Related papers: GASP: Gated Attention For Saliency Prediction
Two prominent strategies that the human visual system uses to reduce incoming information are spatial integration and selective attention. Although spatial integration summarizes and combines information over the visual field, selective…
Salient object detection is subjective in nature, which implies that multiple estimations should be related to the same input image. Most existing salient object detection models are deterministic following a point to point estimation…
Recent progress in brain-guided image generation has improved the quality of fMRI-based reconstructions; however, fundamental challenges remain in preserving object-level structure and semantic fidelity. Many existing approaches overlook…
Gaze is a powerful form of non-verbal communication and social interaction that humans develop from an early age. As such, modeling this behavior is an important task that can benefit a broad set of application domains ranging from robotics…
The ability to selectively attend to relevant stimuli while filtering out distractions is essential for agents that process complex, high-dimensional sensory input. This paper introduces a model of covert and overt visual attention through…
Saliency methods interpret the prediction of a neural network by showing the importance of input elements for that prediction. A popular family of saliency methods utilize gradient information. In this work, we empirically show that two…
A smart vehicle should be able to understand human behavior and predict their actions to avoid hazardous situations. Specific traits in human behavior can be automatically predicted, which can help the vehicle make decisions, increasing…
Traditional gaze estimation methods typically require explicit user calibration to achieve high accuracy. This process is cumbersome and recalibration is often required when there are changes in factors such as illumination and pose. To…
Social recommendation leverages social information to solve data sparsity and cold-start problems in traditional collaborative filtering methods. However, most existing models assume that social effects from friend users are static and…
Reusable embeddings of user behaviour have shown significant performance improvements for the personalised saliency prediction task. However, prior works require explicit user characteristics and preferences as input, which are often…
Retailers have long been searching for ways to effectively understand their customers' behaviour in order to provide a smooth and pleasant shopping experience that attracts more customers everyday and maximises their revenue, consequently.…
It is well known that human gaze carries significant information about visual attention. However, there are three main difficulties in incorporating the gaze data in an attention mechanism of deep neural networks: 1) the gaze fixation…
Pedestrian trajectory prediction is an important technique of autonomous driving, which has become a research hot-spot in recent years. Previous methods mainly rely on the position relationship of pedestrians to model social interaction,…
Humans utilize their gaze to concentrate on essential information while perceiving and interpreting intentions in videos. Incorporating human gaze into computational algorithms can significantly enhance model performance in video…
Attention--or attribution--maps methods are methods designed to highlight regions of the model's input that were discriminative for its predictions. However, different attention maps methods can highlight different regions of the input,…
Recently, there has been a growing interest in developing saliency methods that provide visual explanations of network predictions. Still, the usability of existing methods is limited to image classification models. To overcome this…
To bridge the gap between humans and machines in image understanding and describing, we need further insight into how people describe a perceived scene. In this paper, we study the agreement between bottom-up saliency-based visual attention…
Extensive research has been conducted on assessing grasp stability, a crucial prerequisite for achieving optimal grasping strategies, including the minimum force grasping policy. However, existing works employ basic feature-level fusion…
Deep convolutional neural networks have demonstrated high performances for fixation prediction in recent years. How they achieve this, however, is less explored and they remain to be black box models. Here, we attempt to shed light on the…
Most automatic matting methods try to separate the salient foreground from the background. However, the insufficient quantity and subjective bias of the current existing matting datasets make it difficult to fully explore the semantic…