Scope Head for Accurate Localization in Object Detection
The University of Sydney（悉尼大学）；SenseTime Computer Vision Research Group（商汤科技计算机视觉研究组）；University of Oxford（牛津大学）；Shanghai Jiao Tong University（上海交通大学）；SenseTime Group Ltd（商汤集团有限公司）；The University of Adelaide（阿德莱德大学）
Existing anchor-based and anchor-free object detectors in multi-stage or one-stage pipelines have achieved very promising detection performance. However, they still encounter the design difficulty in hand-crafted 2D anchor definition and the learning complexity in 1D direct location regression. To tackle these issues, in this paper, we propose a novel detector coined as ScopeNet, which models anchors of each location as a mutually dependent relationship. This approach quantizes the prediction space and employs a coarse-to-fine strategy for localization. It achieves superior flexibility as in the regression based anchor-free methods, while produces more precise prediction. Besides, an inherit anchor selection score is learned to indicate the localization quality of the detection result, and we propose to better represent the confidence of a detection box by combining the category-classification score and the anchor-selection score. With our concise and effective design, the proposed ScopeNet achieves state-of-the-art results on COCO
Two head structures (i.e. fully connected head and convolution head) have been widely used in R-CNN based detectors for classification and localization tasks. However, there is a lack of understanding of how does these two head structures work for these two tasks. To address this issue, we perform a thorough analysis and find an interesting fact that the two head structures have opposite preferences towards the two tasks. Specifically, the fully connected head (fc-head) is more suitable for the classification task, while the convolution head (conv-head) is more suitable for the localization ta…
National University of Defense Technology（国防科技大学）；Technical University of Munich（慕尼黑工业大学）
Classification and localization are two main sub-tasks in object detection. Nonetheless, these two tasks have inconsistent preferences for feature context, i.e., localization expects more boundary-aware features to accurately regress the bounding box, while more semantic context is preferred for object classification. Exsiting methods usually leverage disentangled heads to learn different feature context for each task. However, the heads are still applied on the same input features, which leads to an imperfect balance between classifcation and localization. In this work, we propose a novel Tas…
hutom；Yonsei University College of Medicine（延世大学医学院）
Automated surgical instrument localization is an important technology to understand the surgical process and in order to analyze them to provide meaningful guidance during surgery or surgical index after surgery to the surgeon. We introduce a new dataset that reflects the kinematic characteristics of surgical instruments for automated surgical instrument localization of surgical videos. The hSDB(hutom Surgery DataBase)-instrument dataset consists of instrument localization information from 24 cases of laparoscopic cholecystecomy and 24 cases of robotic gastrectomy. Localization information for…
The complex nature of combining localization and classification in object detection has resulted in the flourished development of methods. Previous works tried to improve the performance in various object detection heads but failed to present a unified view. In this paper, we present a novel dynamic head framework to unify object detection heads with attentions. By coherently combining multiple self-attention mechanisms between feature levels for scale-awareness, among spatial locations for spatial-awareness, and within output channels for task-awareness, the proposed approach significantly im…
In this paper, we propose a deep part-based model (DeePM) for symbiotic object detection and semantic part localization. For this purpose, we annotate semantic parts for all 20 object categories on the PASCAL VOC 2012 dataset, which provides information on object pose, occlusion, viewpoint and functionality. DeePM is a latent graphical model based on the state-of-the-art R-CNN framework, which learns an explicit representation of the object-part configuration with flexible type sharing (e.g., a sideview horse head can be shared by a fully-visible sideview horse and a highly truncated sideview …
A key step to driver safety is to observe the driver's activities with the face being a key step in this process to extracting information such as head pose, blink rate, yawns, talking to passenger which can then help derive higher level information such as distraction, drowsiness, intent, and where they are looking. In the context of driving safety, it is important for the system perform robust estimation under harsh lighting and occlusion but also be able to detect when the occlusion occurs so that information predicted from occluded parts of the face can be taken into account properly. This…
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）
The classification and regression head are both indispensable components to build up a dense object detector, which are usually supervised by the same training samples and thus expected to have consistency with each other for detecting objects accurately in the detection pipeline. In this paper, we break the convention of the same training samples for these two heads in dense detectors and explore a novel supervisory paradigm, termed as Mutual Supervision (MuSu), to respectively and mutually assign training samples for the classification and regression head to ensure this consistency. MuSu def…
University of Basel（巴塞尔大学）；University Hospital Basel（巴塞尔大学医院）；MIAC AG
We present an automated method for localizing an anatomical landmark in three-dimensional medical images. The method combines two recurrent neural networks in a coarse-to-fine approach: The first network determines a candidate neighborhood by analyzing the complete given image volume. The second network localizes the actual landmark precisely and accurately in the candidate neighborhood. Both networks take advantage of multi-dimensional gated recurrent units in their main layers, which allow for high model complexity with a comparatively small set of parameters. We localize the medullopontine …
UniHead: Unifying Multi-Perception for Detection Heads
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；School of Information and Electronics, Beijing Institute of Technology（北京理工大学信息与电子学院）；Durham University（杜伦大学）；Tencent Jarvis Lab（腾讯杰维斯实验室）
Carnegie Mellon University（卡内基梅隆大学）；University of Michigan（密歇根大学）
C. elegans is commonly used in neuroscience for behaviour analysis because of it's compact nervous system with well-described connectivity. Localizing the animal and distinguishing between its head and tail are important tasks to track the worm during behavioural assays and to perform quantitative analyses. We demonstrate a neural network based approach to localize both the head and the tail of the worm in an image. To make empirical results in the paper reproducible and promote open source machine learning based solutions for C. elegans behavioural analysis, we also make our code publicly ava…
Multi-label sentences (text) in the clinical domain result from the rich description of scenarios during patient care. The state-of-theart methods for assertion detection mostly address this task in the setting of a single assertion label per sentence (text). In addition, few rules based and deep learning methods perform negation/assertion scope detection on single-label text. It is a significant challenge extending these methods to address multi-label sentences without diminishing performance. Therefore, we developed a convolutional neural network (CNN) architecture to localize multiple label…
In this paper, we propose a simple yet effective crowd counting and localization network named SCALNet. Unlike most existing works that separate the counting and localization tasks, we consider those tasks as a pixel-wise dense prediction problem and integrate them into an end-to-end framework. Specifically, for crowd counting, we adopt a counting head supervised by the Mean Square Error (MSE) loss. For crowd localization, the key insight is to recognize the keypoint of people, i.e., the center point of heads. We propose a localization head to distinguish dense crowds trained by two loss funct…
Arvalis, Institut du végétal（Arvalis 植物研究所）；INRAE（法国国家农业食品与环境研究院）；The University of Queensland（昆士兰大学）；Hiphen SAS；Nanjing Agricultural University（南京农业大学）；International Maize and Wheat Improvement Centre (CIMMYT)（国际玉米小麦改良中心 (CIMMYT)）；Norwegian University of Life Sciences（挪威生命科学大学）；Agricultural Research Corporation（农业研究公司）；Tottori University（鸟取大学）；Kyoto University（京都大学）；CSIRO Agriculture and Food（澳大利亚联邦科学与工业研究组织农业与食品部）；ETH Zurich（苏黎世联邦理工学院）；Rothamsted Research（洛桑研究所）；National Agriculture and Food Research Organization（日本国家农业和食品研究机构）；University of Liège（列日大学）；The University of Tokyo（东京大学）；University of Saskatchewan（萨斯喀彻温大学）
The Global Wheat Head Detection (GWHD) dataset was created in 2020 and has assembled 193,634 labelled wheat heads from 4,700 RGB images acquired from various acquisition platforms and 7 countries/institutions. With an associated competition hosted in Kaggle, GWHD has successfully attracted attention from both the computer vision and agricultural science communities. From this first experience in 2020, a few avenues for improvements have been identified, especially from the perspective of data size, head diversity and label reliability. To address these issues, the 2020 dataset has been reexami…
Medical University of Vienna（维也纳医科大学）；Carl Zeiss Meditec, Inc.（卡尔蔡司医疗技术公司）
The automatic detection and localization of anatomical features in retinal imaging data are relevant for many aspects. In this work, we follow a data-centric approach to optimize classifier training for optic nerve head detection and localization in optical coherence tomography en face images of the retina. We examine the effect of domain knowledge driven spatial complexity reduction on the resulting optic nerve head segmentation and localization performance. We present a machine learning approach for segmenting optic nerve head in 2D en face projections of 3D widefield swept source optical co…
University of Melbourne（墨尔本大学）；Sun Yat-sen University（中山大学）；SenseTime Group Limited（商汤集团有限公司）；Northwestern Polytechnical University（西北工业大学）；Tsinghua University（清华大学）
Video crowd localization is a crucial yet challenging task, which aims to estimate exact locations of human heads in the given crowded videos. To model spatial-temporal dependencies of human mobility, we propose a multi-focus Gaussian neighborhood attention (GNA), which can effectively exploit long-range correspondences while maintaining the spatial topological structure of the input videos. In particular, our GNA can also capture the scale variation of human heads well using the equipped multi-focus mechanism. Based on the multi-focus GNA, we develop a unified neural network called GNANet to …
All in One: Unifying Deepfake Detection, Tampering Localization, and Source Tracing with a Robust Landmark-Identity Watermark
School of Computer Science and Technology, Xinjiang University, Urumqi, China（新疆大学计算机科学与技术学院）；Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center, Urumqi, China（新疆多模态智能处理与信息安全工程技术研究中心）
Head pose estimation and face alignment constitute a backbone preprocessing for many applications relying on face analysis. While both are closely related tasks, they are generally addressed separately, e.g. by deducing the head pose from the landmark locations. In this paper, we propose to entwine face alignment and head pose tasks inside an attentional cascade. This cascade uses a geometry transfer network for integrating heterogeneous annotations to enhance landmark localization accuracy. Furthermore, we propose a doubly-conditional fusion scheme to select relevant feature maps, and regions…
Huazhong University of Science and Technology（华中科技大学）；Beijing University of Posts and Telecommunications（北京邮电大学）
Crowd localization, predicting head positions, is a more practical and high-level task than simply counting. Existing methods employ pseudo-bounding boxes or pre-designed localization maps, relying on complex post-processing to obtain the head positions. In this paper, we propose an elegant, end-to-end Crowd Localization Transformer named CLTR that solves the task in the regression-based paradigm. The proposed method views the crowd localization as a direct set prediction problem, taking extracted features and trainable embeddings as input of the transformer-decoder. To reduce the ambiguous po…
University of Chinese Academy of Sciences（中国科学院大学）；CASIA（中国科学院自动化研究所）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
The task of Dense Video Captioning (DVC) aims to generate captions with timestamps for multiple events in one video. Semantic information plays an important role for both localization and description of DVC. We present a semantic-assisted dense video captioning model based on the encoding-decoding framework. In the encoding stage, we design a concept detector to extract semantic information, which is then fused with multi-modal visual features to sufficiently represent the input video. In the decoding stage, we design a classification head, paralleled with the localization and captioning heads…
One of the routine examinations that are used for prenatal care in many countries is ultrasound imaging. This procedure provides various information about fetus health and development, the progress of the pregnancy and, the baby's due date. Some of the biometric parameters of the fetus, like fetal head circumference (HC), must be measured to check the fetus's health and growth. In this paper, we investigated the effects of using multi-scale inputs in the network. We also propose a light convolutional neural network for automatic HC measurement. Experimental results on an ultrasound dataset of …
Cochlear implants (CIs) are neural prosthetics which are used to treat patients with hearing loss. CIs use an array of electrodes which are surgically inserted into the cochlea to stimulate the auditory nerve endings. After surgery, CIs need to be programmed. Studies have shown that the spatial relationship between the intra-cochlear anatomy and electrodes derived from medical images can guide CI programming and lead to significant improvement in hearing outcomes. However, clinical head CT images are usually obtained from scanners of different brands with different protocols. The field of view…
HwaMei Hospital, University of Chinese Academy of Sciences（中国科学院大学华美医院）；Ningbo Institute of Life and Health Industry, UCAS（中国科学院大学宁波生命与健康产业研究院）；University of Hong Kong（香港大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Harbin Institute of Technology（哈尔滨工业大学）
In recent years, several works have adopted the convolutional neural network (CNN) to diagnose the avascular necrosis of the femoral head (AVNFH) based on X-ray images or magnetic resonance imaging (MRI). However, due to the tissue overlap, X-ray images are difficult to provide fine-grained features for early diagnosis. MRI, on the other hand, has a long imaging time, is more expensive, making it impractical in mass screening. Computed tomography (CT) shows layer-wise tissues, is faster to image, and is less costly than MRI. However, to our knowledge, there is no work on CT-based automated dia…
Object-level Cross-view Geo-localization with Location Enhancement and Multi-Head Cross Attention
Meitu Inc.（美图公司）；University of Melbourne（墨尔本大学）；Swinburne University of Technology（斯威本技术大学）；The University of Western Australia（西澳大学）；Deakin University（迪金大学）
UBTech Robotics Corp Ltd（优必选机器人股份有限公司）；Shanghaitech University（上海科技大学）；Institute for Infocomm Research（信息通信研究院）
With the emergence of service robots and surveillance cameras, dynamic face recognition (DFR) in wild has received much attention in recent years. Face detection and head pose estimation are two important steps for DFR. Very often, the pose is estimated after the face detection. However, such sequential computations lead to higher latency. In this paper, we propose a low latency and lightweight network for simultaneous face detection, landmark localization and head pose estimation. Inspired by the observation that it is more challenging to locate the facial landmarks for faces with large angle…
Centre for Autonomous Systems, University of Technology, Sydney（悉尼科技大学自主系统中心）；University of Technology, Sydney（悉尼科技大学）
Real-time simultaneously localization and dense mapping is very helpful for providing Virtual Reality and Augmented Reality for surgeons or even surgical robots. In this paper, we propose MIS-SLAM: a complete real-time large scale dense deformable SLAM system with stereoscope in Minimal Invasive Surgery based on heterogeneous computing by making full use of CPU and GPU. Idled CPU is used to perform ORB- SLAM for providing robust global pose. Strategies are taken to integrate modules from CPU and GPU. We solved the key problem raised in previous work, that is, fast movement of scope and blurry …
Currently in the domain of facial analysis single task approaches for face detection and landmark localization dominate. In this paper we draw attention to multi-task models solving both tasks simultaneously. We present a highly accurate model for face and landmark detection. The method, called MaskFace, extends previous face detection approaches by adding a keypoint prediction head. The new keypoint head adopts ideas of Mask R-CNN by extracting facial features with a RoIAlign layer. The keypoint head adds small computational overhead in the case of few faces in the image while improving the a…
Tracing and Mitigating Hallucinations in Multimodal LLMs via Dynamic Attention Localization
MBZUAI；Provable Responsible AI and Data Analytics (PRADA) Lab（可证明负责任的人工智能与数据分析实验室）；King Abdullah University of Science and Technology（卡迪夫大学科学与技术大学）；School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences（中国科学院大学先进交叉科学学院）；University of Copenhagen（哥本哈根大学）；Tsinghua University（清华大学）
Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）；School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）
University of Modena and Reggio Emilia（摩德纳和雷焦艾米利亚大学）
Head detection and localization is a demanding task and a key element for many computer vision applications, like video surveillance, Human Computer Interaction and face analysis. The stunning amount of work done for detecting faces on RGB images, together with the availability of huge face datasets, allowed to setup very effective systems on that domain. However, due to illumination issues, infrared or depth cameras may be required in real applications. In this paper, we introduce a novel method for head detection on depth images that exploits the classification ability of deep learning appro…
SMGeo: Cross-View Object Geo-Localization with Grid-Level Mixture-of-Experts
School of Information Science and Technology（信息科学与技术学院）；Interdisciplinary Research Center for Artificial Intelligence（人工智能交叉研究中心）；Beijing University of Chemical Technology（北京化工大学）
NeuroLoc: Encoding Navigation Cells for 6-DOF Camera Localization
Software Engineering Institute, East China Normal University（华东师范大学软件工程学院）；School of Geospatial Information, Information Engineering University（信息工程大学地理信息学院）；University of Shanghai for Science and Technology（上海科技大学）；Fujian (Quanzhou) Institute of Advanced Manufacturing Technology, China（福建（泉州）先进制造技术研究院）
University of Michigan（密歇根大学）；Capacloud AI（Capacloud人工智能公司）
Objective:Computer vision-based up-to-date accurate damage classification and localization are of decisive importance for infrastructure monitoring, safety, and the serviceability of civil infrastructure. Current state-of-the-art deep learning (DL)-based damage detection models, however, often lack superior feature extraction capability in complex and noisy environments, limiting the development of accurate and reliable object distinction. Method: To this end, we present DenseSPH-YOLOv5, a real-time DL-based high-performance damage detection model where DenseNet blocks have been integrated wit…
