中文
相关论文

相关论文: OmniVL-Guard: Towards Unified Vision-Language Forg…

200 篇论文

Existing vision-language forgery detection and grounding methods operate under a closed-world paradigm, assuming verification can be completed by the model alone. However, self-contained MLLMs are constrained by finite parametric knowledge,…

计算机视觉与模式识别 · 计算机科学 2026-05-21 Jinjie Shen , Zheng Huang , Yuchen Zhang , Yujiao Wu , Yaxiong Wang , Lechao Cheng , Shengeng Tang , Tianrui Hui , Nan Pu , Zhun Zhong

Traditional visual grounding methods primarily focus on single-image scenarios with simple textual references. However, extending these methods to real-world scenarios that involve implicit and complex instructions, particularly in…

计算机视觉与模式识别 · 计算机科学 2025-05-21 Sule Bai , Mingxing Li , Yong Liu , Jing Tang , Haoji Zhang , Lei Sun , Xiangxiang Chu , Yansong Tang

The deployment of Vision-Language Models (VLMs) in safety-critical domains like autonomous driving (AD) is critically hindered by reliability failures, most notably object hallucination. This failure stems from their reliance on ungrounded,…

计算机视觉与模式识别 · 计算机科学 2026-05-01 Zhenguo Zhang , Haohan Zheng , Yishen Wang , Le Xu , Tianchen Deng , Xuefeng Chen , Qu Chen , Bo Zhang , Wuxiong Huang

This paper presents OmniVL, a new foundation model to support both image-language and video-language tasks using one universal architecture. It adopts a unified transformer-based visual encoder for both image and video inputs, and thus can…

计算机视觉与模式识别 · 计算机科学 2022-10-21 Junke Wang , Dongdong Chen , Zuxuan Wu , Chong Luo , Luowei Zhou , Yucheng Zhao , Yujia Xie , Ce Liu , Yu-Gang Jiang , Lu Yuan

The rapid advancement of generative models has intensified the challenge of detecting and interpreting visual forgeries, necessitating robust frameworks for image forgery detection while providing reasoning as well as localization. While…

计算机视觉与模式识别 · 计算机科学 2025-09-09 Ipsita Praharaj , Yukta Butala , Badrikanath Praharaj , Yash Butala

Large Vision Language Models (LVLMs) achieve strong multimodal reasoning but frequently exhibit hallucinations and incorrect responses with high certainty, which hinders their usage in high-stakes domains. Existing verbalized confidence…

计算机视觉与模式识别 · 计算机科学 2026-04-13 Wenyi Xiao , Xinchi Xu , Leilei Gan

Omni-modal Large Language Models (OLLMs) that process text, images, videos, and audio introduce new challenges for safety and value guardrails in human-AI interaction. Prior guardrail research largely targets unimodal settings and typically…

人工智能 · 计算机科学 2025-12-03 Boyu Zhu , Xiaofei Wen , Wenjie Jacky Mo , Tinghui Zhu , Yanan Xie , Peng Qi , Muhao Chen

Visual Grounding (VG) aims at localizing target objects from an image based on given expressions and has made significant progress with the development of detection and vision transformer. However, existing VG methods tend to generate…

计算机视觉与模式识别 · 计算机科学 2023-07-25 Menghao Li , Chunlei Wang , Wenquan Feng , Shuchang Lyu , Guangliang Cheng , Xiangtai Li , Binghao Liu , Qi Zhao

Face forgery detection encompasses multiple critical tasks, including identifying forged images and videos and localizing manipulated regions and temporal segments. Current approaches typically employ task-specific models with independent…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Haotian Liu , Haoyu Chen , Chenhui Pan , You Hu , Guoying Zhao , Xiaobai Li

Video Temporal Grounding (VTG), the task of localizing video segments from text queries, struggles in open-world settings due to limited dataset scale and semantic diversity, causing performance gaps between common and rare concepts. To…

计算机视觉与模式识别 · 计算机科学 2026-04-29 Minghang Zheng , Zihao Yin , Yi Yang , Yuxin Peng , Yang Liu

Existing deepfake detection techniques struggle to keep-up with the ever-evolving novel, unseen forgeries methods. This limitation stems from their reliance on statistical artifacts learned during training, which are often tied to specific…

计算机视觉与模式识别 · 计算机科学 2025-06-06 Guangyu Shen , Zhihua Li , Xiang Xu , Tianchen Zhao , Zheng Zhang , Dongsheng An , Zhuowen Tu , Yifan Xing , Qin Zhang

Recent advances in generative artificial intelligence have enabled the creation of highly realistic image forgeries, raising significant concerns about digital media authenticity. While existing detection methods demonstrate promising…

多媒体 · 计算机科学 2025-04-15 Junhao Xu , Jingjing Chen , Yang Jiao , Jiacheng Zhang , Zhiyu Tan , Hao Li , Yu-Gang Jiang

Visual-language grounding aims to establish semantic correspondences between natural language and visual entities, enabling models to accurately identify and localize target objects based on textual instructions. Existing VLG approaches…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Linfei Li , Lin Zhang , Ying Shen

Multimodal Large Language Models (MLLMs) are making significant progress in multimodal reasoning. Early approaches focus on pure text-based reasoning. More recent studies have incorporated multimodal information into the reasoning steps;…

人工智能 · 计算机科学 2026-04-21 Dongjie Cheng , Yongqi Li , Zhixin Ma , Hongru Cai , Yupeng Hu , Wenjie Wang , Liqiang Nie , Wenjie Li

Visual grounding is a common vision task that involves grounding descriptive sentences to the corresponding regions of an image. Most existing methods use independent image-text encoding and apply complex hand-crafted modules or…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Ming Dai , Lingfeng Yang , Yihao Xu , Zhenhua Feng , Wankou Yang

Open-Vocabulary Aerial Detection (OVAD) and Remote Sensing Visual Grounding (RSVG) have emerged as two key paradigms for aerial scene understanding. However, each paradigm suffers from inherent limitations when operating in isolation: OVAD…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Guoting Wei , Xia Yuan , Yang Zhou , Haizhao Jing , Yu Liu , Xianbiao Qi , Chunxia Zhao , Haokui Zhang , Rong Xiao

Long-horizon video-audio reasoning and fine-grained pixel understanding impose conflicting requirements on omnimodal models: dense temporal coverage demands many low-resolution frames, whereas precise grounding calls for high-resolution…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Hao Zhong , Muzhi Zhu , Zongze Du , Zheng Huang , Canyu Zhao , Mingyu Liu , Wen Wang , Hao Chen , Chunhua Shen

Vision-language-action (VLA) models have shown strong generalization for robotic action prediction through large-scale vision-language pretraining. However, most existing models rely solely on RGB cameras, limiting their perception and,…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Heyu Guo , Shanmu Wang , Ruichun Ma , Shiqi Jiang , Yasaman Ghasempour , Omid Abari , Baining Guo , Lili Qiu

Most existing vision-language pre-training methods focus on understanding tasks and use BERT-like objectives (masked language modeling and image-text matching) during pretraining. Although they perform well in many understanding downstream…

计算机视觉与模式识别 · 计算机科学 2021-12-16 Tianyi Liu , Zuxuan Wu , Wenhan Xiong , Jingjing Chen , Yu-Gang Jiang

Video Temporal Grounding (VTG), which aims to ground target clips from videos (such as consecutive intervals or disjoint shots) according to custom language queries (e.g., sentences or words), is key for video browsing on social media. Most…

计算机视觉与模式识别 · 计算机科学 2023-08-21 Kevin Qinghong Lin , Pengchuan Zhang , Joya Chen , Shraman Pramanick , Difei Gao , Alex Jinpeng Wang , Rui Yan , Mike Zheng Shou
‹ 上一页 1 2 3 10 下一页 ›