Camouflaged object detection (COD) aims to segment camouflaged objects which exhibit very similar patterns with the surrounding environment. Recent research works have shown that enhancing the feature representation via the frequency information can ...

Self-training has been shown to achieve remarkable gains in semi-supervised semantic segmentation by creating pseudo-labels using unlabeled data. This approach, however, suffers from the quality of the generated pseudo-labels, and generating higher ...

Crowd counting has drawn increasing attention across various fields. However, existing crowd counting tasks primarily focus on estimating the overall population, ignoring the behavioral and semantic information of different social groups within the crowd. ...

Camouflaged object detection (COD) aims to segment targeted objects that have similar colors, textures, or shapes to their background environment. Due to the limited ability in distinguishing highly similar patterns, existing COD methods usually produce ...

Local feature detectors and descriptors serve various computer vision tasks, such as image matching, visual localization, and 3D reconstruction. To address the extreme variations of rotation and light in the real world, most detectors and descriptors ...

Dental plaque segmentation is crucial for maintaining oral health. However, accurately segmenting dental plaque in unconstrained environments can be challenging due to its low contrast and high variability in appearance. While existing transformer-based ...

Low-light images often suffer from severe detail lost in darker areas and non-uniform illumination distribution across distinct regions. Thus, structure modeling and region-specific illumination manipulation are crucial for high-quality enhanced image ...

RGB and Thermal (RGBT) Salient Object Detection (SOD) aims to achieve high-quality saliency prediction by exploiting the complementary information of visible and thermal image pairs, which are initially captured in an unaligned manner. However, existing ...

The fusion of infrared (IR) and visible (VIS) images aims to capture complementary information from diverse sensors, resulting in a fused image that enhances the overall human perception of the scene. However, existing fusion methods face challenges ...

Infrared target recognition and anti-interference in complex battlefields is one of the key technologies enabling the precise strike capability of aircraft. Currently, infrared-guided aircraft face complex interference such as natural backgrounds and ...

The successful application of semantic segmentation technology in the real world has been among the most exciting achievements in the computer vision community over the past decade. Although the long-tailed phenomenon has been investigated in many fields, ...

In recent years, various distillation methods for semantic segmentation have been proposed. However, these methods typically train the student model to imitate the intermediate features or logits of the teacher model directly, thereby overlooking the high-...

The recently proposed MaskFormer [Cheng et al. (2021)] gives a refreshed perspective on the task of semantic segmentation: it shifts from the popular pixel-level classification paradigm to a mask-level classification method. In essence, it generates ...

Few-shot semantic segmentation is a challenging task that aims to segment novel classes in the query images given only a few annotated support samples. Most existing prototype-based approaches extract global or local prototypes by global average pooling (...

RGB-Thermal pedestrian detection has shown many notable advantages in various lighting and weather conditions by combining the information from RGB-T images. Due to distinct imaging principles, RGB-T modalities consist of modality-specific and modality-...

Transformer-based semantic segmentation has been developed rapidly. Vision transformer (ViT) rely on self-attention mechanism which employs all image patches to compute long-range dependencies. ViT considers all tokens equally important for self-attention ...

Visible-infrared person re-identification (VI-ReID) is a challenging task because the different imaging principles of visible and infrared images bring about huge modality discrepancy. Existing methods primarily address this issue by generating ...

Recently, three-dimensional (3D) point-cloud analysis has been extensively utilized in the domain of machine vision, encompassing tasks include shape classification and segmentation. However the inherent disorder in point clouds poses a challenge in ...

In the tracking literature, foreground and background information have been extensively investigated to discriminate a target from its surrounding background. However, both foreground and background possess their own spatial-temporal correlation ...

Fully supervised salient object detection (SOD) has made considerable progress based on expensive and time-consuming data with pixel-wise annotations. Recently, to relieve the labeling burden while maintaining performance, some scribble-based SOD methods ...