English
Related papers

Related papers: What can Off-the-Shelves Large Multi-Modal Models …

200 papers

Long video understanding (LVU) remains a core challenge in multimodal learning. Although recent vision-language models (VLMs) have made notable progress, existing benchmarks mainly focus on either fine-grained perception or coarse…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Seng Nam Chen , Hao Chen , Chenglam Ho , Xinyu Mao , Jinping Wang , Yu Zhang , Chao Li

The rapid advancement of Multimodal Large Language Models (MLLMs) has significantly impacted various multimodal tasks. However, these models face challenges in tasks that require spatial understanding within 3D environments. Efforts to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Duo Zheng , Shijia Huang , Liwei Wang

While Open Set Semantic Mapping and 3D Semantic Scene Graphs (3DSSGs) are established paradigms in robotic perception, deploying them effectively to support high-level reasoning in large-scale, real-world environments remains a significant…

Robotics · Computer Science 2026-02-04 Martin Günther , Felix Igelbrink , Oscar Lima , Lennart Niecksch , Marian Renz , Martin Atzmueller

Deep learning techniques have led to remarkable breakthroughs in the field of generic object detection and have spawned a lot of scene-understanding tasks in recent years. Scene graph has been the focus of research because of its powerful…

Computer Vision and Pattern Recognition · Computer Science 2022-06-23 Guangming Zhu , Liang Zhang , Youliang Jiang , Yixuan Dang , Haoran Hou , Peiyi Shen , Mingtao Feng , Xia Zhao , Qiguang Miao , Syed Afaq Ali Shah , Mohammed Bennamoun

This position paper argues for the use of \emph{structured generative models} (SGMs) for the understanding of static scenes. This requires the reconstruction of a 3D scene from an input image (or a set of multi-view images), whereby the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Christopher K. I. Williams

The task of dynamic scene graph generation (DynSGG) aims to generate scene graphs for given videos, which involves modeling the spatial-temporal information in the video. However, due to the long-tailed distribution of samples in the…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Xinyu Lyu , Jingwei Liu , Yuyu Guo , Lianli Gao

3D scene graph generation (SGG) has been of high interest in computer vision. Although the accuracy of 3D SGG on coarse classification and single relation label has been gradually improved, the performance of existing works is still far…

Computer Vision and Pattern Recognition · Computer Science 2022-11-15 Yuanyuan Liu , Chengjiang Long , Zhaoxuan Zhang , Bokai Liu , Qiang Zhang , Baocai Yin , Xin Yang

The scene graph generation (SGG) task aims to detect visual relationship triplets, i.e., subject, predicate, object, in an image, providing a structural vision layout for scene understanding. However, current models are stuck in common…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Yuyu Guo , Lianli Gao , Xuanhan Wang , Yuxuan Hu , Xing Xu , Xu Lu , Heng Tao Shen , Jingkuan Song

Traditional scene graphs primarily focus on spatial relationships, limiting vision-language models' (VLMs) ability to reason about complex interactions in visual scenes. This paper addresses two key challenges: (1) conventional…

Computer Vision and Pattern Recognition · Computer Science 2025-05-15 Dayong Liang , Changmeng Zheng , Zhiyuan Wen , Yi Cai , Xiao-Yong Wei , Qing Li

Scene graphs provide a rich, structured representation of a scene by encoding the entities (objects) and their spatial relationships in a graphical format. This representation has proven useful in several tasks, such as question answering,…

Computer Vision and Pattern Recognition · Computer Science 2022-12-01 Sanjoy Kundu , Sathyanarayanan N. Aakur

The latest emerged 4D Panoptic Scene Graph (4D-PSG) provides an advanced-ever representation for comprehensively modeling the dynamic 4D visual real world. Unfortunately, current pioneering 4D-PSG research can primarily suffer from data…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Shengqiong Wu , Hao Fei , Jingkang Yang , Xiangtai Li , Juncheng Li , Hanwang Zhang , Tat-seng Chua

Scene Graph Generation (SGG) converts visual scenes into structured graph representations, providing deeper scene understanding for complex vision tasks. However, existing SGG models often overlook essential spatial relationships and…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Mingjie Xu , Mengyang Wu , Yuzhi Zhao , Jason Chun Lok Li , Weifeng Ou

Panoptic Scene Graph Generation (PSG) aims to segment objects and recognize their relations, enabling the structured understanding of an image. Previous methods focus on predicting predefined object and relation categories, hence limiting…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Zijian Zhou , Zheng Zhu , Holger Caesar , Miaojing Shi

Dynamic scene graph generation extends scene graph generation from images to videos by modeling entity relationships and their temporal evolution. However, existing methods either generate scene graphs from observed frames without…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Yi Yang , Yuren Cong , Hao Cheng , Bodo Rosenhahn , Michael Ying Yang

Scene graph generation aims to detect visual relationship triplets, (subject, predicate, object). Due to biases in data, current models tend to predict common predicates, e.g. "on" and "at", instead of informative ones, e.g. "standing on"…

Computer Vision and Pattern Recognition · Computer Science 2024-11-21 Lianli Gao , Xinyu Lyu , Yuyu Guo , Yuxuan Hu , Yuan-Fang Li , Lu Xu , Heng Tao Shen , Jingkuan Song

A 3D scene graph represents a compact scene model by capturing both the objects present and the semantic relationships between them, making it a promising structure for robotic applications. To effectively interact with users, an embodied…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Tatiana Zemskova , Dmitry Yudin

Scene graph generation from images is a task of great interest to applications such as robotics, because graphs are the main way to represent knowledge about the world and regulate human-robot interactions in tasks such as Visual Question…

Robotics · Computer Science 2022-12-21 Fernando Amodeo , Fernando Caballero , Natalia Díaz-Rodríguez , Luis Merino

We introduce the Deformable Gaussian Splats Large Reconstruction Model (DGS-LRM), the first feed-forward method predicting deformable 3D Gaussian splats from a monocular posed video of any dynamic scene. Feed-forward scene reconstruction…

3D scene graphs provide a structured representation of object entities and their relationships, enabling high-level interpretation and reasoning for robots while remaining intuitively understandable to humans. Existing approaches for 3D…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Zirui Wang , Ruiping Liu , Yufan Chen , Junwei Zheng , Weijia Fan , Kunyu Peng , Di Wen , Jiale Wei , Jiaming Zhang , Rainer Stiefelhagen

Inverse graphics -- the task of inverting an image into physical variables that, when rendered, enable reproduction of the observed scene -- is a fundamental challenge in computer vision and graphics. Successfully disentangling an image…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Peter Kulits , Haiwen Feng , Weiyang Liu , Victoria Abrevaya , Michael J. Black