Related papers: ScanFormer: Referring Expression Comprehension by …

Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications. To capture context at both global and local granularity, we propose ASpanFormer, a Transformer-based detector-free matcher…

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…

Conditional diffusion models have demonstrated impressive performance on various tasks like text-guided semantic image editing. Prior work requires image regions to be identified manually by human users or use an object detector that only…

In this paper, we address the semantic segmentation problem with a focus on the context aggregation strategy. Our motivation is that the label of a pixel is the category of the object that the pixel belongs to. We present a simple yet…

In this paper, we investigate a new framework for image classification that adaptively generates spatial representations. Our strategy is based on a sequential process that learns to explore the different regions of any image in order to…

Multi-modal Retrieval-Augmented Generation (RAG) has become a critical method for empowering LLMs by leveraging candidate visual documents. However, current methods consider the entire document as the basic retrieval unit, introducing…

Referring Image Segmentation (RIS) aims to segment target objects expressed in natural language within a scene at the pixel level. Various recent RIS models have achieved state-of-the-art performance by generating contextual tokens to model…

Referring image segmentation (RIS) aims to segment an object mentioned in natural language from an image. The main challenge is text-to-pixel fine-grained correlation. In the previous methods, the final results are obtained by convolutions…

Deep learning architectures exhibit a critical drop of performance due to catastrophic forgetting when they are required to incrementally learn new tasks. Contemporary incremental learning frameworks focus on image classification and object…

Transformers are widely used in computer vision areas and have achieved remarkable success. Most state-of-the-art approaches split images into regular grids and represent each grid region with a vision token. However, fixed token…

Object parts serve as crucial intermediate representations in various downstream tasks, but part-level representation learning still has not received as much attention as other vision tasks. Previous research has established that Vision…

Scene text recognition is a challenging task due to diverse variations of text instances in natural scene images. Conventional methods based on CNN-RNN-CTC or encoder-decoder with attention mechanism may not fully investigate stable and…

We address the problem of referring image segmentation that aims to generate a mask for the object specified by a natural language expression. Many recent works utilize Transformer to extract features for the target object by aggregating…

We present a framework for efficient perceptual inference that explicitly reasons about the segmentation of its inputs and features. Rather than being trained for any specific segmentation, our framework learns the grouping process in an…

We propose a hybrid architecture composed of a fully convolutional network (FCN) and a Dempster-Shafer layer for image semantic segmentation. In the so-called evidential FCN (E-FCN), an encoder-decoder architecture first extracts pixel-wise…

While generative modeling has become prevalent across numerous research fields, its integration into the realm of image retrieval remains largely unexplored and underjustified. In this paper, we present a novel methodology, reframing image…

In this paper, we introduce RED-NET: A Recursive Encoder-Decoder Network with Skip-Connections for edge detection in natural images. The proposed network is a novel integration of a Recursive Neural Network with an Encoder-Decoder…

Graphics rendering applications increasingly leverage neural networks in tasks such as denoising, supersampling, and frame extrapolation to improve image quality while maintaining frame rates. The temporal coherence inherent in these tasks…

Image captioning is the process of automatically generating a description of an image in natural language. Image captioning is one of the significant challenges in image understanding since it requires not only recognizing salient objects…

Referring Camouflaged Object Detection (Ref-COD) segments specified camouflaged objects in a scene by leveraging a small set of referring images. Though effective, current systems adopt a dual-branch design that requires reference images at…