Related papers: Rethinking VLMs for Image Forgery Detection and Lo…

Large Language Model-based Vision-Language Models (LLM-based VLMs) have demonstrated impressive results in various vision-language understanding tasks. However, how well these VLMs can see image detail beyond the semantic level remains…

Autonomous driving perception systems are particularly vulnerable in foggy conditions, where light scattering reduces contrast and obscures fine details critical for safe operation. While numerous defogging methods exist, from handcrafted…

As large language models (LLMs) become ubiquitous in our daily tasks and digital interactions, associated privacy risks are increasingly in focus. While LLM privacy research has primarily focused on the leakage of model training data, it…

With imaging devices delivering ever-higher resolutions and the emerging diffusion-based forgery methods, current detectors trained only on traditional datasets (with splicing, copy-moving and object removal forgeries) lack exposure to this…

Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake detection technique is developed to distinguish between real…

Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. In the cross-modal setting, tokens in the sentence are masked at random, and the model predicts the masked tokens given the image and the text. In…

Leveraging large-scale Text-to-Image (TTI) models have become a common technique for generating exemplar or training dataset in the fields of image synthesis, video editing, 3D reconstruction. However, semantic structural visual…

A comprehensive benchmark is yet to be established in the Image Manipulation Detection & Localization (IMDL) field. The absence of such a benchmark leads to insufficient and misleading model evaluations, severely undermining the development…

Vision-Language Models (VLMs) exhibit systematic bias toward visual illusions, recalling memorized facts rather than perceiving actual visual differences. This paper presents a training-free framework for the 5th DataCV Challenge Task 1 at…

Large visual-language models (LVLMs) exhibit exceptional performance in visual-language reasoning across diverse cross-modal benchmarks. Despite these advances, recent research indicates that Large Language Models (LLMs), like…

Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges on having a good connector that maps visual features generated by a vision encoder to a shared…

Social media's global reach amplifies the spread of information, highlighting the need for robust Natural Language Processing tasks like stance detection across languages and modalities. Prior research predominantly focuses on text-only…

In recent years, particularly since the early 2020s, Large Language Models (LLMs) have emerged as the most powerful AI tools in addressing a diverse range of challenges, from natural language processing to complex problem-solving in various…

Vision-language models (VLMs) extend the conventional large language models by integrating visual data, enabling richer multimodal reasoning and significantly broadens the practical applications of AI. However, including visual inputs also…

Large vision-language models (LVLMs) are markedly proficient in deriving visual representations guided by natural language. Recent explorations have utilized LVLMs to tackle zero-shot visual anomaly detection (VAD) challenges by pairing…

Reliable prediction by classifiers is crucial for their deployment in high security and dynamically changing situations. However, modern neural networks often exhibit overconfidence for misclassified predictions, highlighting the need for…

Following the recent popularity of Large Language Models (LLMs), several attempts have been made to extend them to the visual domain. From having a visual assistant that could guide us through unfamiliar environments to generative models…

Through a controlled study, we identify a systematic deficiency in the multimodal grounding of Vision Language Models (VLMs). While VLMs can recall factual associations when provided a textual reference to an entity; their ability to do so…

Recent advances in image manipulation have enabled highly photorealistic content generation, but also lowered the barrier to arbitrary editing, raising concerns about multimedia authenticity and security. Existing Image Manipulation…

Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection…