Related papers: More Than Meets the Eye: A Semantics-Aware Traffic…

Over the past few years, vision transformers (ViTs) have consistently demonstrated remarkable performance across various visual recognition tasks. However, attempts to enhance their robustness have yielded limited success, mainly focusing…

Adapting a trained model to perform satisfactorily on continually changing testing domains/environments is an important and challenging task. In this work, we propose a novel framework, SATA, which aims to satisfy the following…

More powerful feature representations derived from deep neural networks benefit visual tracking algorithms widely. However, the lack of exploitation on temporal information prevents tracking algorithms from adapting to appearances changing…

Tracking and segmentation play essential roles in video understanding, providing basic positional information and temporal association of objects within video sequences. Despite their shared objective, existing approaches often tackle these…

Domain adaptation has been widely explored by transferring the knowledge from a label-rich source domain to a related but unlabeled target domain. Most existing domain adaptation algorithms attend to adapting feature representations across…

Transformers have become the foundation of numerous state-of-the-art AI models across diverse domains, thanks to their powerful attention mechanism for modeling long-range dependencies. However, the quadratic scaling complexity of attention…

The use of vision transformers (ViT) in computer vision is increasing due to limited inductive biases (e.g., locality, weight sharing, etc.) and increased scalability compared to other deep learning methods. This has led to some initial…

Open-vocabulary Multiple Object Tracking (MOT) aims to generalize trackers to novel categories not in the training set. Currently, the best-performing methods are mainly based on pure appearance matching. Due to the complexity of motion…

In this paper, we introduce the Semantic Environment Atlas (SEA), a novel mapping approach designed to enhance visual navigation capabilities of embodied agents. The SEA utilizes semantic graph maps that intricately delineate the…

The ability to efficiently search for images is essential for improving the user experiences across various products. Incorporating user feedback, via multi-modal inputs, to navigate visual search can help tailor retrieved results to…

Deep Learning has seen an unprecedented increase in vision applications since the publication of large-scale object recognition datasets and introduction of scalable compute hardware. State-of-the-art methods for most vision tasks for…

At present, deep neural network methods have played a dominant role in face alignment field. However, they generally use predefined network structures to predict landmarks, which tends to learn general features and leads to mediocre…

Distribution shifts between training and testing data are a critical bottleneck limiting the practical utility of models, especially in real-world test-time scenarios. To adapt models when the source domain is unknown and the target domain…

Multimodal aspect-based sentiment analysis (MABSA) aims to understand opinions in a granular manner, advancing human-computer interaction and other fields. Traditionally, MABSA methods use a joint prediction approach to identify aspects and…

Although point-based networks are demonstrated to be accurate for 3D point cloud modeling, they are still falling behind their voxel-based competitors in 3D detection. We observe that the prevailing set abstraction design for down-sampling…

Domain generalization (DG) aims to enhance the model robustness against domain shifts without accessing target domains. A prevalent category of methods for DG is data augmentation, which focuses on generating virtual samples to simulate…

Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…

While deep face recognition models have demonstrated remarkable performance, they often struggle on the inputs from domains beyond their training data. Recent attempts aim to expand the training set by relying on computationally expensive…

Textual interaction networks (TINs) are an omnipresent data structure used to model the interplay between users and items on e-commerce websites, social networks, etc., where each interaction is associated with a text description.…

Data augmentation has been recently leveraged as an effective regularizer in various vision-language deep neural networks. However, in text-to-image synthesis (T2Isyn), current augmentation wisdom still suffers from the semantic mismatch…