Related papers: Context Does Matter: End-to-end Panoptic Narrative…

Semantic segmentation of remote sensing images plays an important role in a wide range of applications including land resource management, biosphere monitoring and urban planning. Although the accuracy of semantic segmentation in remote…

We propose Pixel-BERT to align image pixels with text by deep multi-modal transformers that jointly learn visual and language embedding in a unified end-to-end framework. We aim to build a more accurate and thorough connection between image…

Scene text image super-resolution aims to increase the resolution and readability of the text in low-resolution images. Though significant improvement has been achieved by deep convolutional neural networks (CNNs), it remains difficult to…

Image-language matching tasks have recently attracted a lot of attention in the computer vision field. These tasks include image-sentence matching, i.e., given an image query, retrieving relevant sentences and vice versa, and region-phrase…

Referring image segmentation aims at localizing all pixels of the visual objects described by a natural language sentence. Previous works learn to straightforwardly align the sentence embedding and pixel-level embedding for highlighting the…

Vision-language models have achieved remarkable success in cross-modal understanding. Yet, these models remain limited to object-level or region-level grounding, lacking the capability for pixel-precise keypoint comprehension through…

Convolutional neural networks (CNNs) are ubiquitous in computer vision, with a myriad of effective and efficient variations. Recently, Transformers -- originally introduced in natural language processing -- have been increasingly adopted in…

The global and local contexts significantly contribute to the integrity of predictions in Salient Object Detection (SOD). Unfortunately, existing methods still struggle to generate complete predictions with fine details. There are two major…

Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly…

We develop a probabilistic framework for deep learning based on the Deep Rendering Mixture Model (DRMM), a new generative probabilistic model that explicitly capture variations in data due to latent task nuisance variables. We demonstrate…

We propose a margin-based loss for tuning joint vision-language models so that their gradient-based explanations are consistent with region-level annotations provided by humans for relatively smaller grounding datasets. We refer to this…

As a common method in the field of computer vision, spatial attention mechanism has been widely used in semantic segmentation of remote sensing images due to its outstanding long-range dependency modeling capability. However, remote sensing…

Grounding language in the physical world requires AI systems to interpret references that emerge dynamically during conversation. While current vision-language models (VLMs) excel at static image tasks, they struggle to resolve ambiguous…

Multimodal Large Language Models have achieved impressive performance on a variety of vision-language tasks, yet their fine-grained visual perception and precise spatial reasoning remain limited. In this work, we introduce DiG (Differential…

Neural processes (NPs) aim to stochastically complete unseen data points based on a given context dataset. NPs essentially leverage a given dataset as a context representation to derive a suitable identifier for a novel task. To improve the…

While Transformers have had significant success in paragraph generation, they treat sentences as linear sequences of tokens and often neglect their hierarchical information. Prior work has shown that decomposing the levels of…

Recently, deep learning based facial landmark detection has achieved great success. Despite this, we notice that the semantic ambiguity greatly degrades the detection performance. Specifically, the semantic ambiguity means that some…

While image segmentation is crucial in various computer vision applications, such as autonomous driving, grasping, and robot navigation, annotating all objects at the pixel-level for training is nearly impossible. Therefore, the study of…

Human visual system is modeled in engineering field providing feature-engineered methods which detect contrasted/surprising/unusual data into images. This data is "interesting" for humans and leads to numerous applications. Deep learning…

Pansharpening aims to fuse a multispectral (MS) image with an associated panchromatic (PAN) image, producing a composite image with the spectral resolution of the former and the spatial resolution of the latter. Traditional pansharpening…