Search Results for author: Ali Borji

Found 83 papers, 36 papers with code

BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network

1 code implementation ECCV 2020 Deng-Ping Fan, Yingjie Zhai, Ali Borji, Jufeng Yang, Ling Shao

In particular, we 1) propose a bifurcated backbone strategy (BBS) to split the multi-level features into teacher and student features, and 2) utilize a depth-enhanced module (DEM) to excavate informative parts of depth cues from the channel and spatial views.

RGB-D Salient Object Detection Salient Object Detection

CNNs and Transformers Perceive Hybrid Images Similar to Humans

1 code implementation19 Mar 2022 Ali Borji

Hybrid images is a technique to generate images with two interpretations that change as a function of viewing distance.

Overparametrization improves robustness against adversarial attacks: A replication study

no code implementations20 Feb 2022 Ali Borji

Overparametrization has become a de facto standard in machine learning.

Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face Videos

1 code implementation5 Nov 2021 Minglang Qiao, Yufan Liu, Mai Xu, Xin Deng, Bing Li, Weiming Hu, Ali Borji

In this paper, we propose a multitask learning method for visual-audio saliency prediction and sound source localization on multi-face video by leveraging visual, audio and face information.

Saliency Prediction

Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model

1 code implementation ECCV 2020 Yufan Liu, Minglang Qiao, Mai Xu, Bing Li, Weiming Hu, Ali Borji

Inspired by the findings of our investigation, we propose a novel multi-modal video saliency model consisting of three branches: visual, audio and face.

Saliency Prediction

Pros and Cons of GAN Evaluation Measures: New Developments

1 code implementation17 Mar 2021 Ali Borji

This work is an update of a previous paper on the same topic published a few years ago.

Fairness

Enhancing sensor resolution improves CNN accuracy given the same number of parameters or FLOPS

1 code implementation9 Mar 2021 Ali Borji

High image resolution is critical to obtain a good performance in many computer vision applications.

Contemplating real-world object classification

1 code implementation8 Mar 2021 Ali Borji

They showed a dramatic performance drop of the state of the art object recognition models on this dataset.

Classification Data Augmentation +2

CONTEMPLATING REAL-WORLDOBJECT RECOGNITION

no code implementations ICLR 2021 Ali Borji

Relative to the numbers reported in Barbu et al., around 10-15% of the performance loss is recovered, without any test time data augmentation.

Data Augmentation Object Recognition

EMPIRICAL UPPER BOUND IN OBJECT DETECTION

no code implementations1 Jan 2021 Ali Borji

In this work, by employing two popular state-of-the-art object detection benchmarks, MMDetection and Detectron2, and analyzing more than 15 models over 4 large-scale datasets, we systematically determine the upper bound in AP, which is 91. 6% on PASCAL VOC (test2007), 78. 2% on MS COCO (val2017), and 58. 9% on OpenImages (V4 validation set), regardless of the IOU.

Instance Segmentation Object Detection +3

Shape Defense

no code implementations NeurIPS Workshop ICBINB 2021 Ali Borji

Further, we show that edge information can a) benefit other adversarial training methods, b) be even more effective in conjunction with background subtraction, c) be used to defend against poisoning attacks, and d) make CNNs more robust against natural image corruptions such as motion blur, impulse noise, and JPEG compression, than CNNs trained solely on RGB images.

Shape Defense Against Adversarial Attacks

2 code implementations31 Aug 2020 Ali Borji

In the first one, a classifier is adversarially trained on images with the edge map as an additional channel.

A Compact Deep Architecture for Real-time Saliency Prediction

no code implementations30 Aug 2020 Samad Zabihi, Hamed Rezazadegan Tavakoli, Ali Borji

Our proposed model consists of a modified U-net architecture, a novel fully connected layer, and central difference convolutional layers.

Saliency Prediction

Bifurcated backbone strategy for RGB-D salient object detection

2 code implementations6 Jul 2020 Yingjie Zhai, Deng-Ping Fan, Jufeng Yang, Ali Borji, Ling Shao, Junwei Han, Liang Wang

In particular, first, we propose to regroup the multi-level features into teacher and student features using a bifurcated backbone strategy (BBS).

RGB-D Salient Object Detection RGB Salient Object Detection +1

Adversarial examples are useful too!

1 code implementation13 May 2020 Ali Borji

Deep learning has come a long way and has enjoyed an unprecedented success.

Backdoor Attack

Harnessing adversarial examples with a surprisingly simple defense

1 code implementation26 Apr 2020 Ali Borji

I introduce a very simple method to defend against adversarial examples.

ObjectNet Dataset: Reanalysis and Correction

1 code implementation4 Apr 2020 Ali Borji

They showed a dramatic performance drop of the state of the art object recognition models on this dataset.

Ranked #4 on Image Classification on ObjectNet (Bounding Box) (using extra training data)

Data Augmentation Image Classification +1

White Noise Analysis of Neural Networks

1 code implementation ICLR 2020 Ali Borji, Sikun Lin

A white noise analysis of modern deep neural networks is presented to unveil their biases at the whole network level or the single neuron level.

General Classification

Empirical Upper Bound in Object Detection and More

1 code implementation27 Nov 2019 Ali Borji, Seyed Mehdi Iranmanesh

Object detection remains as one of the most notorious open problems in computer vision.

Object Detection

DAVE: A Deep Audio-Visual Embedding for Dynamic Saliency Prediction

2 code implementations25 May 2019 Hamed R. -Tavakoli, Ali Borji, Esa Rahtu, Juho Kannala

Our results suggest that (1) audio is a strong contributing cue for saliency prediction, (2) salient visible sound-source is the natural cause of the superiority of our Audio-Visual model, (3) richer feature representations for the input space leads to more powerful predictions even in absence of more sophisticated saliency decoders, and (4) Audio-Visual model improves over 53. 54\% of the frames predicted by the best Visual model (our baseline).

Saliency Prediction Video Saliency Prediction

How is Gaze Influenced by Image Transformations? Dataset and Model

1 code implementation16 May 2019 Zhaohui Che, Ali Borji, Guangtao Zhai, Xiongkuo Min, Guodong Guo, Patrick Le Callet

Data size is the bottleneck for developing deep saliency models, because collecting eye-movement data is very time consuming and expensive.

Data Augmentation Saliency Prediction

Digging Deeper into Egocentric Gaze Prediction

no code implementations12 Apr 2019 Hamed R. -Tavakoli, Esa Rahtu, Juho Kannala, Ali Borji

Extensive experiments over multiple datasets reveal that (1) spatial biases are strong in egocentric videos, (2) bottom-up saliency models perform poorly in predicting gaze and underperform spatial biases, (3) deep features perform better compared to traditional features, (4) as opposed to hand regions, the manipulation point is a strong influential cue for gaze prediction, (5) combining the proposed recurrent model with bottom-up cues, vanishing points and, in particular, manipulation point results in the best gaze prediction accuracy over egocentric videos, (6) the knowledge transfer works best for cases where the tasks or sequences are similar, and (7) task and activity recognition can benefit from gaze prediction.

Activity Recognition Gaze Prediction +2

Adversarial Attacks against Deep Saliency Models

no code implementations2 Apr 2019 Zhaohui Che, Ali Borji, Guangtao Zhai, Suiyi Ling, Guodong Guo, Patrick Le Callet

The proposed attack only requires a part of the model information, and is able to generate a sparser and more insidious adversarial perturbation, compared to traditional image-space attacks.

Adversarial Attack Object Detection

Human Attention in Image Captioning: Dataset and Analysis

no code implementations ICCV 2019 Sen He, Hamed R. -Tavakoli, Ali Borji, Nicolas Pugeault

In this work, we present a novel dataset consisting of eye movements and verbal descriptions recorded synchronously over images.

Image Captioning

Understanding and Visualizing Deep Visual Saliency Models

1 code implementation CVPR 2019 Sen He, Hamed R. -Tavakoli, Ali Borji, Yang Mi, Nicolas Pugeault

Our analyses reveal that: 1) some visual regions (e. g. head, text, symbol, vehicle) are already encoded within various layers of the network pre-trained for object recognition, 2) using modern datasets, we find that fine-tuning pre-trained models for saliency prediction makes them favor some categories (e. g. head) over some others (e. g. text), 3) although deep models of saliency outperform classical models on natural images, the converse is true for synthetic stimuli (e. g. pop-out search arrays), an evidence of significant difference between human and data-driven saliency models, and 4) we confirm that, after-fine tuning, the change in inner-representations is mostly due to the task and not the domain shift in the data.

Object Recognition Saliency Prediction +1

Video Summarization via Actionness Ranking

no code implementations1 Mar 2019 Mohamed Elfeki, Ali Borji

Prior work proposed supervised and unsupervised algorithms to train models for learning the underlying behavior of humans by increasing modeling complexity or craft-designing better heuristics to simulate human summary generation process.

Video Summarization

From Third Person to First Person: Dataset and Baselines for Synthesis and Retrieval

1 code implementation1 Dec 2018 Mohamed Elfeki, Krishna Regmi, Shervin Ardeshir, Ali Borji

In this work, we introduce two datasets (synthetic and natural/real) containing simultaneously recorded egocentric and exocentric videos.

Domain Adaptation Frame +1

Multi-Stream Dynamic Video Summarization

1 code implementation1 Dec 2018 Mohamed Elfeki, Liqiang Wang, Ali Borji

With vast amounts of video content being uploaded to the Internet every minute, video summarization becomes critical for efficient browsing, searching, and indexing of visual content.

Video Summarization

Bottom-up Attention, Models of

no code implementations11 Oct 2018 Ali Borji, Hamed R. -Tavakoli, Zoya Bylinskii

In this review, we examine the recent progress in saliency prediction and proposed several avenues for future research.

Saliency Prediction

Invariance Analysis of Saliency Models versus Human Gaze During Scene Free Viewing

1 code implementation10 Oct 2018 Zhaohui Che, Ali Borji, Guangtao Zhai, Xiongkuo Min

Most of current studies on human gaze and saliency modeling have used high-quality stimuli.

Data Augmentation

Saliency Prediction in the Deep Learning Era: Successes, Limitations, and Future Challenges

no code implementations8 Oct 2018 Ali Borji

Visual saliency models have enjoyed a big leap in performance in recent years, thanks to advances in deep learning and large scale annotated data.

Saliency Prediction

Understanding Perceptual and Conceptual Fluency at a Large Scale

no code implementations ECCV 2018 Shengli Hu, Ali Borji

We create a dataset of 543, 758 logo designs spanning 39 industrial categories and 216 countries.

Causal Inference

Integrating Egocentric Videos in Top-view Surveillance Videos: Joint Identification and Temporal Alignment

no code implementations ECCV 2018 Shervin Ardeshir, Ali Borji

Videos recorded from first person (egocentric) perspective have little visual appearance in common with those from third person perspective, especially with videos captured by top-view surveillance cameras.

Cross-view image synthesis using geometry-guided conditional GANs

2 code implementations14 Aug 2018 Krishna Regmi, Ali Borji

For this, we propose to use homography as a guide to map the images between the views based on the common field of view to preserve the details in the input image.

Cross-View Image-to-Image Translation Image Generation

Improving Sequential Determinantal Point Processes for Supervised Video Summarization

no code implementations ECCV 2018 Aidean Sharghi, Ali Borji, Chengtao Li, Tianbao Yang, Boqing Gong

In terms of modeling, we design a new probabilistic distribution such that, when it is integrated into SeqDPP, the resulting model accepts user input about the expected length of the summary.

Point Processes Supervised Video Summarization

Learning a Saliency Evaluation Metric Using Crowdsourced Perceptual Judgments

no code implementations27 Jun 2018 Changqun Xia, Jia Li, Jinming Su, Ali Borji

Due to the effectiveness of the learned metric, it also can be used to facilitate the development of new models for fixation prediction.

Detect Globally, Refine Locally: A Novel Approach to Saliency Detection

no code implementations CVPR 2018 Tiantian Wang, Lihe Zhang, Shuo Wang, Huchuan Lu, Gang Yang, Xiang Ruan, Ali Borji

Moreover, to effectively recover object boundaries, we propose a local Boundary Refinement Network (BRN) to adaptively learn the local contextual information for each spatial position.

RGB Salient Object Detection Saliency Detection +1

Learning to Promote Saliency Detectors

1 code implementation CVPR 2018 Yu Zeng, Huchuan Lu, Lihe Zhang, Mengyang Feng, Ali Borji

The categories and appearance of salient objects vary from image to image, therefore, saliency detection is an image-specific task.

Saliency Detection Small Data Image Classification +1

Salient Object Detection Driven by Fixation Prediction

1 code implementation CVPR 2018 Wenguan Wang, Jianbing Shen, Xingping Dong, Ali Borji

Salient object detection is then viewed as fine-grained object-level saliency segmentation and is progressively optimized with the guidance of the fixation map in a top-down manner.

RGB Salient Object Detection Salient Object Detection

Enhanced-alignment Measure for Binary Foreground Map Evaluation

2 code implementations26 May 2018 Deng-Ping Fan, Cheng Gong, Yang Cao, Bo Ren, Ming-Ming Cheng, Ali Borji

The existing binary foreground map (FM) measures to address various types of errors in either pixel-wise or structural ways.

Three Birds One Stone: A General Architecture for Salient Object Segmentation, Edge Detection and Skeleton Extraction

no code implementations27 Mar 2018 Qibin Hou, Jiang-Jiang Liu, Ming-Ming Cheng, Ali Borji, Philip H. S. Torr

Although these tasks are inherently very different, we show that our unified approach performs very well on all of them and works far better than current single-purpose state-of-the-art methods.

Edge Detection Semantic Segmentation

Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground

no code implementations ECCV 2018 Deng-Ping Fan, Ming-Ming Cheng, Jiang-Jiang Liu, Shang-Hua Gao, Qibin Hou, Ali Borji

Our analysis identifies a serious design bias of existing SOD datasets which assumes that each image contains at least one clearly outstanding salient object in low clutter.

RGB Salient Object Detection Salient Object Detection

What Catches the Eye? Visualizing and Understanding Deep Saliency Models

no code implementations15 Mar 2018 Sen He, Ali Borji, Yang Mi, Nicolas Pugeault

Deep convolutional neural networks have demonstrated high performances for fixation prediction in recent years.

Analysis of Hand Segmentation in the Wild

1 code implementation CVPR 2018 Aisha Urooj Khan, Ali Borji

In the quest for robust hand segmentation methods, we evaluated the performance of the state of the art semantic segmentation methods, off the shelf and fine-tuned, on existing datasets.

Fine-grained Action Recognition Hand Segmentation +1

Pros and Cons of GAN Evaluation Measures

4 code implementations9 Feb 2018 Ali Borji

Generative models, in particular generative adversarial networks (GANs), have received significant attention recently.

Visual Weather Temperature Prediction

no code implementations25 Jan 2018 Wei-Ta Chu, Kai-Chia Ho, Ali Borji

In this paper, we attempt to employ convolutional recurrent neural networks for weather temperature estimation using only image data.

Revisiting Video Saliency: A Large-scale Benchmark and a New Model

1 code implementation CVPR 2018 Wenguan Wang, Jianbing Shen, Fang Guo, Ming-Ming Cheng, Ali Borji

Existing video saliency datasets lack variety and generality of common dynamic scenes and fall short in covering challenging situations in unconstrained environments.

Segmenting Sky Pixels in Images

no code implementations26 Dec 2017 Cecilia La Place, Aisha Urooj Khan, Ali Borji

As a result of our efforts, we have seen an improvement of 10-15% in the average MCR compared to the prior methods on SkyFinder dataset.

Scene Parsing

A Stagewise Refinement Model for Detecting Salient Objects in Images

no code implementations ICCV 2017 Tiantian Wang, Ali Borji, Lihe Zhang, Pingping Zhang, Huchuan Lu

To remedy this problem, here we propose to augment feedforward neural networks with a novel pyramid pooling module and a multi-stage refinement mechanism for saliency detection.

RGB Salient Object Detection Saliency Detection +1

Statistics of Deep Generated Images

no code implementations9 Aug 2017 Yu Zeng, Huchuan Lu, Ali Borji

Here, we explore the low-level statistics of images generated by state-of-the-art deep generative models.

An Unsupervised Game-Theoretic Approach to Saliency Detection

no code implementations8 Aug 2017 Yu Zeng, Huchuan Lu, Ali Borji, Mengyang Feng

Saliency maps are generated according to each region's strategy in the Nash equilibrium of the proposed Saliency Game.

RGB Salient Object Detection Saliency Detection +1

Human-like Clustering with Deep Convolutional Neural Networks

1 code implementation15 Jun 2017 Ali Borji, Aysegul Dundar

We do not dwell much on the learning mechanisms in these frameworks as they are still a matter of debate, with respect to biological constraints.

Object Recognition Semantic Segmentation

Saliency Revisited: Analysis of Mouse Movements versus Fixations

no code implementations CVPR 2017 Hamed R. -Tavakoli, Fawad Ahmed, Ali Borji, Jorma Laaksonen

This paper revisits visual saliency prediction by evaluating the recent advancements in this field such as crowd-sourced mouse tracking-based databases and contextual annotations.

Model Selection Saliency Prediction

What are the Receptive, Effective Receptive, and Projective Fields of Neurons in Convolutional Neural Networks?

no code implementations19 May 2017 Hung Le, Ali Borji

In this work, we explain in detail how receptive fields, effective receptive fields, and projective fields of neurons in different layers, convolution or pooling, of a Convolutional Neural Network (CNN) are calculated.

Negative Results in Computer Vision: A Perspective

no code implementations11 May 2017 Ali Borji

A negative result is when the outcome of an experiment or a model is not what is expected or when a hypothesis does not hold.

Experimental Design Two-sample testing

Paying Attention to Descriptions Generated by Image Captioning Models

2 code implementations ICCV 2017 Hamed R. -Tavakoli, Rakshith Shetty, Ali Borji, Jorma Laaksonen

To bridge the gap between humans and machines in image understanding and describing, we need further insight into how people describe a perceived scene.

Image Captioning

EgoTransfer: Transferring Motion Across Egocentric and Exocentric Domains using Deep Neural Networks

no code implementations17 Dec 2016 Shervin Ardeshir, Krishna Regmi, Ali Borji

On one hand, the abundance of egocentric cameras in the past few years has offered the opportunity to study a lot of vision problems from the first-person perspective.

Learning to predict where to look in interactive environments using deep recurrent q-learning

no code implementations17 Dec 2016 Sajad Mousavi, Michael Schukat, Enda Howley, Ali Borji, Nasser Mozayani

Bottom-Up (BU) saliency models do not perform well in complex interactive environments where humans are actively engaged in tasks (e. g., sandwich making and playing the video games).

Atari Games Q-Learning +1

Exploiting inter-image similarity and ensemble of extreme learners for fixation prediction using deep features

1 code implementation20 Oct 2016 Hamed R. -Tavakoli, Ali Borji, Jorma Laaksonen, Esa Rahtu

This paper presents a novel fixation prediction and saliency modeling framework based on inter-image similarities and ensemble of Extreme Learning Machines (ELM).

Egocentric Height Estimation

no code implementations9 Oct 2016 Jessica Finocchiaro, Aisha Urooj Khan, Ali Borji

We used both traditional computer vision approaches and deep learning in order to determine the visual cues that results in best height estimation.

Object Recognition Object Tracking +1

Vanishing point detection with convolutional neural networks

no code implementations4 Sep 2016 Ali Borji

Inspired by the finding that vanishing point (road tangent) guides driver's gaze, in our previous work we showed that vanishing point attracts gaze during free viewing of natural scenes as well as in visual search (Borji et al., Journal of Vision 2016).

Egocentric Meets Top-view

no code implementations30 Aug 2016 Shervin Ardeshir, Ali Borji

First, having a set of egocentric videos and a top-view video, can we verify if the top-view video contains all, or some of the egocentric viewers present in the egocentric set?

Graph Matching

Ego2Top: Matching Viewers in Egocentric and Top-view Videos

no code implementations24 Jul 2016 Shervin Ardeshir, Ali Borji

At the same time, surveillance cameras and drones offer an abundance of visual information, often captured from top-view.

Graph Matching

iLab-20M: A Large-Scale Controlled Object Dataset to Investigate Deep Learning

no code implementations CVPR 2016 Ali Borji, Saeed Izadi, Laurent Itti

Tolerance to image variations (e. g. translation, scale, pose, illumination, background) is an important desired property of any object recognition system, be it human or machine.

Domain Adaptation Object Recognition +1

Fixation prediction with a combined model of bottom-up saliency and vanishing point

no code implementations6 Dec 2015 Mengyang Feng, Ali Borji, Huchuan Lu

By predicting where humans look in natural scenes, we can understand how they perceive complex natural scenes and prioritize information for further high-level visual processing.

Vanishing point attracts gaze in free-viewing and visual search tasks

no code implementations6 Dec 2015 Ali Borji, Mengyang Feng

In the second experiment, we asked 14 subjects (4 female, mean age 23. 07, SD=1. 26) to search for a target character (T or L) placed randomly on a 3x3 imaginary grid overlaid on top of an image.

What can we learn about CNNs from a large scale controlled object dataset?

no code implementations4 Dec 2015 Ali Borji, Saeed Izadi, Laurent Itti

Tolerance to image variations (e. g. translation, scale, pose, illumination) is an important desired property of any object recognition system, be it human or machine.

Domain Adaptation Object Recognition +1

Computational models: Bottom-up and top-down aspects

no code implementations27 Oct 2015 Laurent Itti, Ali Borji

We focus on {\em computational models of attention} as defined by Tsotsos \& Rothenstein \shortcite{Tsotsos_Rothenstein11}: Models which can process any visual stimulus (typically, an image or video clip), which can possibly also be given some task definition, and which make predictions that can be compared to human or animal behavioral or physiological responses elicited by the same stimulus and task.

Computational models of attention

no code implementations24 Oct 2015 Laurent Itti, Ali Borji

This chapter reviews recent computational models of visual attention.

CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Research

2 code implementations14 May 2015 Ali Borji, Laurent Itti

Saliency modeling has been an active research area in computer vision for about two decades.

Reconciling saliency and object center-bias hypotheses in explaining free-viewing fixations

no code implementations30 Mar 2015 Ali Borji, James Tanner

Predicting where people look in natural scenes has attracted a lot of interest in computer vision and computational neuroscience over the past two decades.

Salient Object Detection: A Benchmark

no code implementations5 Jan 2015 Ali Borji, Ming-Ming Cheng, Huaizu Jiang, Jia Li

We extensively compare, qualitatively and quantitatively, 40 state-of-the-art models (28 salient object detection, 10 fixation prediction, 1 objectness, and 1 baseline) over 6 challenging datasets for the purpose of benchmarking salient object detection and segmentation methods.

RGB Salient Object Detection Salient Object Detection

What is a salient object? A dataset and a baseline model for salient object detection

no code implementations8 Dec 2014 Ali Borji

While the notion of most salient object is sensible when multiple objects exist in a scene, current datasets for evaluation of saliency detection approaches often have scenes with only one single object.

RGB Salient Object Detection Saliency Detection +2

Salient Object Detection: A Survey

no code implementations18 Nov 2014 Ali Borji, Ming-Ming Cheng, Qibin Hou, Huaizu Jiang, Jia Li

Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision.

Object Proposal Generation RGB Salient Object Detection +2

Human vs. Computer in Scene and Object Recognition

no code implementations CVPR 2014 Ali Borji, Laurent Itti

Several decades of research in computer and primate vision have resulted in many models (some specialized for one problem, others more general) and invaluable experimental data.

Object Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.