中文
相关论文

相关论文: STORM: End-to-End Referring Multi-Object Tracking …

200 篇论文

One of the recent trends in vision problems is to use natural language captions to describe the objects of interest. This approach can overcome some limitations of traditional methods that rely on bounding boxes or category annotations.…

计算机视觉与模式识别 · 计算机科学 2023-10-03 Pha Nguyen , Kha Gia Quach , Kris Kitani , Khoa Luu

LVLMs have been shown to perform excellently in image-level tasks such as VQA and caption. However, in many instance-level tasks, such as visual grounding and object detection, LVLMs still show performance gaps compared to previous expert…

计算机视觉与模式识别 · 计算机科学 2025-11-24 Teng Fu , Mengyang Zhao , Ke Niu , Kaixin Peng , Bin Li

Multiple-object tracking (MOT) is a challenging task that requires simultaneous reasoning about location, appearance, and identity of the objects in the scene over time. Our aim in this paper is to move beyond tracking-by-detection…

计算机视觉与模式识别 · 计算机科学 2022-10-27 Bruno Korbar , Andrew Zisserman

Semantic Multi-Object Tracking (SMOT) extends multi-object tracking with semantic outputs such as video summaries, instance-level captions, and interaction labels, aiming to move from trajectories to human-interpretable descriptions of…

计算机视觉与模式识别 · 计算机科学 2026-04-16 Laurence Bonat , Francesco Tonini , Elisa Ricci , Lorenzo Vaquero

Multi-Object Tracking (MOT) is evolving from geometric localization to Semantic MOT (SMOT) to answer complex relational queries, yet progress is hindered by semantic data scarcity and a structural disconnect between tracking architectures…

计算机视觉与模式识别 · 计算机科学 2026-03-13 Pan Liao , Feng Yang , Di Wu , Jinwen Yu , Yuhua Zhu , Wenhui Zhao , Dingwen Zhang

Language-vision understanding has driven the development of advanced perception systems, most notably the emerging paradigm of Referring Multi-Object Tracking (RMOT). By leveraging natural-language queries, RMOT systems can selectively…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Halima Bouzidi , Haoyu Liu , Mohammad Abdullah Al Faruque

Referring Multi-Object Tracking (RMOT) is a relatively new concept that has rapidly gained traction as a promising research direction at the intersection of computer vision and natural language processing. Unlike traditional multi-object…

计算机视觉与模式识别 · 计算机科学 2025-06-02 Huu-Thien Tran , Phuoc-Sang Pham , Thai-Son Tran , Khoa Luu

Referring Multi-Object Tracking (RMOT) aims to track specific targets based on language descriptions and is vital for interactive AI systems such as robotics and autonomous driving. However, existing RMOT models rely solely on 2D RGB data,…

计算机视觉与模式识别 · 计算机科学 2026-02-09 Sijia Chen , Lijuan Ma , Yanqiu Yu , En Yu , Liman Liu , Wenbing Tao

Referring Multi-Object Tracking (RMOT) aims to track targets specified by language instructions. However, existing RMOT paradigms heavily rely on explicit visual-textual matching and consequently fail to generalize to complex instructions…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Sijia Chen , Yanqiu Yu , En Yu , Wenbing Tao

Most existing Multi-Object Tracking (MOT) approaches follow the Tracking-by-Detection paradigm and the data association framework where objects are firstly detected and then associated. Although deep-learning based method can noticeably…

计算机视觉与模式识别 · 计算机科学 2020-07-14 Xingyu Wan , Jiakai Cao , Sanping Zhou , Jinjun Wang

While Multi-Object Tracking (MOT) has made substantial advancements, it is limited by heavy reliance on prior knowledge and limited to predefined categories. In contrast, Generic Multiple Object Tracking (GMOT), tracking multiple objects…

计算机视觉与模式识别 · 计算机科学 2024-09-05 Duy Le Dinh Anh , Kim Hoang Tran , Ngan Hoang Le

Referring Multi-Object Tracking (RMOT) aims to achieve precise object detection and tracking through natural language instructions, representing a fundamental capability for intelligent robotic systems. However, current RMOT research…

Multi-object tracking (MOT) has traditionally focused on estimating trajectories of all objects in a video, without selectively reasoning about user-specified targets under semantic instructions. In this work, we introduce a query-driven…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Tajamul Ashraf , Tavaheed Tariq , Sonia Yadav , Abrar Ul Riyaz , Wasif Tak , Moloud Abdar , Janibul Bashir

Temporal modeling of objects is a key challenge in multiple object tracking (MOT). Existing methods track by associating detections through motion-based and appearance-based similarity heuristics. The post-processing nature of association…

计算机视觉与模式识别 · 计算机科学 2022-07-20 Fangao Zeng , Bin Dong , Yuang Zhang , Tiancai Wang , Xiangyu Zhang , Yichen Wei

The problem of multi-object tracking is a fundamental computer vision research focus, widely used in public safety, transport, autonomous vehicles, robotics, and other regions involving artificial intelligence. Because of the complexity of…

计算机视觉与模式识别 · 计算机科学 2022-10-20 Kai Ren , Chuanping Hu

Visual foundation models provide strong perceptual features for robotics, but their dense representations lack explicit object-level structure, limiting robustness and contractility in manipulation tasks. We propose STORM (Slot-based…

机器人学 · 计算机科学 2026-01-29 Alexandre Chapin , Emmanuel Dellandréa , Liming Chen

Given an untrimmed video and natural language query, video sentence grounding aims to localize the target temporal moment in the video. Existing methods mainly tackle this task by matching and aligning semantics of the descriptive sentence…

计算机视觉与模式识别 · 计算机科学 2022-12-29 Wei Ji , Long Chen , Yinwei Wei , Yiming Wu , Tat-Seng Chua

The referring video object segmentation task (RVOS) involves segmentation of a text-referred object instance in the frames of a given video. Due to the complex nature of this multimodal task, which combines text reasoning, video…

计算机视觉与模式识别 · 计算机科学 2022-04-05 Adam Botach , Evgenii Zheltonozhskii , Chaim Baskin

Multi-modal language models (LM) have recently shown promising performance in high-level reasoning tasks on videos. However, existing methods still fall short in tasks like causal or compositional spatiotemporal reasoning over actions, in…

计算机视觉与模式识别 · 计算机科学 2024-01-23 Apratim Bhattacharyya , Sunny Panchal , Mingu Lee , Reza Pourreza , Pulkit Madan , Roland Memisevic

Referring Multi-Object Tracking (RMOT) aims to track multiple objects specified by natural language expressions in videos. With the recent significant progress of one-stage methods, the two-stage Referring-by-Tracking (RBT) paradigm has…

计算机视觉与模式识别 · 计算机科学 2026-03-12 Weize Li , Yunhao Du , Qixiang Yin , Zhicheng Zhao , Fei Su