Related papers: SpotDiff: Spotting and Disentangling Interference …
Optimizing a deep neural network is a fundamental task in computer vision, yet direct training methods often suffer from over-fitting. Teacher-student optimization aims at providing complementary cues from a model trained previously, but…
Consistent human-centric image and video synthesis aims to generate images or videos with new poses while preserving appearance consistency with a given reference image, which is crucial for low-cost visual content creation. Recent advances…
Clothes-changing person re-identification (CC-ReID) aims to recognize individuals under different clothing scenarios. Current CC-ReID approaches either concentrate on modeling body shape using additional modalities including silhouette,…
Recent research in subject-driven generation increasingly emphasizes the importance of selective subject features. Nevertheless, accurately selecting the content in a given reference image still poses challenges, especially when selecting…
Prior studies show that the key to face anti-spoofing lies in the subtle image pattern, termed "spoof trace", e.g., color distortion, 3D mask edge, Moire pattern, and many others. Designing a generic face anti-spoofing model to estimate…
In order to encode the class correlation and class specific information in image representation, we propose a new local feature learning approach named Deep Discriminative and Shareable Feature Learning (DDSFL). DDSFL aims to hierarchically…
We propose DiscoFaceGAN, an approach for face image generation of virtual people with disentangled, precisely-controllable latent representations for identity of non-existing people, expression, pose, and illumination. We embed 3D priors…
Person image synthesis with controllable body poses and appearances is an essential task owing to the practical needs in the context of virtual try-on, image editing and video production. However, existing methods face significant…
Customized video generation aims to generate high-quality videos guided by text prompts and subject's reference images. However, since it is only trained on static images, the fine-tuning process of subject learning disrupts abilities of…
Person re identification is a challenging retrieval task that requires matching a person's acquired image across non overlapping camera views. In this paper we propose an effective approach that incorporates both the fine and coarse pose…
Robust local feature representations are essential for spatial intelligence tasks such as robot navigation and augmented reality. Establishing reliable correspondences requires descriptors that provide both high discriminative power and…
With diverse presentation forgery methods emerging continually, detecting the authenticity of images has drawn growing attention. Although existing methods have achieved impressive accuracy in training dataset detection, they still perform…
Traditional data masking techniques such as anonymization cannot achieve the expected privacy protection while ensuring data utility for privacy-preserving machine learning. Synthetic data plays an increasingly important role as it…
Visual speech recognition is a technique to identify spoken content in silent speech videos, which has raised significant attention in recent years. Advancements in data-driven deep learning methods have significantly improved both the…
Graph representation of objects and their relations in a scene, known as a scene graph, provides a precise and discernible interface to manipulate a scene by modifying the nodes or the edges in the graph. Although existing works have shown…
Detecting objects seamlessly blended into their surroundings represents a complex task for both human cognitive capabilities and advanced artificial intelligence algorithms. Currently, the majority of methodologies for detecting camouflaged…
A crucial problem in learning disentangled image representations is controlling the degree of disentanglement during image editing, while preserving the identity of objects. In this work, we propose a simple yet effective model with the…
Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data. However, with downstream tasks generally unknown at training time, it is difficult to deduce a priori which…
We address the problem of person re-identification (reID), that is, retrieving person images from a large dataset, given a query image of the person of interest. A key challenge is to learn person representations robust to intra-class…
Recent works in self-supervised learning have shown impressive results on single-object images, but they struggle to perform well on complex multi-object images as evidenced by their poor visual grounding. To demonstrate this concretely, we…