检索结果-内蒙古大学图书馆

作者： Uranishi, Yuki Ideguchi, Yuta Cybermedia Center Osaka University Osaka Japan NEC Corporation Tokyo Japan

暂无评论

Deep Audio-Visual Speech recognition

ieee TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 2022年第12期44卷 8717-8727页

作者： Afouras, Triantafyllos Chung, Joon Son Senior, Andrew Vinyals, Oriol Zisserman, Andrew Univ Oxford Oxford OX1 2JD England Google DeepMind London N1C 4AG England

the goal of this work is to recognise phrases and sentences being spoken by a talking face, with or without the audio. Unlike previous works that have focussed on recognising a limited number of words or phrases, we tackle lip reading as an open-world problem - unconstrained natural language sentences, and in the wild videos. Our key contributions are: (1) we compare two models for lip reading, one using a CTC loss, and the other using a sequence-to-sequence loss. Both models are built on top of the transformer self-attention architecture;(2) we investigate to what extent lip reading is complementary to audio speech recognition, especially when the audio signal is noisy;(3) we introduce and publicly release a new dataset for audio-visual speech recognition, LRS2-BBC, consisting of thousands of natural sentences from British television. the models that we train surpass the performance of all previous work on a lip reading benchmark dataset by a significant margin.

关键词： Hidden Markov models Lips Speech recognition Visualization Videos Feeds Training Lip reading audio visual speech recognition deep learning

来源：评论

学校读者我要写书评

暂无评论

ABAW: Valence-Arousal Estimation, Expression recognition, Action Unit Detection & Emotional Reaction Intensity Estimation Challenges

ABAW: Valence-Arousal Estimation, Expression Recognition, Ac...

引用

2023 ieee/CVF conference on computer vision and pattern recognition Workshops, cvprW 2023

作者： Kollias, Dimitrios Tzirakis, Panagiotis Baird, Alice Cowen, Alan Zafeiriou, Stefanos Queen Mary University of London United Kingdom Hume AI United States Imperial College London United Kingdom

ISBN: (纸本)9798350302493

the 5th ABAW Competition is part of the respective Workshop held in conjunction with ieee cvpr 2023 and is a continuation of the Competitions held at ECCV 2022, ieee cvpr 2022, ICCV 2021, ieee FG 2020 and cvpr 2017 conferences. It is dedicated at automatically analyzing affect. For this year's Competition, we feature two corpora: i) an extended version of the Aff-Wild2 database and ii) the Hume-Reaction dataset. the former database is an audiovisual (A/V) one of around 600 videos of around 3M frames and is annotated for: a) two continuous affect dimensions, valence (how positive/negative a person is) and arousal (how active/passive a person is);b) basic expressions (e.g. happiness, neutral);and c) action units (i.e., facial muscle actions). the latter dataset is A/V in which reactions of individuals to emotional stimuli have been annotated for seven emotional expression intensities. thus the 5th ABAW Competition encompasses four Challenges: i) Valence-Arousal Estimation, ii) Expression Classification, iii) Action Unit Detection, and iv) Emotional Reaction Intensity Estimation. In this paper, we present these Challenges and their corpora, we outline the evaluation metrics and present the baseline systems and top performing teams' per Challenge along with their obtained performance. More information for the Competition can be found in: https://***/resources/ cvpr-2023-5th-abaw. © 2023 ieee.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?

Noisy Boundaries: Lemon or Lemonade for Semi-supervised Inst...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Wang, Zhenyu Li, Yali Wang, Shengjin Tsinghua Univ Beijing Natl Res Ctr Informat Sci & Technol BNRis Dept Elect Engn Beijing Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Current instance segmentation methods rely heavily on pixel-level annotated images. the huge cost to obtain such fully-annotated images restricts the dataset scale and limits the performance. In this paper, we formally address semi-supervised instance segmentation, where unlabeled images are employed to boost the performance. We construct a framework for semi-supervised instance segmentation by assigning pixel-level pseudo labels. Under this framework, we point out that noisy boundaries associated with pseudo labels are double-edged. We propose to exploit and resist them in a unified manner simultaneously: 1) To combat the negative effects of noisy boundaries, we propose a noise-tolerant mask head by leveraging low-resolution features. 2) To enhance the positive impacts, we introduce a boundary-preserving map for learning detailed information within boundary-relevant regions. We evaluate our approach by extensive experiments. It behaves extraordinarily, outperforming the supervised baseline by a large margin, more than 6% on Cityscapes, 7% on COCO and 4.5% on BDD100k. On Cityscapes, our method achieves comparable performance by utilizing only 30% labeled images.

关键词： Training Image segmentation computer vision Head Costs Resists pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Opening up Open World Tracking

Opening up Open World Tracking

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Liu, Yang Zulfikar, Idil Esen Luiten, Jonathon Dave, Achal Ramanan, Deva Leibe, Bastian Osep, Aljosa Leal-Taixe, Laura Tech Univ Munich Munich Germany Rhein Westfal TH Aachen Aachen Germany Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Tracking and detecting any object, including ones never-seen-before during model training, is a crucial but elusive capability of autonomous systems. An autonomous agent that is blind to never-seen-before objects poses a safety hazard when operating in the real world - and yet this is how almost all current systems work. One of the main obstacles towards advancing tracking any object is that this task is notoriously difficult to evaluate. A benchmark that would allow us to perform an apples-to-apples comparison of existing efforts is a crucial first step towards advancing this important research field. this paper addresses this evaluation deficit and lays out the landscape and evaluation methodology for detecting and tracking both known and unknown objects in the open-world setting. We propose a new benchmark, TAO-OW: Tracking Any Object in an Open World, analyze existing efforts in multi-object tracking, and construct a baseline for this task while highlighting future challenges. We hope to open a new front in multi-object tracking research that will hopefully bring us a step closer to intelligent systems that can operate safely in the real world.

关键词： Training Heart computer vision Autonomous systems Benchmark testing Hazards pattern recognition

来源：评论

学校读者我要写书评

暂无评论

OSKDet: Orientation-sensitive Keypoint Localization for Rotated Object Detection

OSKDet: Orientation-sensitive Keypoint Localization for Rota...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Lu, Dongchen Li, Dongmei Li, Yali Wang, Shengjin Tsinghua Univ Dept Elect Engn Beijing Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Rotated object detection is a challenging issue in computer vision field. Inadequate rotated representation and the confusion of parametric regression have been the bottleneck for high performance rotated detection. In this paper, we propose an orientation-sensitive keypoint based rotated detector OSKDet. First, we adopt a set of keypoints to represent the target and predict the keypoint heatmap on ROI to get the rotated box. By proposing the orientation-sensitive heatmap, OSKDet could learn the shape and direction of rotated target implicitly and has stronger modeling capabilities for rotated representation, which improves the localization accuracy and acquires high quality detection results. Second, we explore a new unordered keypoint representation paradigm, which could avoid the confusion of keypoint regression caused by rule based ordering. Furthermore, we propose a localization quality uncertainty module to better predict the classification score by the distribution uncertainty of keypoints heatmap. Experimental results on several public benchmarks show the state-of-the-art performance of OSKDet. Specifically, we achieve an AP of 80.91% on DOTA, 89.98% on HRSC2016, 97.27% on UCAS-AOD, and a F-measure of 92.18% on ICDAR2015, 81.43% on ICDAR2017, respectively.

关键词： Location awareness Heating systems computer vision Uncertainty Shape Object detection Detectors

来源：评论

学校读者我要写书评

暂无评论

HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images

HODOR: High-level Object Descriptors for Object Re-segmentat...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Athar, Ali Luiten, Jonathon Hermans, Alexander Ramanan, Deva Leibe, Bastian Rhein Westfal TH Aachen Aachen Germany Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Existing state-of-the-art methods for Video Object Segmentation (VOS) learn low-level pixel-to-pixel correspondences between frames to propagate object masks across video. this requires a large amount of densely annotated video data, which is costly to annotate, and largely redundant since frames within a video are highly correlated. In light of this, we propose HODOR: a novel method that tackles VOS by effectively leveraging annotated static images for understanding object appearance and scene context. We encode object instances and scene information from an image frame into robust high-level descriptors which can then be used to re-segment those objects in different frames. As a result, HODOR achieves state-of-the-art performance on the DAVIS and YouTube-VOS benchmarks compared to existing methods trained without video annotations. With out any architectural modification, HODOR can also learn from video context around single annotated video frames by utilizing cyclic consistency, whereas other methods rely on dense, temporally consistent annotations. Source code: https://***/Ali2500/HODOR.

关键词： Training computer vision Image coding Codes Annotations Image annotation Object segmentation

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Auto-Encoders for Self-supervised Representation Learning

Semantic-Aware Auto-Encoders for Self-supervised Representat...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Wang, Guangrun Tang, Yansong Lin, Liang Torr, Philip H. S. Univ Oxford Oxford England Tsinghua Univ Tsinghua Berkeley Shenzhen Inst Shenzhen Peoples R China Sun Yat Sen Univ Guangzhou Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

the resurgence of unsupervised learning can be attributed to the remarkable progress of self-supervised learning, which includes generative (G) and discriminative (D) models. In computer vision, the mainstream self-supervised learning algorithms areD models. However, designing aD model could be over-complicated;also, some studies hinted that a D model might not be as general and interpretable as a G model. In this paper, we switch from D models to G models using the classical auto-encoder (AE). Note that a vanilla G model was far less efficient than a D model in self-supervised computer vision tasks, as it wastes model capability on overfitting semantic-agnostic high-frequency details. Inspired by perceptual learning that could use cross-view learning to perceive concepts and semantics1, we propose a novel AE that could learn semantic-aware representation via cross-view image reconstruction. We use one view of an image as the input and another view of the same image as the reconstruction target. this kind of AE has rarely been studied before, and the optimization is very difficult. To enhance learning ability and find a feasible solution, we propose a semantic aligner that uses geometric transformation knowledge to align the hidden code of AE to help optimization. these techniques significantly improve the representation learning ability of AE and make selfsupervised learning with G models possible. Extensive experiments on many large-scale benchmarks (e.g., ImageNet, COCO 2017, and SYSU-30k) demonstrate the effectiveness of our methods. Code is available at https://github. com/wanggrun/Semantic-Aware- AE.

关键词： Representation learning computer vision Visualization Codes Computational modeling Semantics Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos

SoccerNet-Tracking: Multiple Object Tracking Dataset and Ben...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Cioppa, Anthony Giancola, Silvio Deliege, Adrien Kang, Le Zhou, Xin Cheng, Zhiyu Ghanem, Bernard Van Droogenbroeck, Marc Univ Liege Liege Belgium KAUST Thuwal Saudi Arabia Baidu Res Beijing Peoples R China

ISBN: (纸本)9781665487399

Tracking objects in soccer videos is extremely important to gather both player and team statistics, whether it is to estimate the total distance run, the ball possession or the team formation. Video processing can help automating the extraction of those information, without the need of any invasive sensor, hence applicable to any team on any stadium. Yet, the availability of datasets to train learnable models and benchmarks to evaluate methods on a common testbed is very limited. In this work, we propose a novel dataset for multiple object tracking composed of 200 sequences of 30s each, representative of challenging soccer scenarios, and a complete 45-minutes half-time for long-term tracking. the dataset is fully annotated with bounding boxes and tracklet IDs, enabling the training of MOT baselines in the soccer domain and a full benchmarking of those methods on our segregated challenge sets. Our analysis shows that multiple player, referee and ball tracking in soccer videos is far from being solved, with several improvement required in case of fast motion or in scenarios of severe occlusion.

关键词： Training computer vision conferences Benchmark testing Object tracking Data mining Sports

来源：评论

学校读者我要写书评

暂无评论

vision-Based Human Activity recognition Utilizing DCNN and Stacked Multi-stage Multimodal Fusion Strategy 30

Vision-Based Human Activity Recognition Utilizing DCNN and S...

引用

30th International conference on Mechatronics and Machine vision in Practice, M2VIP 2024

作者： Zhu, Wenqin Meng, Wei Peng, Nian Chen, Kun Liu, Quan Wuhan University of Technology School of Information Engineering Wuhan China

ISBN: (纸本)9798350391916

Human Activity recognition (HAR) possesses significant potential in pattern recognition, machine learning, wearable computing, computer vision, and notably in rehabilitation assistance. With the ability to automatically track patients' recovery progress, it addresses the issue of insufficient human resources. Presently, improving recognition accuracy hinges on the fusion of multiple information sources like physiological signals, motion sensors, and visual sensors. In this study, a multi-stage multimodal fusion strategy based on stacked integration with Deep Convolutional Neural Network (DCNN) is proposed. Firstly, the inertial sensor and depth sensor data are converted into image data, and the data enhancement method is used to extract edge information using Prewitt, and features are extracted and spliced by the DCNN to realize multimodality at the feature layer. At the decision layer, the two unimodal decisions are fused using the stacking fusion strategy to obtain the final classification decision. the experimental results show that this strategy exhibits significant advantages in human motion recognition, with accuracy rates of 99.85% and 99.51% on Kinect V2 and UTD-MHAD datasets, respectively, exceeding the state-of-the-art deep learning methods on the same dataset. © 2024 ieee.

关键词： Convolutional neural networks

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：