中文
相关论文

相关论文: Spherical Vision Transformer for 360-degree Video …

200 篇论文

Natural environment and our interaction with it is essentially multisensory, where we may deploy visual, tactile and/or auditory senses to perceive, learn and interact with our environment. Our objective in this study is to develop a scene…

音频与语音处理 · 电气工程与系统科学 2020-03-17 Sudarshan Ramenahalli

Novel View Synthesis (NVS) aims to generate unseen views of a 3D object given a limited number of known views. Existing methods often struggle to synthesize plausible views for unobserved regions, particularly under single-view input, and…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Jinglin Liang , Zijian Zhou , Rui Huang , Shuangping Huang , Yichen Gong

Depth estimation has been widely studied and serves as the fundamental step of 3D perception for robotics and autonomous driving. Though significant progress has been made in monocular depth estimation in the past decades, these attempts…

计算机视觉与模式识别 · 计算机科学 2025-11-13 Xianda Guo , Wenjie Yuan , Yunpeng Zhang , Tian Yang , Chenming Zhang , Zheng Zhu , Qin Zou , Long Chen

Panorama video recently attracts more interest in both study and application, courtesy of its immersive experience. Due to the expensive cost of capturing 360-degree panoramic videos, generating desirable panorama videos by prompts is…

计算机视觉与模式识别 · 计算机科学 2024-05-13 Qian Wang , Weiqi Li , Chong Mou , Xinhua Cheng , Jian Zhang

360$^{\circ}$ panoramas are a rich medium, yet notoriously difficult to visualize in the 2D image plane. We explore how intelligent rotations of a spherical image may enable content-aware projection with fewer perceptible distortions.…

计算机视觉与模式识别 · 计算机科学 2018-08-14 Bo Xiong , Kristen Grauman

Ensuring safety in autonomous driving is a complex challenge requiring handling unknown objects and unforeseen driving scenarios. We develop multiscale video transformers capable of detecting unknown objects using only motion cues. Video…

计算机视觉与模式识别 · 计算机科学 2025-08-21 Leila Cheshmi , Mennatullah Siam

Deep learning approaches have been established as the main methodology for video classification and recognition. Recently, 3-dimensional convolutions have been used to achieve state-of-the-art performance in many challenging video datasets.…

计算机视觉与模式识别 · 计算机科学 2020-06-24 Alexandros Stergiou , Georgios Kapidis , Grigorios Kalliatakis , Christos Chrysoulas , Remco Veltkamp , Ronald Poppe

Despite significant progress in semi-supervised learning for image object detection, several key issues are yet to be addressed for video object detection: (1) Achieving good performance for supervised video object detection greatly depends…

计算机视觉与模式识别 · 计算机科学 2023-11-14 Tanvir Mahmud , Chun-Hao Liu , Burhaneddin Yaman , Diana Marculescu

Video Object Segmentation (VOS) has emerged as an increasingly important problem with availability of larger datasets and more complex and realistic settings, which involve long videos with global motion (e.g, in egocentric settings),…

计算机视觉与模式识别 · 计算机科学 2024-04-11 Raghav Goyal , Wan-Cyuan Fan , Mennatullah Siam , Leonid Sigal

Implicit neural representations for videos (NeRV) have shown strong potential for video compression. However, applying NeRV to high-resolution 360-degree videos causes high memory usage and slow decoding, making real-time applications…

计算机视觉与模式识别 · 计算机科学 2026-02-17 Daichi Arai , Kyohei Unno , Yasuko Sugito , Yuichi Kusakabe

In this work, we propose an efficient and effective approach for unconstrained salient object detection in images using deep convolutional neural networks. Instead of generating thousands of candidate bounding boxes and refining them, our…

计算机视觉与模式识别 · 计算机科学 2017-08-03 Mahyar Najibi , Fan Yang , Qiaosong Wang , Robinson Piramuthu

Humans excel at constructing panoramic mental models of their surroundings, maintaining object permanence and inferring scene structure beyond visible regions. In contrast, current artificial vision systems struggle with persistent,…

计算机视觉与模式识别 · 计算机科学 2025-12-16 Finlay G. C. Hudson , James A. D. Gardner , William A. P. Smith

Video saliency detection (VSD) aims at fast locating the most attractive objects/things/patterns in a given video clip. Existing VSD-related works have mainly relied on the visual system but paid less attention to the audio aspect, while,…

计算机视觉与模式识别 · 计算机科学 2022-06-28 Chenglizhao Chen , Mengke Song , Wenfeng Song , Li Guo , Muwei Jian

We propose a self-supervised learning framework that uses unlabeled monocular video sequences to generate large-scale supervision for training a Visual Odometry (VO) frontend, a network which computes pointwise data associations across…

计算机视觉与模式识别 · 计算机科学 2018-12-11 Daniel DeTone , Tomasz Malisiewicz , Andrew Rabinovich

Vision Transformer (ViT) has prevailed in computer vision tasks due to its strong long-range dependency modelling ability. \textcolor{blue}{However, its large model size and weak local feature modeling ability hinder its application in real…

计算机视觉与模式识别 · 计算机科学 2025-09-12 Yi Zhang , Lingxiao Wei , Bowei Zhang , Ziwei Liu , Kai Yi , Shu Hu

Video understanding requires reasoning at multiple spatiotemporal resolutions -- from short fine-grained motions to events taking place over longer durations. Although transformer architectures have recently advanced the state-of-the-art,…

计算机视觉与模式识别 · 计算机科学 2022-06-01 Shen Yan , Xuehan Xiong , Anurag Arnab , Zhichao Lu , Mi Zhang , Chen Sun , Cordelia Schmid

Omnidirectional multi-view stereo (MVS) vision is attractive for its ultra-wide field-of-view (FoV), enabling machines to perceive 360{\deg} 3D surroundings. However, the existing solutions require expensive dense depth labels for…

计算机视觉与模式识别 · 计算机科学 2023-02-23 Zisong Chen , Chunyu Lin , Lang Nie , Kang Liao , Yao Zhao

The ability to predict future visual observations conditioned on past observations and motor commands can enable embodied agents to plan solutions to a variety of tasks in complex environments. This work shows that we can create good video…

计算机视觉与模式识别 · 计算机科学 2022-08-09 Agrim Gupta , Stephen Tian , Yunzhi Zhang , Jiajun Wu , Roberto Martín-Martín , Li Fei-Fei

360-degree video becomes increasingly popular among users. In the current network bandwidth, serving high resolution 360 degree video to users is quite difficult. Most of the work has been devoted to the prediction of user viewports or…

多媒体 · 计算机科学 2023-08-29 Zhiyu Pang

In this paper we introduce a Transformer-based approach to video object segmentation (VOS). To address compounding error and scalability issues of prior work, we propose a scalable, end-to-end method for VOS called Sparse Spatiotemporal…

计算机视觉与模式识别 · 计算机科学 2021-03-30 Brendan Duke , Abdalla Ahmed , Christian Wolf , Parham Aarabi , Graham W. Taylor