31 accepted papers
With the widespread application of Video Diffusion Models (VDMs), video synthesis has achieved remarkable temporal dynamics. Image-to-Video (I2V) generation allows users to provide reference images, which enables attackers to inject adversarial noise into these conditions. Due to the robust spatio-t…
Creating realistic and simulation-ready 3D assets is crucial for autonomous driving research and virtual environment construction. However, existing 3D vehicle generation methods are often trained on synthetic data with significant domain gaps from real-world distributions. The generated models ofte
As large language models (LLMs) continue to advance, there is increasing interest in their ability to infer human mental states and demonstrate a human-like Theory of Mind (ToM). Most existing ToM evaluations, however, are centered on text-based inputs, while scenarios relying solely on visual infor
By sharing information across multiple agents, collaborative perception helps autonomous vehicles mitigate occlusions and improve overall perception accuracy. While most previous work focus on vehicle-to-vehicle and vehicle-to-infrastructure collaboration, with limited attention to aerial perspectiv…
Infrared and visible image fusion (IVIF) is a crucial technique for enhancing visual performance by integrating unique information from different modalities into one fused image. Exiting methods pay more attention to conducting fusion with undisturbed data, while overlooking the impact of deliberate…
While image conditional diffusion models demonstrate impressive generation capabilities, they exhibit high vulnerability when facing backdoor and adversarial attacks. In this paper, we define a scenario named diffusion anomaly where the generated results of a reverse process under attack deviate sig…
Contrastive learning is a prevalent technique in self-supervised vision representation learning, typically generating positive pairs by applying two data augmentations to the same image. Designing effective data augmentation strategies is crucial for the success of contrastive learning. Inspired by…
In the fields of machine learning and deep learning, ensuring model robustness and reliability is critical. One major challenge is the handling of Out-of-Distribution (OOD) samples, the presence of In-Distribution (ID) noise in existing OOD datasets. It can increase the risk of misclassification and…
As large language models evolve, there is growing anticipation that they will emulate human-like Theory of Mind (ToM) to assist with routine tasks. However, existing methods for evaluating machine ToM focus primarily on unimodal models and largely treat these models as black boxes, lacking an interp…
Camera pose estimation is a fundamental computer vision task that is essential for applications like visual localization and multi-view stereo reconstruction. In the object-centric scenarios with sparse inputs, the accuracy of pose estimation can be significantly influenced by background textures th…
Robust feature representations are essential for learning-based Multi-View Stereo (MVS), which relies on accurate feature matching. Recent MVS methods leverage Transformers to capture long-range dependencies based on local features extracted by conventional feature pyramid networks. However, the qua…
Learning-based Multi-View Stereo (MVS) methods aim to predict depth maps for a sequence of calibrated images to recover dense point clouds. However, existing MVS methods often struggle with challenging regions, such as textureless regions and reflective surfaces, where feature matching fails. In con…
Reconstructing 3D models from sensor data is a valuable and promising direction for developing testing and validation environments in applications like autonomous driving. However, existing methods for 3D modeling often rely on extensive multi-view data or controlled conditions, making them difficul…
In typical multimodal tasks, such as Visual Question Answering (VQA), adversarial attacks targeting a specific image and question can lead large vision-language models (LVLMs) to provide incorrect answers. However, it is common for a single image to be associated with multiple questions, and LVLMs m…
Learning-based multi-view stereo methods aim to predict depth maps for reconstructing dense point clouds. These methods rely on regularization to reduce redundancy in the cost volume. However, existing methods have limitations: CNN-based regularization is restricted to local receptive fields, while…
In the field of zero-shot 3D instance segmentation, existing 2D-to-3D lifting methods typically obtain 2D segmentation across multiple RGB frames using vision foundation models, which are then projected and merged into 3D space. However, since the inference of vision foundation models on a single fr…
The choice of a suitable visual language projector (VLP) is critical to the successful training of large visual language models (LVLMs). Mainstream VLPs can be broadly categorized into compressed and uncompressed projectors, and each offers distinct advantages in performance and computational effici
Center of pressure (COP) serves as a widely utilized indicator for evaluating balance-related issues, e.g., gait quality of neurological disorders, fall risk of the elderly, and recovery of the injured. Existing methods for acquiring COP mostly rely on expensive force platforms or wearable force-sen…
Previous works have shown that perturbing internal-layer features can significantly enhance the transferability of black-box attacks in classifiers. However, these methods have not achieved satisfactory performance when applied to detectors due to the inherent differences in features between detecto…
3D object detection has gained increasing attention in modern autonomous driving systems. However, the performance of the detector significantly degrades during cross-domain deployment due to domain shift. The detector is inevitably biased towards its training dataset when employed on a target datas…
3D human mesh reconstruction from a single RGB image is a challenging task. Existing methods either utilize parametric mesh models to restrain the 3D human structures or directly regress the 3D coordinates of the mesh vertices. The former ones, called model-based methods, usually fail to recover the…
The high-quality generation results of conditional diffusion models have brought about concerns regarding privacy and copyright issues. As a possible technique for preventing the abuse of diffusion models, the adversarial attack against diffusion models has attracted academic attention recently. In…
Transferable black-box adversarial attacks against classifiers by disturbing the intermediate-layer features have been extensively studied in recent years. However, these methods have not yet achieved satisfactory performances when directly applied to object detectors. This is largely because the fe…
Previous works reveal that similar to CNNs, vision transformers (ViT) are also vulnerable to universal adversarial patch attacks. In this paper, we empirically reveal and mathematically explain that the shallow tokens in the transformer and the attention of the network can largely influence the clas…
Physical-world adversarial attacks based on universal adversarial patches have been proved to be able to mislead deep convolutional neural networks (CNNs), exposing the vulnerability of real-world visual classification systems based on CNNs. In this paper, we empirically reveal and mathematically ex…
Neural networks are vulnerable to adversarial attacks. Practically, adversarial training is by far the most effective approach for enhancing the robustness of neural networks against adversarial examples. The current adversarial training approach aims to maximize the posterior probability for advers…
In convolutional neural networks (CNNs), we propose to estimate the importance of a feature vector at a spatial location in the feature maps by the network's uncertainty on its class prediction, which can be quantified using the information entropy. Based on this idea, we propose the entropy-based f…
We present a deep-learning architecture for multi-view stereo with conditional random fields (MVSCRF). Given an arbitrary number of input images, we first use a U-shape neural network to extract deep features incorporating both global and local information, and then build a 3D cost volume for the re…
We propose a large-margin Gaussian Mixture (L-GM) loss for deep neural networks in classification tasks. Different from the softmax cross-entropy loss, our proposal is established on the assumption that the deep features of the training set follow a Gaussian Mixture distribution. By involving a clas…
Attention based automatic image cropping aims at preserving the most visually important region in an image. A common task in this kind of method is to search for the smallest rectangle inside which the summed attention is maximized. We demonstrate that under appropriate formulations, this task can b…
We present in this paper a superpixel segmentation algorithm called Linear Spectral Clustering (LSC), which produces compact and uniform superpixels with low computational costs. Basically, a normalized cuts formulation of the superpixel segmentation is adopted based on a similarity metric that meas…