Search Results for author:
Found 49 papers, 14 papers with code
SCOUT+: Towards Practical Task-Driven Drivers' Gaze Prediction
In this paper, we address the challenge of effective modeling of task and context with common sources of data for use in practical systems.
Data Limitations for Modeling Top-Down Effects on Drivers' Attention
The crux of the problem is lack of public data with annotations that could be used to train top-down models and evaluate how well models of any kind capture effects of task on attention.
Understanding and Modeling the Effects of Task and Context on Drivers' Gaze Allocation
Therefore, to enable analysis and modeling of these factors for drivers' gaze prediction, we propose the following: 1) we correct the data processing pipeline used in DR(eye)VE to reduce noise in the recorded gaze data; 2) we then add per-frame labels for driving task and context; 3) we benchmark a number of baseline and SOTA models for saliency and driver gaze prediction and use new annotations to analyze how their performance changes in scenarios involving different tasks; and, lastly, 4) we develop a novel model that modulates drivers' gaze prediction with explicit action and context information.
The Psychophysics of Human Three-Dimensional Active Visuospatial Problem-Solving
How well the visual system performs while interacting with the visual environment and how vision is used in the real world have not been well studied, especially in humans.
Self-attention in Vision Transformers Performs Perceptual Grouping, Not Attention
To answer this question, we revisited the attention formulation in these models and found that despite the name, computationally, these models perform a special class of relaxation labeling with similarity grouping effects.
Learning a model of shape selectivity in V4 cells reveals shape encoding mechanisms in the brain
We propose a hierarchical model that reveals V1/V2 encodings that are essential components for this transformation to the reported curvature representations in V4.
Next-Best-View Estimation based on Deep Reinforcement Learning for Active Object Classification
This leads to a viewpoint that provides a more accurate prediction to distinguish such an object from other objects better.
Active Observer Visual Problem-Solving Methods are Dynamically Hypothesized, Deployed and Tested
The importance of active observation is striking as is the lack of any learning effect.
Industry and Academic Research in Computer Vision
The results indicate that the distribution of the research topics is similar in industry and academic papers.
Probing the Effect of Selection Bias on Generalization: A Thought Experiment
The point of the thought experiment is not to demonstrate problems with all learned systems.
Behavioral Research and Practical Models of Drivers' Attention
Drivers deal with multiple concurrent tasks, such as keeping the vehicle in the lane, observing and anticipating the actions of other road users, reacting to hazards, and dealing with distractions inside and outside the vehicle.
Blocks World Revisited: The Effect of Self-Occlusion on Classification by Convolutional Neural Networks
We present baseline evaluations with five well-known classification deep neural networks and show that TEOS poses a significant challenge for all of them.
Video action recognition for lane-change classification and prediction of surrounding vehicles
Up to four different two-stream-based approaches, that have been successfully applied to address human action recognition, are adapted here by stacking visual cues from forward-looking video cameras to recognize and anticipate lane-changes of target vehicles.
On the Control of Attentional Processes in Vision
The key conclusions of this paper are that an executive controller is necessary for human attentional function in vision, and that there is a 'first principles' computational approach to its understanding that is complementary to the previous approaches that focus on modelling or learning from experimental observations directly.
An Empirical Method to Quantify the Peripheral Performance Degradation in Deep Networks
When applying a convolutional kernel to an image, if the output is to remain the same size as the input then some form of padding is required around the image boundary, meaning that for each layer of convolution in a convolutional neural network (CNN), a strip of pixels equal to the half-width of the kernel size is produced with a non-veridical representation.
PESAO: Psychophysical Experimental Setup for Active Observers
Nonetheless, how exactly active observation occurs in humans so that it can inform the design of active computer vision systems is an open problem.
Two-Stream Networks for Lane-Change Prediction of Surrounding Vehicles
Different sizes of the regions around the vehicles are analyzed, evaluating the importance of the interaction between vehicles and the context information in the performance.
Pedestrian Action Anticipation using Contextual Feature Fusion in Stacked RNNs
To this end, we propose a solution for the problem of pedestrian action anticipation at the point of crossing.
Do Saliency Models Detect Odd-One-Out Targets? New Datasets and Evaluations
Furthermore, we investigate the effect of training state-of-the-art CNN-based saliency models on these types of stimuli and conclude that the additional training data does not lead to a significant improvement of their ability to find odd-one-out targets.
A Possible Reason for why Data-Driven Beats Theory-Driven Computer Vision
This reveals a strong mismatch between optimal performance ranges of classical theory-driven algorithms and sensor setting distributions in the common vision datasets, while data-driven models were trained for those datasets.
Scene Classification in Indoor Environments for Robots using Context Based Word Embeddings
Scene Classification has been addressed with numerous techniques in computer vision literature.
Fast Visual Object Tracking with Rotated Bounding Boxes
In this paper, we demonstrate a novel algorithm that uses ellipse fitting to estimate the bounding box rotation angle and size with the segmentation(mask) on the target for online and real-time visual object tracking.
Ranked #1 on
Visual Object Tracking
on VOT2016
Multiplicative modulations in hue-selective cells enhance unique hue representation
Our simulation results indicate that multiplicative modulations have significant contributions in encoding of hues along intermediate directions in the MacLeod-Boynton diagram and that model V4 neurons have the capacity to encode unique hues.
High-Level Perceptual Similarity is Enabled by Learning Diverse Tasks
Predicting human perceptual similarity is a challenging subject of ongoing research.
Rapid Visual Categorization is not Guided by Early Salience-Based Selection
The current dominant visual processing paradigm in both human and machine research is the feedforward, layered hierarchy of neural-like processing elements.
Early recurrence enables figure border ownership
Various models proposed that feedback from higher ventral areas or lateral connections could provide the required contextual information.
SMILER: Saliency Model Implementation Library for Experimental Research
The Saliency Model Implementation Library for Experimental Research (SMILER) is a new software package which provides an open, standardized, and extensible framework for maintaining and executing computational saliency models.
The Elephant in the Room
We showcase a family of common failures of state-of-the art object detectors.
Attention-based Active Visual Search for Mobile Robots
In this paper, we propose a new model that actively extracts visual information via visual attention techniques and, in conjunction with a non-myopic decision-making algorithm, leads the robot to search more relevant areas of the environment.
Visual Attention and its Intimate Links to Spatial Cognition
It is almost universal to regard attention as the facility that permits an agent, human or machine, to give priority processing resources to relevant stimuli while ignoring the irrelevant.
Active Fixation Control to Predict Saccade Sequences
However, on static images the emphasis of these models has largely been based on non-ordered prediction of fixations through a saliency map.
Autonomous Vehicles that Interact with Pedestrians: A Survey of Theory and Practice
To make it a reality, autonomous vehicles require the ability to communicate with other road users and understand their intentions.
Random Polyhedral Scenes: An Image Generator for Active Vision System Experiments
We present a Polyhedral Scene Generator system which creates a random scene based on a few user parameters, renders the scene from random view points and creates a dataset containing the renderings and corresponding annotation files.
Totally Looks Like - How Humans Compare, Compared to Machines
Perceptual judgment of image similarity by humans relies on rich internal representations ranging from low-level features to high-level concepts, scene properties and even cultural associations.
Bridging Cognitive Programs and Machine Learning
While great advances are made in pattern recognition and machine learning, the successes of such fields remain restricted to narrow applications and seem to break down when training data is scarce, a shift in domain occurs, or when intelligent reasoning is required for rapid adaptation to new environments.
Challenging Images For Minds and Machines
There is no denying the tremendous leap in the performance of machine learning methods in the past half-decade.
Joint Attention in Driver-Pedestrian Interaction: from Theory to Practice
Today, one of the major challenges that autonomous vehicles are facing is the ability to drive in urban environments.
Intriguing Properties of Randomly Weighted Networks: Generalizing While Learning Next to Nothing
The implications of this intriguing property of deep neural networks are discussed and we suggest ways to harness it to create more robust representations.
Saccade Sequence Prediction: Beyond Static Saliency Maps
The accuracy of such models has dramatically increased recently due to deep learning.
STAR-RT: Visual attention for real-time video game playing
In this paper we present STAR-RT - the first working prototype of Selective Tuning Attention Reference (STAR) model and Cognitive Programs (CPs).
Priming Neural Networks
This process has been shown to be an effect of top-down signaling in the visual system triggered by the said cue.
Vision-Based Fallen Person Detection for the Elderly
Furthermore, our system consists of a reasoning module which formulates a number of measures to reason whether a person is fallen.
Color-opponent mechanisms for local hue encoding in a hierarchical framework
A biologically plausible computational model for color representation is introduced.
Incremental Learning Through Deep Adaptation
Given an existing trained neural network, it is often desirable to learn new capabilities without hindering performance of those already learned.
Integrating Three Mechanisms of Visual Attention for Active Visual Search
Algorithms for robotic visual search can benefit from the use of visual attention methods in order to reduce computational costs.
The Effect of Color Space Selection on Detectability and Discriminability of Colored Objects
The results indicate that on average color space C1C2C3 followed by HSI and XYZ achieve the best time in searching for objects of various colors.
A Review of 40 Years of Cognitive Architecture Research: Core Cognitive Abilities and Practical Applications
Thus, in this survey we wanted to shift the focus towards a more inclusive and high-level overview of the research on cognitive architectures.
Joint Attention in Autonomous Driving (JAAD)
In this paper we present a novel dataset for a critical aspect of autonomous driving, the joint attention that must occur between drivers and of pedestrians, cyclists or other drivers.
Robotics
Revisiting Active Perception
Despite the recent successes in robotics, artificial intelligence and computer vision, a complete artificial agent necessarily must include active perception.
