中文
相关论文

相关论文: RAPTOR: Real-Time High-Resolution UAV Video Predic…

200 篇论文

Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism,…

计算机视觉与模式识别 · 计算机科学 2024-05-06 Lorenzo Papa , Paolo Russo , Irene Amerini , Luping Zhou

With the increasing prevalence of video content, effectively understanding and answering questions about long form videos has become essential for numerous applications. Although large vision language models (LVLMs) have enhanced…

计算机视觉与模式识别 · 计算机科学 2026-04-13 Urjitkumar Patel , Fang-Chun Yeh , Chinmay Gondhalekar

Recent advances in sparse voxel representations have significantly improved the quality of 3D content generation, enabling high-resolution modeling with fine-grained geometry. However, existing frameworks suffer from severe computational…

计算机视觉与模式识别 · 计算机科学 2025-08-01 Yiwen Chen , Zhihao Li , Yikai Wang , Hu Zhang , Qin Li , Chi Zhang , Guosheng Lin

Multimodal reasoning over long-horizon video is challenging due to the need for precise spatiotemporal fusion and alignment across modalities. While recent methods such as Group Relative Policy Optimization (GRPO) have shown promise in this…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Yogesh Kulkarni , Pooyan Fazli

Object tracking from Unmanned Aerial Vehicles (UAVs) is challenged by platform dynamics, camera motion, and limited onboard resources. Existing visual trackers either lack robustness in complex scenarios or are too computationally demanding…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Augustin Borne , Pierre Notin , Christophe Hennequin , Sebastien Changey , Stephane Bazeille , Christophe Cudel , Franz Quint

Vision-based Transformer have shown huge application in the perception module of autonomous driving in terms of predicting accurate 3D bounding boxes, owing to their strong capability in modeling long-range dependencies between the visual…

计算机视觉与模式识别 · 计算机科学 2023-04-06 Apoorv Singh

We propose Anticipative Video Transformer (AVT), an end-to-end attention-based video modeling architecture that attends to the previously observed video in order to anticipate future actions. We train the model jointly to predict the next…

计算机视觉与模式识别 · 计算机科学 2021-09-23 Rohit Girdhar , Kristen Grauman

Object tracking is a fundamental task in computer vision with broad practical applications across various domains, including traffic monitoring, robotics, and autonomous vehicle tracking. In this project, we aim to develop a sophisticated…

计算机视觉与模式识别 · 计算机科学 2024-05-30 Tharun V. Puthanveettil , Fnu Obaid ur Rahman

Diffusion models have significantly advanced video super-resolution (VSR) by enhancing perceptual quality, largely through elaborately designed temporal modeling to ensure inter-frame consistency. However, existing methods usually suffer…

计算机视觉与模式识别 · 计算机科学 2025-06-11 Xijun Wang , Xin Li , Bingchen Li , Zhibo Chen

Transformer based diffusion and vision-language models have achieved remarkable success; yet, efficiently removing undesirable or sensitive information without retraining remains a central challenge for model safety and compliance. We…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Ravi Ranjan , Utkarsh Grover , Xiaomin Lin , Agoritsa Polyzou

For accomplishing a variety of missions in challenging environments, the capability of navigating with full autonomy while avoiding unexpected obstacles is the most crucial requirement for UAVs in real applications. In this paper, we…

机器人学 · 计算机科学 2020-12-29 Han Chen , Peng Lu

One of the greatest challenges in the design of a real-time perception system for autonomous driving vehicles and drones is the conflicting requirement of safety (high prediction accuracy) and efficiency. Traditional approaches use a single…

计算机视觉与模式识别 · 计算机科学 2018-11-27 Ziyao Tang , Yongxi Lu , Tara Javidi

In this paper, we propose a new Transformer block for video future frames prediction based on an efficient local spatial-temporal separation attention mechanism. Based on this new Transformer block, a fully autoregressive video future…

计算机视觉与模式识别 · 计算机科学 2022-03-31 Xi Ye , Guillaume-Alexandre Bilodeau

This paper addresses the problem of real-time vision-based autonomous obstacle avoidance in unstructured environments for quadrotor UAVs. We assume that our UAV is equipped with a forward facing stereo camera as the only sensor to perceive…

机器人学 · 计算机科学 2020-10-20 Shakeeb Ahmad , Rafael Fierro

Video super-resolution (VSR) has many applications that pose strict causal, real-time, and latency constraints, including video streaming and TV. We address the VSR problem under these settings, which poses additional important challenges…

图像与视频处理 · 电气工程与系统科学 2022-04-07 Dario Fuoli , Martin Danelljan , Radu Timofte , Luc Van Gool

We propose a novel approach for aerial video action recognition. Our method is designed for videos captured using UAVs and can run on edge or mobile devices. We present a learning-based approach that uses customized auto zoom to…

计算机视觉与模式识别 · 计算机科学 2023-07-20 Xijun Wang , Ruiqi Xian , Tianrui Guan , Celso M. de Melo , Stephen M. Nogar , Aniket Bera , Dinesh Manocha

In this paper we propose an effective vision-based navigation method that allows a multirotor vehicle to simultaneously reach a desired goal pose in the environment while constantly facing a target object or landmark. Standard techniques…

机器人学 · 计算机科学 2018-01-26 Ciro Potena , Daniele Nardi , Alberto Pretto

Video super-resolution (VSR) aims to restore a sequence of high-resolution (HR) frames from their low-resolution (LR) counterparts. Although some progress has been made, there are grand challenges to effectively utilize temporal dependency…

图像与视频处理 · 电气工程与系统科学 2022-04-21 Chengxu Liu , Huan Yang , Jianlong Fu , Xueming Qian

We present Recurrent Vision Transformers (RVTs), a novel backbone for object detection with event cameras. Event cameras provide visual information with sub-millisecond latency at a high-dynamic range and with strong robustness against…

计算机视觉与模式识别 · 计算机科学 2023-05-26 Mathias Gehrig , Davide Scaramuzza

En Route Travel Time Estimation (ER-TTE) aims to learn driving patterns from traveled routes to achieve rapid and accurate real-time predictions. However, existing methods ignore the complexity and dynamism of real-world traffic systems,…

机器学习 · 计算机科学 2025-01-28 Zhihan Zheng , Haitao Yuan , Minxiao Chen , Shangguang Wang