Related papers: S$^3$POT: Contrast-Driven Face Occlusion Segmentat…

Despite the recent success of convolutional neural networks for computer vision applications, unconstrained face recognition remains a challenge. In this work, we make two contributions to the field. Firstly, we consider the problem of face…

With the rise of pre-trained models in the 3D point cloud domain for a wide range of real-world applications, adapting them to downstream tasks has become increasingly important. However, conventional full fine-tuning methods are…

Generating accurate and coherent image captions in a continual learning setting remains a major challenge due to catastrophic forgetting and the difficulty of aligning evolving visual concepts with language over time. In this work, we…

The Segment Anything Model (SAM) excels at general image segmentation but has limited ability to understand natural language, which restricts its direct application in Referring Expression Segmentation (RES). Toward this end, we propose…

The extraction of a clean background image by removing foreground occlusion holds immense practical significance, but it also presents several challenges. Presently, the majority of de-occlusion research focuses on addressing this issue…

This paper presents a real-time face detector, named Single Shot Scale-invariant Face Detector (S$^3$FD), which performs superiorly on various scales of faces with a single deep neural network, especially for small faces. Specifically, we…

Few-shot semantic segmentation aims to segment novel-class objects in a query image with only a few annotated examples in support images. Most of advanced solutions exploit a metric learning framework that performs segmentation through…

Modern supervised semantic segmentation methods are usually finetuned based on the supervised or self-supervised models pre-trained on ImageNet. Recent work shows that transferring the knowledge from CLIP to semantic segmentation via prompt…

Vision transformers (ViTs) have recently been widely applied to 3D point cloud understanding, with masked autoencoding as the predominant pre-training paradigm. However, the challenge of learning dense and informative semantic features from…

Natural scene understanding is a challenging task, particularly when encountering images of multiple objects that are partially occluded. This obstacle is given rise by varying object ordering and positioning. Existing scene understanding…

The impressive performance of GPT-3 using natural language prompts and in-context learning has inspired work on better fine-tuning of moderately-sized models under this paradigm. Following this line of work, we present a contrastive…

Although many approaches for multi-human pose estimation in videos have shown profound results, they require densely annotated data which entails excessive man labor. Furthermore, there exists occlusion and motion blur that inevitably lead…

Accurate medical image segmentation is of utmost importance for enabling automated clinical decision procedures. However, prevailing supervised deep learning approaches for medical image segmentation encounter significant challenges due to…

Open-vocabulary image segmentation has been advanced through the synergy between mask generators and vision-language models like Contrastive Language-Image Pre-training (CLIP). Previous approaches focus on generating masks while aligning…

Face occlusions, covering either the majority or discriminative parts of the face, can break facial perception and produce a drastic loss of information. Biometric systems such as recent deep face recognition models are not immune to…

One major challenge in 3D reconstruction is to infer the complete shape geometry from partial foreground occlusions. In this paper, we propose a method to reconstruct the complete 3D shape of an object from a single RGB image, with…

Prompt-guided generative AI models have rapidly expanded across vision and language domains, producing realistic and diverse outputs from textual inputs. The growing variety of such models, trained with different data and architectures,…

Segment Anything (SAM) provides an unprecedented foundation for human segmentation, but may struggle under occlusion, where keypoints may be partially or fully invisible. We adapt SAM 2.1 for pose-guided segmentation with minimal encoder…

Most existing self-supervised learning (SSL) approaches for 3D point clouds are dominated by generative methods based on Masked Autoencoders (MAE). However, these generative methods have been proven to struggle to capture high-level…

An instance with a bad mask might make a composite image that uses it look fake. This encourages us to learn segmentation by generating realistic composite images. To achieve this, we propose a novel framework that exploits a new proposed…