Related papers: MaskRIS: Semantic Distortion-aware Data Augmentati…
Reference Expression Segmentation (RES) aims to segment image regions specified by referring expressions and has become popular with the rise of multimodal large models (MLLMs). While MLLMs excel in semantic understanding, their…
Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textual representations often become intertwined in the deeper…
Recently, masked video modeling has been widely explored and significantly improved the model's understanding ability of visual regions at a local level. However, existing methods usually adopt random masking and follow the same…
In recent years, Deep Neural Networks (DNN) have emerged as a practical method for image recognition. The raw data, which contain sensitive information, are generally exploited within the training process. However, when the training process…
This paper proposes a novel Attention-based Multi-Reference Super-resolution network (AMRSR) that, given a low-resolution image, learns to adaptively transfer the most similar texture from multiple reference images to the super-resolution…
Self-attention is of vital importance in semantic segmentation as it enables modeling of long-range context, which translates into improved performance. We argue that it is equally important to model short-range context, especially to…
Referring Remote Sensing Image Segmentation (RRSIS) aims to segment instances in remote sensing images according to referring expressions. Unlike Referring Image Segmentation on general images, acquiring high-quality referring expressions…
Image recaptioning is widely used to generate training datasets with enhanced quality for various multimodal tasks. Existing recaptioning methods typically rely on powerful multimodal large language models (MLLMs) to enhance textual…
Current top-leading solutions for video object segmentation (VOS) typically follow a matching-based regime: for each query frame, the segmentation mask is inferred according to its correspondence to previously processed and the first…
Referring expression segmentation aims to segment an object described by a language expression from an image. Despite the recent progress on this task, existing models tackling this task may not be able to fully capture semantics and visual…
Masked reconstruction serves as a fundamental pretext task for self-supervised learning, enabling the model to enhance its feature extraction capabilities by reconstructing the masked segments from extensive unlabeled data. In human…
Although recent masked image modeling (MIM)-based HSI-LiDAR/SAR classification methods have gradually recognized the importance of the spectral information, they have not adequately addressed the redundancy among different spectra,…
We propose a visual-linguistic representation learning approach within a self-supervised learning framework by introducing a new operation, loss, and data augmentation strategy. First, we generate diverse features for the image-text…
Image restoration is the task of recovering a clean image from a degraded version. In most cases, the degradation is spatially varying, and it requires the restoration network to both localize and restore the affected regions. In this…
3D referring segmentation is an emerging and challenging vision-language task that aims to segment the object described by a natural language expression in a point cloud scene. The key challenge behind this task is vision-language feature…
We present Retrieve in Style (RIS), an unsupervised framework for facial feature transfer and retrieval on real images. Recent work shows capabilities of transferring local facial features by capitalizing on the disentanglement property of…
Self-supervised learning has become a popular approach in recent years for its ability to learn meaningful representations without the need for data annotation. This paper proposes a novel image augmentation technique, overlaying images,…
The rich textual information of large vision-language models (VLMs) combined with the powerful generative prior of pre-trained text-to-image (T2I) diffusion models has achieved impressive performance in single-image super-resolution (SISR).…
Referring 3D Segmentation is a visual-language task that segments all points of the specified object from a 3D point cloud described by a sentence of query. Previous works perform a two-stage paradigm, first conducting language-agnostic…
Referring detection refers to locate the target referred by natural languages, which has recently attracted growing research interests. However, existing datasets are limited to ground images with large object centered in relative small…