Related papers: MemeSequencer: Sparse Matching for Embedding Image…
The rapid development of generative AI has transformed content creation, communication, and human development. However, this technology raises profound concerns in high-stakes domains, demanding rigorous methods to analyze and evaluate…
Prior art has shown it is possible to estimate, through image processing and computer vision techniques, the types and parameters of transformations that have been applied to the content of individual images to obtain new images. Given a…
The emergence of generative AI and controllable diffusion has made image-to-image synthesis increasingly practical and efficient. However, when input images exhibit low entropy and sparse, the inherent characteristics of diffusion models…
Despite enormous progress in object detection and classification, the problem of incorporating expected contextual relationships among object instances into modern recognition systems remains a key challenge. In this work we propose…
We introduce a deep neural network for automated sarcasm detection. Recent work has emphasized the need for models to capitalize on contextual features, beyond lexical and syntactic cues present in utterances. For example, different…
Transformations produced by image and video generation models often evolve in a highly non-linear manner: long stretches where the content barely changes are followed by sudden, abrupt semantic jumps. To analyze and correct this behavior,…
Interpretable-by-design models are gaining traction in computer vision because they provide faithful explanations for their predictions. In image classification, these models typically recover human-interpretable concepts from an image and…
We propose a method for generating spurious features by leveraging large-scale text-to-image diffusion models. Although the previous work detects spurious features in a large-scale dataset like ImageNet and introduces Spurious ImageNet, we…
As deep learning models are increasingly used in safety-critical applications, explainability and trustworthiness become major concerns. For simple images, such as low-resolution face portraits, synthesizing visual counterfactual…
The rapid development of deep learning has made a great progress in image segmentation, one of the fundamental tasks of computer vision. However, the current segmentation algorithms mostly rely on the availability of pixel-level…
We consider the task of linking social media accounts that belong to the same author in an automated fashion on the basis of the content and metadata of their corresponding document streams. We focus on learning an embedding that maps…
Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be…
We study the problem of grounding distributional representations of texts on the visual domain, namely visual-semantic embeddings (VSE for short). Begin with an insightful adversarial attack on VSE embeddings, we show the limitation of…
The phenomenal growth on the internet has helped in empowering individual's expressions, but the misuse of freedom of expression has also led to the increase of various cyber crimes and anti-social activities. Hate speech is one such issue…
Online media data, in the forms of images and videos, are becoming mainstream communication channels. However, recent advances in deep learning, particularly deep generative models, open the doors for producing perceptually convincing…
Image representations are often evaluated through disjointed, task-specific protocols, leading to a fragmented understanding of model capabilities. For instance, it is unclear whether an image embedding model adept at clustering images is…
Image similarity has been extensively studied in computer vision. In recent years, machine-learned models have shown their ability to encode more semantics than traditional multivariate metrics. However, in labelling semantic similarity,…
The accelerated advancement of generative AI significantly enhance the viability and effectiveness of generative regional editing methods. This evolution render the image manipulation more accessible, thereby intensifying the risk of…
In this paper, we propose a deep convolutional neural network for learning the embeddings of images in order to capture the notion of visual similarity. We present a deep siamese architecture that when trained on positive and negative pairs…
Understanding the diffusion in social network is an important task. However, this task is challenging since (1) the network structure is usually hidden with only observations of events like "post" or "repost" associated with each node, and…