this paper utilizes pre-processing and a landmark detection method in order to find the important landmarks of faces. Thereafter, four different frameworks are proposed which are inspired by state-of-the-art gender recognition systems. The first framework extracts features using Local Binary Pattern (LBP) and Principal Component Analysis (PCA) and uses back propagation neural network. The second framework uses Gabor filters, PCA, and kernel Support Vector Machine (SVM). The third framework uses lower part of faces as input and classifies them using kernel SVM. The fourth framework uses Linear Discriminant Analysis (LDA) in order to classify the side outline landmarks of faces. Finally, the four decisions of frameworks are fused using weighted voting. This paper takes advantage of both texture and geometrical information, the two dominant types of information in facial gender recognition. Experimental results show the power and effectiveness of the proposed method. This method obtains recognition rate of 94% for neutral faces of FEI face dataset, which is equal to state-of-the-art rate for this dataset.

Saeed Ghodsi, Hoda Mohammadzade, Erfan Korki

The availability of low-cost range sensors and the development of relatively robust algorithms for the extraction of skeleton joint locations have inspired many researchers to develop human activity recognition methods using the 3-D data. In this paper, an effective method for the recognition of human activities from the normalized joint trajectories is proposed. We represent the actions as multidimensional signals and introduce a novel method for generating action templates by averaging the samples in a "dynamic time" sense. Then in order to deal with the variations in the speed and style of performing actions, we warp the samples to the action templates by an efficient algorithm and employ wavelet filters to extract meaningful spatiotemporal features. The proposed method is also capable of modeling the human-object interactions, by performing the template generation and temporal warping procedure via the joint and object trajectories simultaneously. The experimental evaluation on several challenging datasets demonstrates the effectiveness of our method compared to the state-of-the-arts.

Mozhgan Mokari, Hoda Mohammadzade, Benyamin Ghojogh

Human action recognition has been one of the most active fields of research in computer vision for last years. Two dimensional action recognition methods are facing serious challenges such as occlusion and missing the third dimension of data. Development of depth sensors has made it feasible to track positions of human body joints over time. This paper proposes a novel method of action recognition which uses temporal 3D skeletal Kinect data. This method introduces the definition of body states and then every action is modeled as a sequence of these states. The learning stage uses Fisher Linear Discriminant Analysis (LDA) to construct discriminant feature space for discriminating the body states. Moreover, this paper suggests the use of the Mahalonobis distance as an appropriate distance metric for the classification of the states of involuntary actions. Hidden Markov Model (HMM) is then used to model the temporal transition between the body states in each action. According to the results, this method significantly outperforms other popular methods, with recognition rate of 88.64% for eight different actions and up to 96.18% for classifying fall actions.