Related papers: Guided Visual Attention Model Based on Interaction…

Robots operating in open, unstructured real-world environments must rely on onboard visual perception while autonomously moving across different locations. Continuous changes in onboard camera viewpoints cause significant visual scale…

This paper presents a novel keypoints-based attention mechanism for visual recognition in still images. Deep Convolutional Neural Networks (CNNs) for recognizing images with distinctive classes have shown great success, but their…

We propose an attention-based networks for transferring motions between arbitrary objects. Given a source image(s) and a driving video, our networks animate the subject in the source images according to the motion in the driving video. In…

Recent breakthroughs in Go play and strategic games have witnessed the great potential of reinforcement learning in intelligently scheduling in uncertain environment, but some bottlenecks are also encountered when we generalize this…

Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction. Most of the current existing methods adopt the…

In recent years, a number of models that learn the relations between vision and language from large datasets have been released. These models perform a variety of tasks, such as answering questions about images, retrieving sentences that…

Predicting high-fidelity future human poses, from a historically observed sequence, is decisive for intelligent robots to interact with humans. Deep end-to-end learning approaches, which typically train a generic pre-trained model on…

Visual Commonsense Reasoning (VCR) remains a significant yet challenging research problem in the realm of visual reasoning. A VCR model generally aims at answering a textual question regarding an image, followed by the rationale prediction…

State-of-the-art deep neural network recognition systems are designed for a static and closed world. It is usually assumed that the distribution at test time will be the same as the distribution during training. As a result, classifiers are…

Multi-view deep neural network is perhaps the most successful approach in 3D shape classification. However, the fusion of multi-view features based on max or average pooling lacks a view selection mechanism, limiting its application in,…

Deep learning provides a powerful framework for automated acquisition of complex robotic motions. However, despite a certain degree of generalization, the need for vast amounts of training data depending on the work-object position is an…

Building perceptual systems for robotics which perform well under tight computational budgets requires novel architectures which rethink the traditional computer vision pipeline. Modern vision architectures require the agent to build a…

Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…

Deep reinforcement learning (RL) algorithms can learn complex robotic skills from raw sensory inputs, but have yet to achieve the kind of broad generalization and applicability demonstrated by deep learning methods in supervised domains. We…

Autonomous robots operating in open and changing environments cannot always rely on predefined inputs, outputs, and action routines. Although existing learning methods enable robots to improve their performance through environmental…

Few-shot object detection aims at detecting objects with few annotated examples, which remains a challenging research problem yet to be explored. Recent studies have shown the effectiveness of self-learned top-down attention mechanisms in…

Visual place recognition is a challenging task for applications such as autonomous driving navigation and mobile robot localization. Distracting elements presenting in complex scenes often lead to deviations in the perception of visual…

Existing deep trackers mainly use convolutional neural networks pre-trained for generic object recognition task for representations. Despite demonstrated successes for numerous vision tasks, the contributions of using pre-trained deep…

Solving the camera-to-robot pose is a fundamental requirement for vision-based robot control, and is a process that takes considerable effort and cares to make accurate. Traditional approaches require modification of the robot via markers,…

Although deep convolutional neural networks achieve state-of-the-art performance across nearly all image classification tasks, their decisions are difficult to interpret. One approach that offers some level of interpretability by design is…