English
Related papers

Related papers: FrameVGGT: Geometry-Aligned Frame-Level Memory for…

200 papers

Recent 3D feed-forward models, such as the Visual Geometry Grounded Transformer (VGGT), have shown strong capability in inferring 3D attributes of static scenes. However, since they are typically trained on static datasets, these models…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Kaichen Zhou , Yuhan Wang , Grace Chen , Xinhai Chang , Gaspard Beaudouin , Fangneng Zhan , Paul Pu Liang , Mengyu Wang

The core challenge for streaming video generation is maintaining the content consistency in long context, which poses high requirement for the memory design. Most existing solutions maintain the memory by compressing historical frames with…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Sihui Ji , Xi Chen , Shuai Yang , Xin Tao , Pengfei Wan , Hengshuang Zhao

Despite recent advances in Video Large Language Models (Vid-LLMs), Temporal Video Grounding (TVG), which aims to precisely localize time segments corresponding to query events, remains a significant challenge. Existing methods often match…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Jiahao Nie , Wenbin An , Gongjie Zhang , Yicheng Xu , Yap-Peng Tan , Alex C. Kot , Shijian Lu

Video depth estimation extends monocular prediction into the temporal domain to ensure coherence. However, existing methods often suffer from spatial blurring in fine-detail regions and temporal inconsistencies. We argue that current…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Yuecheng Liu , Junda Cheng , Longliang Liu , Wenjing Liao , Hanrui Cheng , Yuzhou Wang , Xin Yang

Transformers process images and videos by flattening space and time into long token sequences. While attention and KV caching preserve past features, their memory grows with sequence length and they lack an explicit, persistent spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Kabir Swain , Sijie Han , Daniel Karl I. Weidele , Mauro Martino , Antonio Torralba

The rapid development of deep learning has significant implications for the advancement of Computational Fluid Dynamics (CFD). Currently, most pixel-grid-based deep learning methods for flow field prediction exhibit significantly reduced…

Fluid Dynamics · Physics 2024-04-11 Tianyu Li , Shufan Zou , Xinghua Chang , Laiping Zhang , Xiaogang Deng

Visual Language Models (VLMs) have increasingly become the main paradigm for understanding indoor scenes, but they still struggle with metric and spatial reasoning. Current approaches rely on end-to-end video understanding or large-scale…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Fernando Ropero , Erkin Turkoz , Daniel Matos , Junqing Du , Antonio Ruiz , Yanfeng Zhang , Lu Liu , Mingwei Sun , Yongliang Wang

Top-leading solutions for Video Scene Graph Generation (VSGG) typically adopt an offline pipeline. Though demonstrating promising performance, they remain unable to handle real-time video streams and consume large GPU memory. Moreover,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Mu Chen , Liulei Li , Wenguan Wang , Yi Yang

Video Temporal Grounding (VTG) localizes the temporal boundaries of a query-relevant moment in long, untrimmed videos, making video-language-model (VLM) pipelines prohibitively expensive. While recent training-free visual token pruning has…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Jiaqi Li , Shuntian Zheng , Yixian Shen , Jia-Hong Huang , Xiaoman Lu , Minzhe Ni , Yu Guan

Vision-language models (VLM) excel at general understanding yet remain weak at dynamic spatial reasoning (DSR), i.e., reasoning about the evolvement of object geometry and relationship in 3D space over time, largely due to the scarcity of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Shengchao Zhou , Yuxin Chen , Yuying Ge , Wei Huang , Jiehong Lin , Ying Shan , Xiaojuan Qi

Recent advancements in neural visual geometry, including transformer-based models such as VGGT and Pi3, have achieved impressive accuracy on 3D reconstruction tasks. However, their reliance on full attention makes them fundamentally limited…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Leo Kaixuan Cheng , Abdus Shaikh , Ruofan Liang , Zhijie Wu , Yushi Guan , Nandita Vijaykumar

As Large Language Models (LLMs) scale to support context windows exceeding one million tokens, the linear growth of Key-Value (KV) cache imposes severe memory capacity and bandwidth bottlenecks, constraining the efficiency of long-context…

Computation and Language · Computer Science 2026-04-09 Zhirui Chen , Peiyang Liu , Ling Shao

Point cloud semantic segmentation from projected views, such as range-view (RV) and bird's-eye-view (BEV), has been intensively investigated. Different views capture different information of point clouds and thus are complementary to each…

Computer Vision and Pattern Recognition · Computer Science 2022-09-27 Haibo Qiu , Baosheng Yu , Dacheng Tao

Knowledge graph embeddings (KGE) have been extensively studied to embed large-scale relational data for many real-world applications. Existing methods have long ignored the fact many KGs contain two fundamentally different views: high-level…

Artificial Intelligence · Computer Science 2023-07-06 Zijie Huang , Daheng Wang , Binxuan Huang , Chenwei Zhang , Jingbo Shang , Yan Liang , Zhengyang Wang , Xian Li , Christos Faloutsos , Yizhou Sun , Wei Wang

Humans perceive and understand real-world spaces through a stream of visual observations. Therefore, the ability to streamingly maintain and update spatial evidence from potentially unbounded video streams is essential for spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Fangfu Liu , Diankun Wu , Jiawei Chi , Yimo Cai , Yi-Hsin Hung , Xumin Yu , Hao Li , Han Hu , Yongming Rao , Yueqi Duan

Empowered by large-scale training, vision-language models (VLMs) achieve strong image and video understanding, yet their ability to perform spatial reasoning in both static scenes and dynamic videos remains limited. Recent advances try to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Shihua Zhang , Qiuhong Shen , Shizun Wang , Tianbo Pan , Xinchao Wang

Recent advancements in generative video codec (GVC) typically encode video into a 2D latent grid and employ high-capacity generative decoders for reconstruction. However, this paradigm still leaves two key challenges in fully exploiting…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Zihan Zheng , Zhaoyang Jia , Naifu Xue , Jiahao Li , Bin Li , Zongyu Guo , Xiaoyi Zhang , Zhenghao Chen , Houqiang Li , Yan Lu

The rapid progress of large language models (LLMs) has laid the foundation for multimodal models. However, visual language models (VLMs) still face heavy computational costs when extended from images to videos due to high frame rates and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Peiran Wu , Zhuorui Yu , Yunze Liu , Chi-Hao Wu , Enmin Zhou , Junxiao Shen

Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Ruyi Xu , Guangxuan Xiao , Yukang Chen , Liuning He , Kelly Peng , Yao Lu , Song Han

Efficient video-language modeling should consider the computational cost because of a large, sometimes intractable, number of video frames. Parametric approaches such as the attention mechanism may not be ideal since its computational cost…

Computer Vision and Pattern Recognition · Computer Science 2023-01-30 Sungdong Kim , Jin-Hwa Kim , Jiyoung Lee , Minjoon Seo