中文
相关论文

相关论文: RAVEN: Robust Advertisement Video Violation Tempor…

200 篇论文

Advertising (Ad) is a cornerstone of the digital economy, yet the moderation of video advertisements remains a significant challenge due to their complexity and the need for precise violation localization. While recent advancements, such as…

机器学习 · 计算机科学 2025-11-25 Deyi Ji , Yuekui Yang , Liqun Liu , Peng Shu , Haiyang Wu , Shaogang Tang , Xudong Chen , Shaoping Ma , Tianrun Chen , Lanyun Zhu

We present RAVEN an adaptive AI agent framework designed for multimodal entity discovery and retrieval in large-scale video collections. Synthesizing information across visual, audio, and textual modalities, RAVEN autonomously processes…

信息检索 · 计算机科学 2025-04-10 Kevin Dela Rosa

The scaling of large language models to encode all the world's knowledge in model parameters is unsustainable and has exacerbated resource barriers. Retrieval-Augmented Generation (RAG) presents a potential solution, yet its application to…

计算机视觉与模式识别 · 计算机科学 2024-06-28 Varun Nagaraj Rao , Siddharth Choudhary , Aditya Deshpande , Ravi Kumar Satzoda , Srikar Appalaraju

Video understanding is inherently intention-driven-humans naturally focus on relevant frames based on their goals. Recent advancements in multimodal large language models (MLLMs) have enabled flexible query-driven reasoning; however,…

计算机视觉与模式识别 · 计算机科学 2025-05-22 Ziqiang Xu , Qi Dai , Tian Xie , Yifan Yang , Kai Qiu , DongDong Chen , Zuxuan Wu , Chong Luo

Causal autoregressive video diffusion models support real-time streaming generation by extrapolating future chunks from previously generated content. Distilling such generators from high-fidelity bidirectional teachers yields competitive…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Yanzuo Lu , Ronglai Zuo , Jiankang Deng

Multimodal question answering (QA) often requires identifying which video, audio, or sensor tokens are relevant to the question. Yet modality disagreements are common: off-camera speech, background noise, or motion outside the field of view…

计算与语言 · 计算机科学 2025-09-08 Subrata Biswas , Mohammad Nur Hossain Khan , Bashima Islam

Video reasoning, which requires multi-step deduction across frames, remains a major challenge for multimodal large language models (MLLMs). While reinforcement learning (RL)-based methods enhance reasoning capabilities, they often rely on…

计算机视觉与模式识别 · 计算机科学 2025-11-21 Kun Ouyang , Yuanxin Liu , Linli Yao , Yishuo Cai , Hao Zhou , Jie Zhou , Fandong Meng , Xu Sun

Reinforcement learning (RL) has emerged as a powerful paradigm for achieving online agile navigation with quadrotors. Despite this success, policies trained via standard RL typically fail to generalize across significant dynamic variations,…

机器人学 · 计算机科学 2026-03-12 Jin Zhou , Dongcheng Cao , Xian Wang , Shuo Li

Video temporal grounding (VTG) aims to locate precise segments in videos based on language queries, which is a fundamental challenge in video understanding. While recent Multimodal Large Language Models (MLLMs) have shown promise in…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Lu Dong , Haiyu Zhang , Han Lin , Ziang Yan , Xiangyu Zeng , Hongjie Zhang , Yifei Huang , Yi Wang , Zhen-Hua Ling , Limin Wang , Yali Wang

Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large language models (MLLMs) has demonstrated strong capabilities in…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Hongyu Li , Songhao Han , Yue Liao , Junfeng Luo , Jialin Gao , Shuicheng Yan , Si Liu

Comprehending long videos remains a significant challenge for Large Multi-modal Models (LMMs). Current LMMs struggle to process even minutes to hours videos due to their lack of explicit memory and retrieval mechanisms. To address this…

计算机视觉与模式识别 · 计算机科学 2025-05-07 Sameer Malik , Moyuru Yamada , Ayush Singh , Dishank Aggarwal

In real-world deployment, vision-language models often encounter disturbances such as weather, occlusion, and camera motion. Under such conditions, their understanding and reasoning degrade substantially, revealing a gap between clean,…

计算机视觉与模式识别 · 计算机科学 2026-04-15 Yangfan He , Changgyu Boo , Jaehong Yoon

Training Vision Language Models (VLMs) for video event reasoning requires high-quality structured annotations capturing not only what happened, but when, where, why, and with what consequence, at a scale manual labelling cannot support. We…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Han Zhang , Wanting Jiang , Tomasz Kornuta , Tian Zheng , Vidya Murali

Video generation models produce visually coherent content but struggle with tasks requiring spatial reasoning and multi-step planning. Reinforcement learning (RL) offers a path to improve generalization, but its effectiveness in video…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Ming Liu , Yunbei Zhang , Shilong Liu , Liwen Wang , Wensheng Zhang

The task of video grounding, which temporally localizes a natural language description in a video, plays an important role in understanding videos. Existing studies have adopted strategies of sliding window over the entire video or…

计算机视觉与模式识别 · 计算机科学 2019-01-23 Dongliang He , Xiang Zhao , Jizhou Huang , Fu Li , Xiao Liu , Shilei Wen

Temporal grounding of natural language in untrimmed videos is a fundamental yet challenging multimedia task facilitating cross-media visual content retrieval. We focus on the weakly supervised setting of this task that merely accesses to…

计算机视觉与模式识别 · 计算机科学 2020-09-21 Jie Wu , Guanbin Li , Xiaoguang Han , Liang Lin

Reasoning over dynamic visual content remains a central challenge for multimodal large language models. Recent thinking models generate explicit reasoning traces for interpretability; however, their reasoning often appears convincing while…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Muhammad Maaz , Hanoona Rasheed , Fahad Shahbaz Khan , Salman Khan

Large Vision-Language Models (LVLMs) have recently advanced robotic manipulation by leveraging vision for scene perception and language for instruction following. However, existing methods rely heavily on costly human-annotated training…

Evaluating the alignment between textual prompts and generated images is critical for ensuring the reliability and usability of text-to-image (T2I) models. However, most existing evaluation methods rely on coarse-grained metrics or static…

计算机视觉与模式识别 · 计算机科学 2026-02-24 Fulin Shi , Wenyi Xiao , Bin Chen , Liang Din , Leilei Gan

Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Yiyang Zhou , Yangfan He , Yaofeng Su , Siwei Han , Joel Jang , Gedas Bertasius , Mohit Bansal , Huaxiu Yao
‹ 上一页 1 2 3 10 下一页 ›