424 citations · 518 across the 28 of their papers we have counts for
28 papers
Emotion Alignment: Discovering the Gap Between Social Media and Real-World Sentiments in Persian Tweets and Images
Sina Elahimanesh, Mohammadali Mohammadkhani, Shohreh Kasaei
In contemporary society, widespread social media usage is evident in people's daily lives. Nevertheless, disparities in emotional expressions between the real world and online plat…
Improving Weakly-supervised Video Instance Segmentation by Leveraging Spatio-temporal Consistency
Farnoosh Arefi, Amir M. Mansourian, Shohreh Kasaei
The performance of Video Instance Segmentation (VIS) methods has improved significantly with the advent of transformer networks. However, these networks often face challenges in tr…
Attention-guided Feature Distillation for Semantic Segmentation
Amir M. Mansourian, Arya Jalali, Rozhan Ahmadi +1
Deep learning models have achieved significant results across various computer vision tasks. However, due to the large number of parameters in these models, deploying them in real-…
Deep Spectral Improvement for Unsupervised Image Instance Segmentation
Farnoosh Arefi, Amir M. Mansourian, Shohreh Kasaei
Deep spectral methods reframe the image decomposition process as a graph partitioning task by extracting features using self-supervised learning and utilizing the Laplacian of the…
Leveraging Swin Transformer for Local-to-Global Weakly Supervised Semantic Segmentation
Rozhan Ahmadi, Shohreh Kasaei
In recent years, weakly supervised semantic segmentation using image-level labels as supervision has received significant attention in the field of computer vision. Most existing m…
Rethinking RAFT for Efficient Optical Flow
Navid Eslami, Farnoosh Arefi, Amir M. Mansourian +1
Despite significant progress in deep learning-based optical flow methods, accurately estimating large displacements and repetitive patterns remains a challenge. The limitations of…
AICSD: Adaptive Inter-Class Similarity Distillation for Semantic Segmentation
Amir M. Mansourian, Rozhan Ahmadi, Shohreh Kasaei
In recent years, deep neural networks have achieved remarkable accuracy in computer vision tasks. With inference time being a crucial factor, particularly in dense prediction tasks…
Trainable Loss Weights in Super-Resolution
Arash Chaichi Mellatshahi, Shohreh Kasaei
In recent years, limited research has discussed the loss function in the super-resolution process. The majority of those studies have only used perceptual similarity conventionally…
Information-Theoretic Analysis of Minimax Excess Risk
Hassan Hafez-Kolahi, Behrad Moniri, Shohreh Kasaei
Two main concepts studied in machine learning theory are generalization gap (difference between train and test error) and excess risk (difference between test error and the minimum…
Adversarial Attack by Limited Point Cloud Surface Modifications
Atrin Arya, Hanieh Naderi, Shohreh Kasaei
Recent research has revealed that the security of deep neural networks that directly process 3D point clouds to classify objects can be threatened by adversarial samples. Although…
CHASE: Robust Visual Tracking via Cell-Level Differentiable Neural Architecture Search
Seyed Mojtaba Marvasti-Zadeh, Javad Khaghani, Li Cheng +2
A strong visual object tracker nowadays relies on its well-crafted modules, which typically consist of manually-designed network architectures to deliver high-quality tracking resu…
Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning
Hassan Hafez-Kolahi, Behrad Moniri, Shohreh Kasaei +1
In parametric Bayesian learning, a prior is assumed on the parameter which determines the distribution of samples. In this setting, Minimum Excess Risk (MER) is defined as the…
Generating Unrestricted Adversarial Examples via Three Parameters
Hanieh Naderi, Leili Goli, Shohreh Kasaei
Deep neural networks have been shown to be vulnerable to adversarial examples deliberately constructed to misclassify victim models. As most adversarial examples have restricted th…
Be Your Own Best Competitor! Multi-Branched Adversarial Knowledge Transfer
Mahdi Ghorbani, Fahimeh Fooladgar, Shohreh Kasaei
Deep neural network architectures have attained remarkable improvements in scene understanding tasks. Utilizing an efficient model is one of the most important constraints for limi…
Adaptive Exploitation of Pre-trained Deep Convolutional Neural Networks for Robust Visual Tracking
Seyed Mojtaba Marvasti-Zadeh, Hossein Ghanei-Yakhdan, Shohreh Kasaei
Due to the automatic feature extraction procedure via multi-layer nonlinear transformations, the deep learning-based visual trackers have recently achieved great success in challen…
COMET: Context-Aware IoU-Guided Network for Small Object Tracking
Seyed Mojtaba Marvasti-Zadeh, Javad Khaghani, Hossein Ghanei-Yakhdan +2
We consider the problem of tracking an unknown small target from aerial videos of medium to high altitudes. This is a challenging problem, which is even more pronounced in unavoida…
Efficient Scale Estimation Methods using Lightweight Deep Convolutional Neural Networks for Visual Tracking
Seyed Mojtaba Marvasti-Zadeh, Hossein Ghanei-Yakhdan, Shohreh Kasaei
In recent years, visual tracking methods that are based on discriminative correlation filters (DCF) have been very promising. However, most of these methods suffer from a lack of r…
Beyond Background-Aware Correlation Filters: Adaptive Context Modeling by Hand-Crafted and Deep RGB Features for Visual Tracking
Seyed Mojtaba Marvasti-Zadeh, Hossein Ghanei-Yakhdan, Shohreh Kasaei
In recent years, the background-aware correlation filters have achie-ved a lot of research interest in the visual target tracking. However, these methods cannot suitably model the…
Effective Fusion of Deep Multitasking Representations for Robust Visual Tracking
Seyed Mojtaba Marvasti-Zadeh, Hossein Ghanei-Yakhdan, Shohreh Kasaei +2
Visual object tracking remains an active research field in computer vision due to persisting challenges with various problem-specific factors in real-world scenes. Many existing tr…
Lightweight Residual Densely Connected Convolutional Neural Network
Fahimeh Fooladgar, Shohreh Kasaei
Extremely efficient convolutional neural network architectures are one of the most important requirements for limited-resource devices (such as embedded and mobile devices). The co…
Pointwise Attention-Based Atrous Convolutional Neural Networks
Mobina Mahdavi, Fahimeh Fooladgar, Shohreh Kasaei
With the rapid progress of deep convolutional neural networks, in almost all robotic applications, the availability of 3D point clouds improves the accuracy of 3D semantic segmenta…
Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Images
Fahimeh Fooladgar, Shohreh Kasaei
The 3D scene understanding is mainly considered as a crucial requirement in computer vision and robotics applications. One of the high-level tasks in 3D scene understanding is sema…
Deep Learning for Visual Tracking: A Comprehensive Survey
Seyed Mojtaba Marvasti-Zadeh, Li Cheng, Hossein Ghanei-Yakhdan +1
Visual target tracking is one of the most sought-after yet challenging research topics in computer vision. Given the ill-posed nature of the problem and its popularity in a broad r…
Do Compressed Representations Generalize Better?
Hassan Hafez-Kolahi, Shohreh Kasaei, Mahdiyeh Soleymani-Baghshah
One of the most studied problems in machine learning is finding reasonable constraints that guarantee the generalization of a learning algorithm. These constraints are usually expr…