检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Zhenxin Lan, Shiyi Alvarez, Jose M. Wu, Zuxuan Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China NVIDIA United States

Recently, the rise of query-based Transformer decoders is reshaping camera-based 3D object detection. These query-based decoders are surpassing the traditional dense BEV (Bird’s Eye View)-based methods. However, we argue that dense BEV frameworks remain important due to their outstanding abilities in depth estimation and object localization, depicting 3D scenes accurately and comprehensively. This paper aims to address the drawbacks of the existing dense BEV-based 3D object detectors by introducing our proposed enhanced components, including a CRF-modulated depth estimation module enforcing object-level consistencies, a long-term temporal aggregation module with extended receptive fields, and a two-stage object decoder combining perspective techniques with CRF-modulated depth embedding. These enhancements lead to a "modernized" dense BEV framework dubbed BEVNeXt. On the nuScenes benchmark, BEVNeXt outperforms both BEV-based and query-based frameworks under various settings, achieving a state-of-the-art result of 64.2 NDS on the nuScenes test set. Code will be available at https://***/woxihuanjiangguo/BEVNeXt. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

OmniViD: A Generative Framework for Universal Video Understanding

OmniViD: A Generative Framework for Universal Video Understa...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Junke Wang Dongdong Chen Chong Luo Bo He Lu Yuan Zuxuan Wu Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing Microsoft Cloud + AI Microsoft Research Asia University of Maryland College Park

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The core of video understanding tasks, such as recognition, captioning, and tracking, is to automatically de-tect objects or actions in a video and analyze their temporal evolution. Despite sharing a common goal, different tasks often rely on distinct model architectures and annotation formats. In contrast, natural language processing benefits from a unified output space, i.e., text sequences, which simplifies the training of powerful foundational language models, such as GPT-3, with extensive training cor-pora. Inspired by this, we seek to unify the output space of video understanding tasks by using languages as labels and additionally introducing time and box tokens. In this way, a variety of video tasks could be formulated as video-grounded token generation. This enables us to address var-ious types of video tasks, including classification (such as action recognition), captioning (covering clip captioning, video question answering, and dense video captioning), and localization tasks (such as visual object tracking) within a fully shared encoder-decoder architecture, following a generative framework. Through comprehensive experiments, we demonstrate such a simple and straightforward idea is quite effective and can achieve state-of-the-art or compet-itive results on seven video benchmarks, providing a novel perspective for more universal video understanding. Code is available at https://***/wangjk666/OmniVid.

关键词： Training Location awareness visualization Vocabulary Computer architecture Benchmark testing Robustness

来源：评论

学校读者我要写书评

暂无评论

ResFormer: Scaling ViTs with Multi-Resolution Training

ResFormer: Scaling ViTs with Multi-Resolution Training

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Rui Tian Zuxuan Wu Qi Dai Han Hu Yu Qiao Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing Microsoft Research Asia Shanghai AI Laboratory

Vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with input resolutions that are unseen during training. We introduce, ResFormer, a framework that is built upon the seminal idea of multi-resolution training for improved performance on a wide spectrum of, mostly unseen, testing resolutions. In particular, ResFormer operates on replicated images of different resolutions and enforces a scale consistency loss to engage interactive information across different scales. More importantly, to alternate among varying resolutions effectively, especially novel ones in testing, we propose a global-local positional embedding strategy that changes smoothly conditioned on input sizes. We conduct extensive experiments for image classification on ImageNet. The results provide strong quantitative evidence that ResFormer has promising scaling abilities towards a wide range of resolutions. For instance, ResFormer-B-MR achieves a Top-1 accuracy of 75.86% and 81.72% when evaluated on relatively low and high resolutions respectively (i.e., 96 and 640), which are 48% and 7.49% better than DeiT-B. We also demonstrate, moreover, ResFormer is flexible and can be easily extended to semantic segmentation, object detection and video action recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prototypical Residual Networks for Anomaly Detection and Localization

Prototypical Residual Networks for Anomaly Detection and Loc...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Hui Zhang Zuxuan Wu Zheng Wang Zhineng Chen Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing School of Computer Science Zhejiang University of Technology

Anomaly detection and localization are widely used in industrial manufacturing for its efficiency and effectiveness. Anomalies are rare and hard to collect and supervised models easily over-fit to these seen anomalies with a handful of abnormal samples, producing unsatisfactory performance. On the other hand, anomalies are typically subtle, hard to discern, and of various appearance, making it difficult to detect anomalies and let alone locate anomalous regions. To address these issues, we propose a framework called Prototypical Residual Network (PRN), which learns feature residuals of varying scales and sizes between anomalous and normal patterns to accurately reconstruct the segmentation maps of anomalous regions. PRN mainly consists of two parts: multi-scale prototypes that explicitly represent the residual features of anomalies to normal patterns; a multisize self-attention mechanism that enables variable-sized anomalous feature learning. Besides, we present a variety of anomaly generation strategies that consider both seen and unseen appearance variance to enlarge and diversify anomalies. Extensive experiments on the challenging and widely used MVTec AD benchmark show that PRN outperforms current state-of-the-art unsupervised and supervised methods. We further report SOTA results on three additional datasets to demonstrate the effectiveness and generalizability of PRN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Split-Fusion Transformer

Adaptive Split-Fusion Transformer

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zixuan Su Jingjing Chen Lei Pang Chong-Wah Ngo Yu-Gang Jiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing City University of Hong Kong Singapore Management University

Neural networks for visual content understanding have recently evolved from convolutional ones to transformers. The prior (CNN) relies on small-windowed kernels to capture the regional clues, demonstrating solid local expressiveness. On the contrary, the latter (transformer) establishes long-range global connections between localities for holistic learning. Inspired by this complementary nature, there is a growing interest in designing hybrid models which utilize both techniques. Current hybrids merely replace convolutions as simple approximations of linear projection or juxtapose a convolution branch with attention without considering the importance of local/global modeling. To tackle this, we propose a new hybrid named Adaptive Split-Fusion Transformer (ASF-former) that treats convolutional and attention branches differently with adaptive weights. Specifically, an ASF-former encoder equally splits feature channels into half to fit dual-path inputs. Then, the outputs of the dual-path are fused with weights calculated from visual cues. We also design a compact convolutional path from a concern of efficiency. Extensive experiments on standard benchmarks show that our ASF-former outperforms its CNN, transformer, and hybrid counterparts in terms of accuracy (83.9% on ImageNet-1K), under similar conditions (12.9G MACs / 56.7M Params, without large-scale pre-training). The code is available at: https://***/szx503045266/ASF-former.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Look Before You Match: Instance Understanding Matters in Video Object Segmentation

Look Before You Match: Instance Understanding Matters in Vid...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Junke Wang Dongdong Chen Zuxuan Wu Chong Luo Chuanxin Tang Xiyang Dai Yucheng Zhao Yujia Xie Lu Yuan Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing Microsoft Cloud + AI Microsoft Research Asia

Exploring dense matching between the current frame and past frames for long-range context modeling, memory-based methods have demonstrated impressive results in video object segmentation (VOS) recently. Nevertheless, due to the lack of instance understanding ability, the above approaches are oftentimes brittle to large appearance variations or viewpoint changes resulted from the movement of objects and cameras. In this paper, we argue that instance understanding matters in VOS, and integrating it with memory-based matching can enjoy the synergy, which is intuitively sensible from the definition of VOS task, i.e., identifying and segmenting object instances within the video. Towards this goal, we present a two-branch network for VOS, where the query-based instance segmentation (IS) branch delves into the instance details of the current frame and the VOS branch performs spatial-temporal matching with the memory bank. We employ the well-learned object queries from IS branch to inject instance-specific information into the query key, with which the instance-augmented matching is further performed. In addition, we introduce a multi-path fusion block to effectively combine the memory readout with multi-scale features from the instance segmentation decoder, which incorporates high-resolution instance-aware features to produce final segmentation results. Our method achieves state-of-the-art performance on DAVIS 2016/2017 val (92.6% and 87.1%), DAVIS 2017 test-dev (82.8%), and YouTube-VOS 2018/2019 val (86.3% and 86.3%), outperforming alternative methods by clear margins.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implicit Temporal Modeling with Learnable Alignment for Video Recognition

Implicit Temporal Modeling with Learnable Alignment for Vide...

引用

International Conference on Computer Vision (ICCV)

作者： Shuyuan Tu Qi Dai Zuxuan Wu Zhi-Qi Cheng Han Hu Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing Microsoft Research Asia Carnegie Mellon University

Contrastive language-image pretraining (CLIP) has demonstrated remarkable success in various image tasks. However, how to extend CLIP with effective temporal modeling is still an open and crucial problem. Existing factorized or joint spatial-temporal modeling trades off between the efficiency and performance. While modeling temporal information within straight through tube is widely adopted in literature, we find that simple frame alignment already provides enough essence without temporal attention. To this end, in this paper, we proposed a novel Implicit Learnable Alignment (ILA) method, which minimizes the temporal modeling effort while achieving incredibly high performance. Specifically, for a frame pair, an interactive point is predicted in each frame, serving as a mutual information rich region. By enhancing the features around the interactive point, two frames are implicitly aligned. The aligned features are then pooled into a single token, which is leveraged in the subsequent spatial self-attention. Our method allows eliminating the costly or insufficient temporal self-attention in video. Extensive experiments on benchmarks demonstrate the superiority and generality of our module. Particularly, the proposed ILA achieves a top-1 accuracy of 88.7% on Kinetics-400 with much fewer FLOPs compared with Swin-L and ViViT-H. Code is released at https://***/Francis-Rings/ILA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Utilizing the Neglected Back Lobe for Mobile Charging

Utilizing the Neglected Back Lobe for Mobile Charging

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Meixuan Ren Dié Wu Jing Xue Wenzheng Xu Jian Peng Tang Liu College of Computer Science Sichuan Normal University Chengdu China Visual Computing and Virtual Reality Key Lab Sichuan Normal University Chengdu China College of Computer Science Sichuan University Chengdu China

Benefitting from the breakthrough of wireless power transfer technology, the lifetime of Wireless Sensor Networks (WSNs) can be significantly prolonged by scheduling a mobile charger (MC) to charge sensors. Compared with omnidirectional charging, the MC equipped with directional antenna can concentrate energy in the intended direction, making charging more efficient. However, all prior arts ignore the considerable energy leakage behind the directional antenna (i.e., back lobe), resulting in energy wasted in vain. To address this issue, we study a fundamental problem of how to utilize the neglected back lobe and schedule the directional MC efficiently. Towards this end, we first build and verify a directional charging model considering both main and back lobes. Then, we focus on jointly optimizing the number of dead sensors and energy usage effectiveness. We achieve these by introducing a scheduling scheme that utilizes both main and back lobes to charge multiple sensors simultaneously. Finally, extensive simulations and field experiments demonstrate that our scheme reduces the number of dead sensors by 49.5% and increases the energy usage effectiveness by 10.2% on average as compared with existing algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DronePose: Photorealistic UAV-Assistant Dataset Synthesis for 3D Pose Estimation via a Smooth Silhouette Loss 16th

DronePose: Photorealistic UAV-Assistant Dataset Synthesis fo...

引用

Workshops held at the 16th European Conference on Computer Vision, ECCV 2020

作者： Albanis, Georgios Zioulis, Nikolaos Dimou, Anastasios Zarpalas, Dimitrios Daras, Petros Visual Computing Lab Information Technologies Institute Centre for Research and Technology Hellas Thessaloniki Greece

ISBN: (纸本)9783030660956

In this work we consider UAVs as cooperative agents supporting human users in their operations. In this context, the 3D localisation of the UAV assistant is an important task that can facilitate the exchange of spatial information between the user and the UAV. To address this in a data-driven manner, we design a data synthesis pipeline to create a realistic multimodal dataset that includes both the exocentric user view, and the egocentric UAV view. We then exploit the joint availability of photorealistic and synthesized inputs to train a single-shot monocular pose estimation model. During training we leverage differentiable rendering to supplement a state-of-the-art direct regression objective with a novel smooth silhouette loss. Our results demonstrate its qualitative and quantitative performance gains over traditional silhouette objectives. Our data and code are available at https://***/DronePose. © 2020, Springer Nature Switzerland AG.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Achieving Efficient and Realistic Full-Radar Simulations and Automatic Data Annotation by exploiting Ray Meta Data of a Radar Ray Tracing Simulator

arXiv

引用

arXiv 2023年

作者： Schüßler, Christian Hoffmann, Marcel Wirth, Vanessa Eskofier, Björn Weyrich, Tim Stamminger, Marc Vossiek, Martin Institute of Microwaves and Photonics Germany Chair of Visual Computing Germany Chair of Digital Reality Germany Machine Learning and Data Analytics Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany

In this work a novel radar simulation concept is introduced that allows to simulate realistic radar data for Range, Doppler, and for arbitrary antenna positions in an efficient way. Further, it makes it possible to automatically annotate the simulated radar signal by allowing to decompose it into different parts. This approach allows not only almost perfect annotations possible, but also allows the annotation of exotic effects, such as multi-path effects or to label signal parts originating from different parts of an object. This is possible by adapting the computation process of a Monte Carlo shooting and bouncing rays (SBR) simulator. By considering the hits of each simulated ray, various meta data can be stored such as hit position, mesh pointer, object IDs, and many more. This collected meta data can then be utilized to predict the change of path lengths introduced by object motion to obtain Doppler information or to apply specific ray filter rules in order obtain radar signals that only fulfil specific conditions, such as multiple bounces or containing specific object IDs. Using this approach, perfect and otherwise almost impossible annotations schemes can be realized. Copyright © 2023, The Authors. All rights reserved.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：