Related papers: Context-Aware Image Inpainting with Learned Semant…

Semantic image editing utilizes local semantic label maps to generate the desired content in the edited region. A recent work borrows SPADE block to achieve semantic image editing. However, it cannot produce pleasing results due to style…

In-context learning enables language models (LM) to adapt to downstream data or tasks by incorporating few samples as demonstrations within the prompts. It offers strong performance without the expense of fine-tuning. However, the…

Going beyond mere fine-tuning of vision-language models (VLMs), learnable prompt tuning has emerged as a promising, resource-efficient alternative. Despite their potential, effectively learning prompts faces the following challenges: (i)…

Recovering clear structures from severely blurry inputs is a challenging problem due to the large movements between the camera and the scene. Although some works apply segmentation maps on human face images for deblurring, they cannot…

Recently semantic parsing in context has received considerable attention, which is challenging since there are complex contextual phenomena. Previous works verified their proposed methods in limited scenarios, which motivates us to conduct…

Recent advances in large pre-trained vision-language models have demonstrated remarkable performance on zero-shot downstream tasks. Building upon this, recent studies, such as CoOp and CoCoOp, have proposed the use of prompt learning, where…

Image semantic segmentation is parsing image into several partitions in such a way that each region of which involves a semantic concept. In a weakly supervised manner, since only image-level labels are available, discriminating objects…

Linguistic style is an essential part of written communication, with the power to affect both clarity and attractiveness. With recent advances in vision and language, we can start to tackle the problem of generating image captions that are…

We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first…

Co-occurrent visual pattern makes aggregating contextual information a common paradigm to enhance the pixel representation for semantic image segmentation. The existing approaches focus on modeling the context from the perspective of the…

Place recognition gives a SLAM system the ability to correct cumulative errors. Unlike images that contain rich texture features, point clouds are almost pure geometric information which makes place recognition based on point clouds…

We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. We derive a new risk bound for this setting that decomposes into a bias…

Cross-modal retrieval methods have been significantly improved in last years with the use of deep neural networks and large-scale annotated datasets such as ImageNet and Places. However, collecting and annotating such datasets requires a…

Image search and retrieval engines rely heavily on textual annotation in order to match word queries to a set of candidate images. A system that can automatically annotate images with meaningful text can be highly beneficial for such…

Scene parsing is a technique that consist on giving a label to all pixels in an image according to the class they belong to. To ensure a good visual coherence and a high class accuracy, it is essential for a scene parser to capture image…

Despite their effectiveness in a wide range of tasks, deep architectures suffer from some important limitations. In particular, they are vulnerable to catastrophic forgetting, i.e. they perform poorly when they are required to update their…

In-context learning is a surprising and important phenomenon that emerged when modern language models were scaled to billions of learned parameters. Without modifying a large language model's weights, it can be tuned to perform various…

Existing image inpainting methods have achieved remarkable accomplishments in generating visually appealing results, often accompanied by a trend toward creating more intricate structural textures. However, while these models excel at…

Although supervised learning has enabled high performance for image segmentation, it requires a large amount of labeled training data, which can be difficult to obtain in the medical imaging field. Self-supervised learning (SSL) methods…

Images can be viewed as layered compositions, foreground objects over background, with potential occlusions. This layered representation enables independent editing of elements, offering greater flexibility for content creation. Despite the…