中文
相关论文

相关论文: Omni-Captioner: Data Pipeline, Models, and Benchma…

200 篇论文

Language-based object detection is a promising direction towards building a natural interface to describe objects in images that goes far beyond plain category names. While recent methods show great progress in that direction, proper…

计算机视觉与模式识别 · 计算机科学 2023-08-16 Samuel Schulter , Vijay Kumar B G , Yumin Suh , Konstantinos M. Dafnis , Zhixing Zhang , Shiyu Zhao , Dimitris Metaxas

Large Language Models (LLMs) have made significant strides in text generation and comprehension, with recent advancements extending into multimodal LLMs that integrate visual and audio inputs. However, these models continue to struggle with…

计算与语言 · 计算机科学 2024-10-17 Arushi Goel , Karan Sapra , Matthieu Le , Rafael Valle , Andrew Tao , Bryan Catanzaro

Training multimodal large language models (MLLMs) for video understanding requires large-scale annotated data spanning diverse tasks such as object counting, question answering, and segmentation. However, collecting and annotating…

计算机视觉与模式识别 · 计算机科学 2026-04-15 Tanzila Rahman , Renjie Liao , Leonid Sigal

Can Multimodal Large Language Models (MLLMs) discern confused objects that are visually present but audio-absent? To study this, we introduce a new benchmark, AV-ConfuseBench, which simulates an ``Audio-Visual Confusion'' scene by modifying…

计算机视觉与模式识别 · 计算机科学 2025-11-14 Qilang Ye , Wei Zeng , Meng Liu , Jie Zhang , Yupeng Hu , Zitong Yu , Yu Zhou

Recent advancements in audio-video joint generation models have demonstrated impressive capabilities in content creation. However, generating high-fidelity human-centric videos in complex, real-world physical scenes remains a significant…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Lei Zhu , Xing Cai , Yingjie Chen , Yiheng Li , Binxin Yang , Hao Liu , Jie Chen , Chen Li , Jing LYu

Despite impressive advancements in video understanding, most efforts remain limited to coarse-grained or visual-only video tasks. However, real-world videos encompass omni-modal information (vision, audio, and speech) with a series of…

计算机视觉与模式识别 · 计算机科学 2025-03-21 Tiantian Geng , Jinrui Zhang , Qingni Wang , Teng Wang , Jinming Duan , Feng Zheng

The progression to "Pervasive Augmented Reality" envisions easy access to multimodal information continuously. However, in many everyday scenarios, users are occupied physically, cognitively or socially. This may increase the friction to…

人机交互 · 计算机科学 2024-05-08 Jiahao Nick Li , Yan Xu , Tovi Grossman , Stephanie Santosa , Michelle Li

The rapid advancements in Large Vision Language Models (LVLMs) offer the potential to surpass conventional labeling by generating richer, more detailed descriptions of on-device human behavior understanding (HBU) in low-resolution vision…

计算机视觉与模式识别 · 计算机科学 2025-05-06 Siyang Jiang , Bufang Yang , Lilin Xu , Mu Yuan , Yeerzhati Abudunuer , Kaiwei Liu , Liekang Zeng , Hongkai Chen , Zhenyu Yan , Xiaofan Jiang , Guoliang Xing

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

Video detailed captioning is a key task which aims to generate comprehensive and coherent textual descriptions of video content, benefiting both video understanding and generation. In this paper, we propose AuroraCap, a video captioner…

计算机视觉与模式识别 · 计算机科学 2025-04-10 Wenhao Chai , Enxin Song , Yilun Du , Chenlin Meng , Vashisht Madhavan , Omer Bar-Tal , Jenq-Neng Hwang , Saining Xie , Christopher D. Manning

Localizing and recognizing objects in the open-ended physical world poses a long-standing challenge within the domain of machine perception. Recent methods have endeavored to address the issue by employing a class-agnostic mask (or box)…

计算机视觉与模式识别 · 计算机科学 2023-11-15 Qihang Yu , Xiaohui Shen , Liang-Chieh Chen

Current Large Multimodal Models (LMMs) achieve remarkable progress, yet there remains significant uncertainty regarding their ability to accurately apprehend visual details, that is, in performing detailed captioning. To address this, we…

计算机视觉与模式识别 · 计算机科学 2024-04-01 Bohan Zhai , Shijia Yang , Chenfeng Xu , Sheng Shen , Kurt Keutzer , Chunyuan Li , Manling Li

Object counting is pivotal for understanding the composition of scenes. Previously, this task was dominated by class-specific methods, which have gradually evolved into more adaptable class-agnostic strategies. However, these strategies…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Anindya Mondal , Sauradip Nag , Xiatian Zhu , Anjan Dutta

Video-language models (VLMs) learn to reason about the dynamic visual world through natural language. We introduce a suite of open datasets, benchmarks, and recipes for scalable oversight that enable precise video captioning. First, we…

The advent of large Vision-Language Models (VLMs) has significantly advanced multimodal tasks, enabling more sophisticated and accurate reasoning across various applications, including image and video captioning, visual question answering,…

计算机视觉与模式识别 · 计算机科学 2024-11-26 Hang Hua , Qing Liu , Lingzhi Zhang , Jing Shi , Zhifei Zhang , Yilin Wang , Jianming Zhang , Jiebo Luo

Audio-text retrieval systems based on Contrastive Language-Audio Pretraining (CLAP) achieve strong performance on traditional benchmarks; however, these benchmarks rely on caption-style queries that differ substantially from real-world…

声音 · 计算机科学 2026-04-21 HaeJun Yoo , Yongseop Shin , Insung Lee , Myoung-Wan Koo , Du-Seong Chang

The advancement of object detection (OD) in open-vocabulary and open-world scenarios is a critical challenge in computer vision. This work introduces OmDet, a novel language-aware object detection architecture, and an innovative training…

计算机视觉与模式识别 · 计算机科学 2024-02-27 Tiancheng Zhao , Peng Liu , Kyusong Lee

Magnetic Resonance Imaging (MRI) is indispensable in clinical practice but remains constrained by fragmented, multi-stage workflows encompassing acquisition, reconstruction, segmentation, detection, diagnosis, and reporting. While deep…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Xingxin He , Aurora Rofena , Ruimin Feng , Haozhe Liao , Zhaoye Zhou , Albert Jang , Fang Liu

Accurate dialogue description in audiovisual video captioning is crucial for downstream understanding and generation tasks. However, existing models generally struggle to produce faithful dialogue descriptions within audiovisual captions.…

Recent progress in multimodal large language models (MLLMs) has brought AI capabilities from static offline data processing to real-time streaming interaction, yet they still remain far from human-level multimodal interaction. The key…