中文
相关论文

相关论文: One Token to Seg Them All: Language Instructed Rea…

200 篇论文

Recent efforts in video reasoning segmentation (VRS) integrate large language models (LLMs) with perception models to localize and track objects via textual instructions, achieving barely satisfactory results in simple scenarios. However,…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Rongkun Zheng , Lu Qi , Xi Chen , Yi Wang , Kun Wang , Yu Qiao , Hengshuang Zhao

Existing Video Object Segmentation (VOS) relies on explicit user instructions, such as categories, masks, or short phrases, restricting their ability to perform complex video segmentation requiring reasoning with world knowledge. In this…

计算机视觉与模式识别 · 计算机科学 2024-07-17 Cilin Yan , Haochen Wang , Shilin Yan , Xiaolong Jiang , Yao Hu , Guoliang Kang , Weidi Xie , Efstratios Gavves

Although perception systems have made remarkable advancements in recent years, they still rely on explicit human instruction or pre-defined categories to identify the target objects before executing visual recognition tasks. Such systems…

计算机视觉与模式识别 · 计算机科学 2024-05-02 Xin Lai , Zhuotao Tian , Yukang Chen , Yanwei Li , Yuhui Yuan , Shu Liu , Jiaya Jia

This paper aims to address universal segmentation for image and video perception with the strong reasoning ability empowered by Visual Large Language Models (VLLMs). Despite significant progress in current unified segmentation methods,…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Cong Wei , Yujie Zhong , Haoxian Tan , Yong Liu , Zheng Zhao , Jie Hu , Yujiu Yang

Boosted by Multi-modal Large Language Models (MLLMs), text-guided universal segmentation models for the image and video domains have made rapid progress recently. However, these methods are often developed separately for specific domains,…

计算机视觉与模式识别 · 计算机科学 2024-12-19 Cong Wei , Yujie Zhong , Haoxian Tan , Yingsen Zeng , Yong Liu , Zheng Zhao , Yujiu Yang

Video Reasoning Segmentation (VRS) aims to segment target objects in videos based on implicit instructions that convey human intent and temporal logic. Existing MLLM-based methods predict masks with a [SEG] token after selecting frames via…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Junwei Wen , Deshui Miao , Guangming Lu , Xin Li , Wenjie Pei

Existing methods for Video Reasoning Segmentation rely heavily on a single special token to represent the object in the keyframe or the entire video, inadequately capturing spatial complexity and inter-frame motion. To overcome these…

计算机视觉与模式识别 · 计算机科学 2025-03-03 Sitong Gong , Yunzhi Zhuge , Lu Zhang , Zongxin Yang , Pingping Zhang , Huchuan Lu

Reasoning Video Object Segmentation (ReasonVOS) is a challenging task that requires stable object segmentation across video sequences using implicit and complex textual inputs. Previous methods fine-tune Multimodal Large Language Models…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Zhengtong Zhu , Jiaqing Fan , Zhixuan Liu , Fanzhang Li

Referring video object segmentation (RVOS) requires tracking and segmenting an object throughout a video according to a given natural language expression, demanding both complex motion understanding and the alignment of visual…

计算机视觉与模式识别 · 计算机科学 2025-03-27 Seongchan Kim , Woojeong Jin , Sangbeom Lim , Heeji Yoon , Hyunwook Choi , Seungryong Kim

The prosperity of Multimodal Large Language Models (MLLMs) has stimulated the demand for video reasoning segmentation, which aims to segment video objects based on human instructions. Previous studies rely on unidirectional and implicit…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Jingnan Luo , Mingqi Gao , Jun Liu , Bin-Bin Gao , Feng Zheng

Multimodal Large Language Models (MLLMs) have demonstrated strong image-level visual understanding and reasoning, yet their pixel-level perception across both images and videos remains limited. Foundation segmentation models such as the SAM…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Hao Wang , Limeng Qiao , Chi Zhang , Lin Ma , Guanglu Wan , Xiangyuan Lan , Xiaodan Liang

In this work, we present a novel method to tackle the token generation challenge in Vision Language Models (VLMs) for video and image understanding, called LLaMA-VID. Current VLMs, while proficient in tasks like image captioning and visual…

计算机视觉与模式识别 · 计算机科学 2023-11-29 Yanwei Li , Chengyao Wang , Jiaya Jia

Referring Audio-Visual Segmentation (Ref-AVS) aims to segment specific objects in videos based on natural language expressions involving audio, vision, and text information. This task poses significant challenges in cross-modal reasoning…

计算机视觉与模式识别 · 计算机科学 2025-09-24 Dian Jin , Yanghao Zhou , Jinxing Zhou , Jiaqi Ma , Ruohao Guo , Dan Guo

Referring Video Object Segmentation (RVOS) aims to segment target objects in videos based on natural language descriptions. However, fixed keyframe-based approaches that couple a vision language model with a separate propagation module…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Jihwan Hong , Jaeyoung Do

We present LlamaSeg, a visual autoregressive framework that unifies multiple image segmentation tasks via natural language instructions. We reformulate image segmentation as a visual generation problem, representing masks as "visual" tokens…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Jiru Deng , Tengjin Weng , Tianyu Yang , Wenhan Luo , Zhiheng Li , Wenhao Jiang

With the exponential growth of video data, there is an urgent need for automated technology to analyze and comprehend video content. However, existing video understanding models are often task-specific and lack a comprehensive capability of…

计算机视觉与模式识别 · 计算机科学 2023-05-24 Guo Chen , Yin-Dong Zheng , Jiahao Wang , Jilan Xu , Yifei Huang , Junting Pan , Yi Wang , Yali Wang , Yu Qiao , Tong Lu , Limin Wang

Video reasoning segmentation (VRS) endeavors to delineate referred objects in videos guided by implicit instructions that encapsulate human intent and temporal logic. Previous approaches leverage large vision language models (LVLMs) to…

计算机视觉与模式识别 · 计算机科学 2026-03-05 Sitong Gong , Lu Zhang , Yunzhi Zhuge , Xu Jia , Pingping Zhang , Huchuan Lu

This paper proposes a novel framework utilizing multi-modal large language models (MLLMs) for referring video object segmentation (RefVOS). Previous MLLM-based methods commonly struggle with the dilemma between "Ref" and "VOS": they either…

计算机视觉与模式识别 · 计算机科学 2025-04-11 Lang Lin , Xueyang Yu , Ziqi Pang , Yu-Xiong Wang

Referring Video Object Segmentation (RVOS) aims to segment an object of interest throughout a video based on a language description. The prominent challenge lies in aligning static text with dynamic visual content, particularly when objects…

计算机视觉与模式识别 · 计算机科学 2025-09-09 Bingrui Zhao , Lin Yuanbo Wu , Xiangtian Fan , Deyin Liu , Lu Zhang , Ruyi He , Jialie Shen , Ximing Li

Understanding human instructions to identify the target objects is vital for perception systems. In recent years, the advancements of Large Language Models (LLMs) have introduced new possibilities for image segmentation. In this work, we…

计算机视觉与模式识别 · 计算机科学 2024-04-16 Junchi Wang , Lei Ke
‹ 上一页 1 2 3 10 下一页 ›