Related papers: Context-Aware Interaction Network for RGB-T Semant…

Video semantic segmentation requires to utilize the complex temporal relations between frames of the video sequence. Previous works usually exploit accurate optical flow to leverage the temporal relations, which suffer much from heavy…

3D scene understanding is important for robots to interact with the 3D world in a meaningful way. Most previous works on 3D scene understanding focus on recognizing geometrical or semantic properties of the scene independently. In this…

RGB-Thermal (RGB-T) semantic segmentation is essential for robotic systems operating in low-light or dark environments. However, traditional approaches often overemphasize modality balance, resulting in limited robustness and severe…

Technologies to predict human actions are extremely important for applications such as human robot cooperation and autonomous driving. However, a majority of the existing algorithms focus on exploiting visual features of the videos and do…

This paper presents GridNet, a new Convolutional Neural Network (CNN) architecture for semantic image segmentation (full scene labelling). Classical neural networks are implemented as one stream from the input to the output with subsampling…

Semantic segmentation is a key technology for autonomous vehicles to understand the surrounding scenes. The appealing performances of contemporary models usually come at the expense of heavy computations and lengthy inference time, which is…

A key challenge in continuous sign language recognition (CSLR) is to efficiently capture long-range spatial interactions over time from the video input. To address this challenge, we propose TCNet, a hybrid network that effectively models…

Semantic segmentation assigns labels to pixels in images, a critical yet challenging task in computer vision. Convolutional methods, although capturing local dependencies well, struggle with long-range relationships. Vision Transformers…

Pattern recognition through the fusion of RGB frames and Event streams has emerged as a novel research area in recent years. Current methods typically employ backbone networks to individually extract the features of RGB frames and event…

In recent years, how to strike a good trade-off between accuracy and inference speed has become the core issue for real-time semantic segmentation applications, which plays a vital role in real-world scenarios such as autonomous driving…

This paper investigates how to perform robust visual tracking in adverse and challenging conditions using complementary visual and thermal infrared data (RGBT tracking). We propose a novel deep network architecture called qualityaware…

Emotion recognition is a crucial task for human conversation understanding. It becomes more challenging with the notion of multimodal data, e.g., language, voice, and facial expressions. As a typical solution, the global- and the local…

State-of-the-art semantic image segmentation methods are mostly based on training deep convolutional neural networks (CNNs). In this work, we proffer to improve semantic segmentation with the use of contextual information. In particular, we…

Semantic segmentation is an essential technology for self-driving cars to comprehend their surroundings. Currently, real-time semantic segmentation networks commonly employ either encoder-decoder architecture or two-pathway architecture.…

Image segmentation is a historic and significant computer vision task. With the help of deep learning techniques, image semantic segmentation has made great progresses. Over recent years, based on guidance of attention mechanism compared…

The ability to endow maps of indoor scenes with semantic information is an integral part of robotic agents which perform different tasks such as target driven navigation, object search or object rearrangement. The state-of-the-art methods…

Understanding complex scenarios from in-vehicle cameras is essential for safely operating autonomous driving systems in densely populated areas. Among these, intersection areas are one of the most critical as they concentrate a considerable…

Change detection encompasses a variety of task types, and the goal of building change detection (BCD) tasks is to accurately locate buildings and distinguish changed building areas. In recent years, various deep learning-based BCD methods…

Dynamic Scene Graph Generation (DSGG) models how object relations evolve over time in videos. However, existing methods are trained only on annotated object pairs and lack guidance for non-related pairs, making it difficult to identify…

Given a question-image input, the Visual Commonsense Reasoning (VCR) model can predict an answer with the corresponding rationale, which requires inference ability from the real world. The VCR task, which calls for exploiting the…