Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Mehrtash Harandi

Mehrtash Harandi

Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions


Apr 22, 2021
Jing Wu, Mingyi Zhou, Ce Zhu, Yipeng Liu, Mehrtash Harandi, Li Li

Figure 1 for Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions
Figure 2 for Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions
Figure 3 for Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions
Figure 4 for Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions

  Access Paper or Ask Questions

On Learning the Geodesic Path for Incremental Learning


Apr 17, 2021
Christian Simon, Piotr Koniusz, Mehrtash Harandi

Figure 1 for On Learning the Geodesic Path for Incremental Learning
Figure 2 for On Learning the Geodesic Path for Incremental Learning
Figure 3 for On Learning the Geodesic Path for Incremental Learning
Figure 4 for On Learning the Geodesic Path for Incremental Learning
* Accepted to CVPR 2021 
  Access Paper or Ask Questions

Learning Log-Determinant Divergences for Positive Definite Matrices


Apr 13, 2021
Anoop Cherian, Panagiotis Stanitsas, Jue Wang, Mehrtash Harandi, Vassilios Morellas, Nikolaos Papanikolopoulos

Figure 1 for Learning Log-Determinant Divergences for Positive Definite Matrices
Figure 2 for Learning Log-Determinant Divergences for Positive Definite Matrices
Figure 3 for Learning Log-Determinant Divergences for Positive Definite Matrices
Figure 4 for Learning Log-Determinant Divergences for Positive Definite Matrices
* Accepted at Trans. PAMI (extended version of ICCV 2017 paper). arXiv admin note: substantial text overlap with arXiv:1708.01741 
  Access Paper or Ask Questions

Reinforced Attention for Few-Shot Learning and Beyond


Apr 09, 2021
Jie Hong, Pengfei Fang, Weihao Li, Tong Zhang, Christian Simon, Mehrtash Harandi, Lars Petersson

Figure 1 for Reinforced Attention for Few-Shot Learning and Beyond
Figure 2 for Reinforced Attention for Few-Shot Learning and Beyond
Figure 3 for Reinforced Attention for Few-Shot Learning and Beyond
Figure 4 for Reinforced Attention for Few-Shot Learning and Beyond

  Access Paper or Ask Questions

Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning


Mar 31, 2021
Ali Cheraghian, Shafin Rahman, Pengfei Fang, Soumava Kumar Roy, Lars Petersson, Mehrtash Harandi

Figure 1 for Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning
Figure 2 for Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning
Figure 3 for Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning
Figure 4 for Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning
* Accepted at CVPR 2021 
  Access Paper or Ask Questions

Learning to Continually Learn Rapidly from Few and Noisy Data


Mar 06, 2021
Nicholas I-Hsien Kuo, Mehrtash Harandi, Nicolas Fourrier, Christian Walder, Gabriela Ferraro, Hanna Suominen

Figure 1 for Learning to Continually Learn Rapidly from Few and Noisy Data
Figure 2 for Learning to Continually Learn Rapidly from Few and Noisy Data
Figure 3 for Learning to Continually Learn Rapidly from Few and Noisy Data
Figure 4 for Learning to Continually Learn Rapidly from Few and Noisy Data
* Accepted to the Meta-Learning and Co-Hosted Competition of AAAI 2021. See https://aaai.org/Conferences/AAAI-21/ws21workshops/ and see https://sites.google.com/chalearn.org/metalearning?pli=1#h.kt23ep5wlehv 
  Access Paper or Ask Questions

Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation


Feb 28, 2021
Lie Ju, Xin Wang, Lin Wang, Dwarikanath Mahapatra, Xin Zhao, Mehrtash Harandi, Tom Drummond, Tongliang Liu, Zongyuan Ge

Figure 1 for Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation
Figure 2 for Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation
Figure 3 for Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation
Figure 4 for Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation

  Access Paper or Ask Questions

Uncertainty-Aware Deep Calibrated Salient Object Detection


Dec 10, 2020
Jing Zhang, Yuchao Dai, Xin Yu, Mehrtash Harandi, Nick Barnes, Richard Hartley

Figure 1 for Uncertainty-Aware Deep Calibrated Salient Object Detection
Figure 2 for Uncertainty-Aware Deep Calibrated Salient Object Detection
Figure 3 for Uncertainty-Aware Deep Calibrated Salient Object Detection
Figure 4 for Uncertainty-Aware Deep Calibrated Salient Object Detection
* Completed in 2019 
  Access Paper or Ask Questions

Set Augmented Triplet Loss for Video Person Re-Identification


Nov 07, 2020
Pengfei Fang, Pan Ji, Lars Petersson, Mehrtash Harandi

Figure 1 for Set Augmented Triplet Loss for Video Person Re-Identification
Figure 2 for Set Augmented Triplet Loss for Video Person Re-Identification
Figure 3 for Set Augmented Triplet Loss for Video Person Re-Identification
Figure 4 for Set Augmented Triplet Loss for Video Person Re-Identification
* to appear in WACV 2021 
  Access Paper or Ask Questions

Hierarchical Neural Architecture Search for Deep Stereo Matching


Oct 26, 2020
Xuelian Cheng, Yiran Zhong, Mehrtash Harandi, Yuchao Dai, Xiaojun Chang, Tom Drummond, Hongdong Li, Zongyuan Ge

Figure 1 for Hierarchical Neural Architecture Search for Deep Stereo Matching
Figure 2 for Hierarchical Neural Architecture Search for Deep Stereo Matching
Figure 3 for Hierarchical Neural Architecture Search for Deep Stereo Matching
Figure 4 for Hierarchical Neural Architecture Search for Deep Stereo Matching
* Accepted at NeurIPS 2020; Xuelian Cheng and Yiran Zhong made equal contribution 
  Access Paper or Ask Questions

Channel Recurrent Attention Networks for Video Pedestrian Retrieval


Oct 07, 2020
Pengfei Fang, Pan Ji, Jieming Zhou, Lars Petersson, Mehrtash Harandi

Figure 1 for Channel Recurrent Attention Networks for Video Pedestrian Retrieval
Figure 2 for Channel Recurrent Attention Networks for Video Pedestrian Retrieval
Figure 3 for Channel Recurrent Attention Networks for Video Pedestrian Retrieval
Figure 4 for Channel Recurrent Attention Networks for Video Pedestrian Retrieval
* To appear in ACCV 2020 
  Access Paper or Ask Questions

Unsupervised Deep Metric Learning via Orthogonality based Probabilistic Loss


Aug 22, 2020
Ujjal Kr Dutta, Mehrtash Harandi, Chellu Chandra Sekhar

Figure 1 for Unsupervised Deep Metric Learning via Orthogonality based Probabilistic Loss
Figure 2 for Unsupervised Deep Metric Learning via Orthogonality based Probabilistic Loss
Figure 3 for Unsupervised Deep Metric Learning via Orthogonality based Probabilistic Loss
Figure 4 for Unsupervised Deep Metric Learning via Orthogonality based Probabilistic Loss
* In the IEEE Transactions on Artificial Intelligence (IEEE TAI) 
  Access Paper or Ask Questions

MTL2L: A Context Aware Neural Optimiser


Jul 18, 2020
Nicholas I-Hsien Kuo, Mehrtash Harandi, Nicolas Fourrier, Christian Walder, Gabriela Ferraro, Hanna Suominen

Figure 1 for MTL2L: A Context Aware Neural Optimiser
Figure 2 for MTL2L: A Context Aware Neural Optimiser
Figure 3 for MTL2L: A Context Aware Neural Optimiser
Figure 4 for MTL2L: A Context Aware Neural Optimiser
* Published in the ICML workshop of Automated Machine Learning (AutoML) 2020. Also see https://www.automl.org/wp-content/uploads/2020/07/AutoML_2020_paper_5.pdf 
  Access Paper or Ask Questions

Cross-Correlated Attention Networks for Person Re-Identification


Jun 17, 2020
Jieming Zhou, Soumava Kumar Roy, Pengfei Fang, Mehrtash Harandi, Lars Petersson

Figure 1 for Cross-Correlated Attention Networks for Person Re-Identification
Figure 2 for Cross-Correlated Attention Networks for Person Re-Identification
Figure 3 for Cross-Correlated Attention Networks for Person Re-Identification
Figure 4 for Cross-Correlated Attention Networks for Person Re-Identification
* Image and Vision Computing, Vol. 100, 2020, p. 103931 
 * Accepted by Image and Vision Computing 
  Access Paper or Ask Questions

Bridge the Domain Gap Between Ultra-wide-field and Traditional Fundus Images via Adversarial Domain Adaptation


Mar 24, 2020
Lie Ju, Xin Wang, Quan Zhou, Hu Zhu, Mehrtash Harandi, Paul Bonnington, Tom Drummond, Zongyuan Ge

Figure 1 for Bridge the Domain Gap Between Ultra-wide-field and Traditional Fundus Images via Adversarial Domain Adaptation
Figure 2 for Bridge the Domain Gap Between Ultra-wide-field and Traditional Fundus Images via Adversarial Domain Adaptation
Figure 3 for Bridge the Domain Gap Between Ultra-wide-field and Traditional Fundus Images via Adversarial Domain Adaptation
Figure 4 for Bridge the Domain Gap Between Ultra-wide-field and Traditional Fundus Images via Adversarial Domain Adaptation

  Access Paper or Ask Questions

Affinity guided Geometric Semi-Supervised Metric Learning


Feb 27, 2020
Ujjal Kr Dutta, Mehrtash Harandi, Chellu Chandra Sekhar

Figure 1 for Affinity guided Geometric Semi-Supervised Metric Learning
Figure 2 for Affinity guided Geometric Semi-Supervised Metric Learning
Figure 3 for Affinity guided Geometric Semi-Supervised Metric Learning
Figure 4 for Affinity guided Geometric Semi-Supervised Metric Learning
* Paper in Review 
  Access Paper or Ask Questions

A Probabilistic approach for Learning Embeddings without Supervision


Dec 17, 2019
Ujjal Kr Dutta, Mehrtash Harandi, Chandra Sekhar Chellu

Figure 1 for A Probabilistic approach for Learning Embeddings without Supervision
Figure 2 for A Probabilistic approach for Learning Embeddings without Supervision
Figure 3 for A Probabilistic approach for Learning Embeddings without Supervision
Figure 4 for A Probabilistic approach for Learning Embeddings without Supervision

  Access Paper or Ask Questions

Neural Collaborative Subspace Clustering


Apr 24, 2019
Tong Zhang, Pan Ji, Mehrtash Harandi, Wenbing Huang, Hongdong Li

Figure 1 for Neural Collaborative Subspace Clustering
Figure 2 for Neural Collaborative Subspace Clustering
Figure 3 for Neural Collaborative Subspace Clustering
Figure 4 for Neural Collaborative Subspace Clustering
* Accepted to ICML 2019 
  Access Paper or Ask Questions

Scalable Deep $k$-Subspace Clustering


Nov 02, 2018
Tong Zhang, Pan Ji, Mehrtash Harandi, Richard Hartley, Ian Reid

Figure 1 for Scalable Deep $k$-Subspace Clustering
Figure 2 for Scalable Deep $k$-Subspace Clustering
Figure 3 for Scalable Deep $k$-Subspace Clustering
Figure 4 for Scalable Deep $k$-Subspace Clustering
* To appear in ACCV 2018 
  Access Paper or Ask Questions

Block Mean Approximation for Efficient Second Order Optimization


Aug 29, 2018
Yao Lu, Mehrtash Harandi, Richard Hartley, Razvan Pascanu

Figure 1 for Block Mean Approximation for Efficient Second Order Optimization
Figure 2 for Block Mean Approximation for Efficient Second Order Optimization
Figure 3 for Block Mean Approximation for Efficient Second Order Optimization
Figure 4 for Block Mean Approximation for Efficient Second Order Optimization

  Access Paper or Ask Questions

Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective


Mar 29, 2018
Jing Zhang, Tong Zhang, Yuchao Dai, Mehrtash Harandi, Richard Hartley

Figure 1 for Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
Figure 2 for Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
Figure 3 for Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
Figure 4 for Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
* Accepted by IEEE/CVF CVPR 2018 as Spotlight 
  Access Paper or Ask Questions

Devon: Deformable Volume Network for Learning Optical Flow


Feb 20, 2018
Yao Lu, Jack Valmadre, Heng Wang, Juho Kannala, Mehrtash Harandi, Philip H. S. Torr

Figure 1 for Devon: Deformable Volume Network for Learning Optical Flow
Figure 2 for Devon: Deformable Volume Network for Learning Optical Flow
Figure 3 for Devon: Deformable Volume Network for Learning Optical Flow

  Access Paper or Ask Questions

Museum Exhibit Identification Challenge for Domain Adaptation and Beyond


Feb 04, 2018
Piotr Koniusz, Yusuf Tas, Hongguang Zhang, Mehrtash Harandi, Fatih Porikli, Rui Zhang

Figure 1 for Museum Exhibit Identification Challenge for Domain Adaptation and Beyond
Figure 2 for Museum Exhibit Identification Challenge for Domain Adaptation and Beyond
Figure 3 for Museum Exhibit Identification Challenge for Domain Adaptation and Beyond
Figure 4 for Museum Exhibit Identification Challenge for Domain Adaptation and Beyond

  Access Paper or Ask Questions

Learning Discriminative Alpha-Beta-divergence for Positive Definite Matrices (Extended Version)


Aug 05, 2017
Anoop Cherian, Panagiotis Stanitsas, Mehrtash Harandi, Vassilios Morellas, Nikolaos Papanikolopoulos

Figure 1 for Learning Discriminative Alpha-Beta-divergence for Positive Definite Matrices (Extended Version)
Figure 2 for Learning Discriminative Alpha-Beta-divergence for Positive Definite Matrices (Extended Version)
Figure 3 for Learning Discriminative Alpha-Beta-divergence for Positive Definite Matrices (Extended Version)
Figure 4 for Learning Discriminative Alpha-Beta-divergence for Positive Definite Matrices (Extended Version)
* Accepted at the International Conference on Computer Vision (ICCV) 
  Access Paper or Ask Questions

Generalized Rank Pooling for Activity Recognition


Jul 22, 2017
Anoop Cherian, Basura Fernando, Mehrtash Harandi, Stephen Gould

Figure 1 for Generalized Rank Pooling for Activity Recognition
Figure 2 for Generalized Rank Pooling for Activity Recognition
Figure 3 for Generalized Rank Pooling for Activity Recognition
Figure 4 for Generalized Rank Pooling for Activity Recognition
* Accepted at IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2017 
  Access Paper or Ask Questions

Learning an Invariant Hilbert Space for Domain Adaptation


Apr 17, 2017
Samitha Herath, Mehrtash Harandi, Fatih Porikli

Figure 1 for Learning an Invariant Hilbert Space for Domain Adaptation
Figure 2 for Learning an Invariant Hilbert Space for Domain Adaptation
Figure 3 for Learning an Invariant Hilbert Space for Domain Adaptation
Figure 4 for Learning an Invariant Hilbert Space for Domain Adaptation
* 24 pages, 7 figures 
  Access Paper or Ask Questions

Analyzing Linear Dynamical Systems: From Modeling to Coding and Learning


Feb 27, 2017
Wenbing Huang, Fuchun Sun, Lele Cao, Mehrtash Harandi

Figure 1 for Analyzing Linear Dynamical Systems: From Modeling to Coding and Learning
Figure 2 for Analyzing Linear Dynamical Systems: From Modeling to Coding and Learning
Figure 3 for Analyzing Linear Dynamical Systems: From Modeling to Coding and Learning
Figure 4 for Analyzing Linear Dynamical Systems: From Modeling to Coding and Learning
* 38 pages 
  Access Paper or Ask Questions

Going Deeper into Action Recognition: A Survey


Feb 01, 2017
Samitha Herath, Mehrtash Harandi, Fatih Porikli

Figure 1 for Going Deeper into Action Recognition: A Survey
Figure 2 for Going Deeper into Action Recognition: A Survey
Figure 3 for Going Deeper into Action Recognition: A Survey
Figure 4 for Going Deeper into Action Recognition: A Survey

  Access Paper or Ask Questions