Related papers: Plan-Recognition-Driven Attention Modeling for Vis…

The idea of using the recurrent neural network for visual attention has gained popularity in computer vision community. Although the recurrent attention model (RAM) leverages the glimpses with more large patch size to increasing its scope,…

Event-based cameras are neuromorphic sensors capable of efficiently encoding visual information in the form of sparse sequences of events. Being biologically inspired, they are commonly used to exploit some of the computational and power…

We are interested in inferring object segmentation by leveraging only object class information, and by considering only minimal priors on the object segmentation task. This problem could be viewed as a kind of weakly supervised segmentation…

Human visual system can selectively attend to parts of a scene for quick perception, a biological mechanism known as Human attention. Inspired by this, recent deep learning models encode attention mechanisms to focus on the most…

Psychological studies have found that human visual tracking system involves learning, memory, and planning. Despite recent successes, not many works have focused on memory and planning in deep learning based tracking. We are thus interested…

Vision-Language Models (VLMs) excel at many multimodal tasks, yet they frequently struggle with tasks requiring precise understanding and handling of fine-grained visual elements. This is mainly due to information loss during image encoding…

Autonomous agents embedded in a physical environment need the ability to recognize objects and their properties from sensory data. Such a perceptual ability is often implemented by supervised machine learning models, which are pre-trained…

There has recently been significant interest in training reinforcement learning (RL) agents in vision-based environments. This poses many challenges, such as high dimensionality and the potential for observational overfitting through…

Human attention mechanisms often work in a top-down manner, yet it is not well explored in vision research. Here, we propose the Top-Down Attention Framework (TDAF) to capture top-down attentions, which can be easily adopted in most…

Visual priming is known to affect the human visual system to allow detection of scene elements, even those that may have been near unnoticeable before, such as the presence of camouflaged animals. This process has been shown to be an effect…

Convolutional neural networks (CNNs) have been shown to be state-of-the-art models for visual cortical neurons. Cortical neurons in the primary visual cortex are sensitive to contextual information mediated by extensive horizontal and…

The utilization of prior knowledge about anomalies is an essential issue for anomaly detections. Recently, the visual attention mechanism has become a promising way to improve the performance of CNNs for some computer vision tasks. In this…

Contexts play an important role in the saliency detection task. However, given a context region, not all contextual information is helpful for the final task. In this paper, we propose a novel pixel-wise contextual attention network, i.e.,…

In saliency detection, every pixel needs contextual information to make saliency prediction. Previous models usually incorporate contexts holistically. However, for each pixel, usually only part of its context region is useful and…

Background noise and scale variation are common problems that have been long recognized in crowd counting. Humans glance at a crowd image and instantly know the approximate number of human and where they are through attention the crowd…

We present an extension to masked autoencoders (MAE) which improves on the representations learnt by the model by explicitly encouraging the learning of higher scene-level features. We do this by: (i) the introduction of a perceptual…

We present a reward-predictive, model-based deep learning method featuring trajectory-constrained visual attention for local planning in visual navigation tasks. Our method learns to place visual attention at locations in latent image space…

We present lambda layers -- an alternative framework to self-attention -- for capturing long-range interactions between an input and structured contextual information (e.g. a pixel surrounded by other pixels). Lambda layers capture such…

Data augmentation is usually adopted to increase the amount of training data, prevent overfitting and improve the performance of deep models. However, in practice, random data augmentation, such as random image cropping, is low-efficiency…

Despite the impressive progress brought by deep network in visual object recognition, robot vision is still far from being a solved problem. The most successful convolutional architectures are developed starting from ImageNet, a large scale…