相关论文: SeamCam: Quantifying Seamless Camouflage via Multi…

We consider the problem of referring camouflaged object detection (Ref-COD), a new task that aims to segment specified camouflaged objects based on a small set of referring images with salient target objects. We first assemble a large-scale…

Learning disentangled representations in sequential data is a key goal in deep learning, with broad applications in vision, audio, and time series. While real-world data involves multiple interacting semantic factors over time, prior work…

Identifying individual animals in long-duration videos is essential for behavioral ecology, wildlife monitoring, and livestock management. Traditional methods require extensive manual annotation, while existing self-supervised approaches…

This paper addresses the task of zero-shot image classification. The key contribution of the proposed approach is to control the semantic embedding of images -- one of the main ingredients of zero-shot learning -- by formulating it as a…

Automatic human matting is highly desired for many real applications. We investigate recent human matting methods and show that common bad cases happen when semantic human segmentation fails. This indicates that semantic understanding is…

Deep learning opacity often impedes deployment in high-stakes domains. We propose a training framework that aligns model focus with class-representative features without requiring pixel-level annotations. To this end, we introduce…

In animal facilities, continuous surveillance of penguins is essential yet technically challenging due to their homogeneous visual characteristics, rapid and frequent posture changes, and substantial environmental noise such as water…

Text-to-image diffusion techniques have shown exceptional capabilities in producing high-quality, dense visual predictions from open-vocabulary text. This indicates a strong correlation between visual and textual domains in open concepts…

Classification networks can be used to localize and segment objects in images by means of class activation maps (CAMs). However, without pixel-level annotations, classification networks are known to (1) mainly focus on discriminative…

In computer vision, a prevailing method for quantifying dataset bias is to train a model to distinguish between datasets. High classification accuracy is then interpreted as evidence of meaningful semantic differences. This approach assumes…

The Segment Anything Model (SAM) excels at generating precise object masks from input prompts but lacks semantic awareness, failing to associate its generated masks with specific object categories. To address this limitation, we propose…

This study demonstrates a novel approach to facial camouflage that combines targeted cosmetic perturbations and alpha transparency layer manipulation to evade modern facial recognition systems. Unlike previous methods -- such as CV dazzle,…

We propose SERUM: an intriguingly simple yet highly effective method for marking images generated by diffusion models (DMs). We only add a unique watermark noise to the initial diffusion generation noise and train a lightweight detector to…

Detecting if and when objects change is difficult in passive sub-diffraction imaging of dynamic scenes. We consider the best possible tradeoff between responsivity and accuracy for detecting a change from one arbitrary object model to…

Geometric navigation is nowadays a well-established field of robotics and the research focus is shifting towards higher-level scene understanding, such as Semantic Mapping. When a robot needs to interact with its environment, it must be…

Camera scene detection is among the most popular computer vision problem on smartphones. While many custom solutions were developed for this task by phone vendors, none of the designed models were available publicly up until now. To address…

Extreme Learning Machine is a powerful classification method very competitive existing classification methods. It is extremely fast at training. Nevertheless, it cannot perform face verification tasks properly because face verification…

Infrared-visible (IR-VIS) feature matching plays an essential role in cross-modality visual localization, navigation and perception. Along with the rapid development of deep learning techniques, a number of representative image matching…

Transparent objects are a very challenging problem in computer vision. They are hard to segment or classify due to their lack of precise boundaries, and there is limited data available for training deep neural networks. As such, current…

We propose a method that learns to camouflage 3D objects within scenes. Given an object's shape and a distribution of viewpoints from which it will be seen, we estimate a texture that will make it difficult to detect. Successfully solving…