Video object detection is challenging in the presence of appearance deterioration in certain video frames. Therefore, it is a natural choice to aggregate temporal information from other frames of the same video into the current frame. However, RoI Align, as one of the most core procedures of video detectors, still remains extracting features from a single-frame feature map for proposals, making the extracted RoI features lack temporal information from videos. In this work, considering the features of the same object instance are highly similar among frames in a video, a novel Temporal RoI Align operator is proposed to extract features from other frames feature maps for current frame proposals by utilizing feature similarity. The proposed Temporal RoI Align operator can extract temporal information from the entire video for proposals. We integrate it into single-frame video detectors and other state-of-the-art video detectors, and conduct quantitative experiments to demonstrate that the proposed Temporal RoI Align operator can consistently and significantly boost the performance. Besides, the proposed Temporal RoI Align can also be applied into video instance segmentation. Codes are available at https://github.com/open-mmlab/mmtracking
US Army Research Laboratory（美国陆军研究实验室）；Booz Allen Hamilton Inc.（博思艾伦汉密尔顿公司）
We present a novel event recognition approach called Spatially-preserved Doubly-injected Object Detection CNN (S-DOD-CNN), which incorporates the spatially preserved object detection information in both a direct and an indirect way. Indirect injection is carried out by simply sharing the weights between the object detection modules and the event recognition module. Meanwhile, our novelty lies in the fact that we have preserved the spatial information for the direct injection. Once multiple regions-of-intereset (RoIs) are acquired, their feature maps are computed and then projected onto a spati…
Object detection in aerial images is an active yet challenging task in computer vision because of the birdview perspective, the highly complex backgrounds, and the variant appearances of objects. Especially when detecting densely packed objects in aerial images, methods relying on horizontal proposals for common object detection often introduce mismatches between the Region of Interests (RoIs) and objects. This leads to the common misalignment between the final object classification confidence and localization accuracy. Although rotated anchors have been used to tackle this problem, the design…
University of Chinese Academy of Sciences（中国科学院大学）；Center for Research on Intelligent Perception and Computing, CASIA（中国科学院自动化研究所智能感知与计算研究中心）；TuSimple（图森未来）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）
Recently, one-stage object detectors gain much attention due to their simplicity in practice. Its fully convolutional nature greatly reduces the difficulty of training and deployment compared with two-stage detectors which require NMS and sorting for the proposal stage. However, a fundamental issue lies in all one-stage detectors is the misalignment between anchor boxes and convolutional features, which significantly hinders the performance of one-stage detectors. In this work, we first reveal the deep connection between the widely used im2col operator and the RoIAlign operator. Guided by this…
We propose a simple yet effective instance segmentation framework, termed CondInst (conditional convolutions for instance segmentation). Top-performing instance segmentation methods such as Mask R-CNN rely on ROI operations (typically ROIPool or ROIAlign) to obtain the final instance masks. In contrast, we propose to solve instance segmentation from a new perspective. Instead of using instance-wise ROIs as inputs to a network of fixed weights, we employ dynamic instance-aware networks, conditioned on instances. CondInst enjoys two advantages: 1) Instance segmentation is solved by a fully convo…
Monocular 3D object detection is one of the most challenging tasks in 3D scene understanding. Due to the ill-posed nature of monocular imagery, existing monocular 3D detection methods highly rely on training with the manually annotated 3D box labels on the LiDAR point clouds. This annotation process is very laborious and expensive. To dispense with the reliance on 3D box labels, in this paper we explore the weakly supervised monocular 3D detection. Specifically, we first detect 2D boxes on the image. Then, we adopt the generated 2D boxes to select corresponding RoI LiDAR points as the weak sup…
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）；Megvii Research Nanjing, Megvii Technology（旷视科技南京研究院）
State-of-the-art two-stage object detectors apply a classifier to a sparse set of object proposals, relying on region-wise features extracted by RoIPool or RoIAlign as inputs. The region-wise features, in spite of aligning well with the proposal locations, may still lack the crucial context information which is necessary for filtering out noisy background detections, as well as recognizing objects possessing no distinctive appearances. To address this issue, we present a simple but effective Hierarchical Context Embedding (HCE) framework, which can be applied as a plug-and-play component, to f…
We explore object detection with two attributes: color and material. The task aims to simultaneously detect objects and infer their color and material. A straight-forward approach is to add attribute heads at the very end of a usual object detection pipeline. However, we observe that the two goals are in conflict: Object detection should be attribute-independent and attributes be largely object-independent. Features computed by a standard detection network entangle the category and attribute features; we disentangle them by the use of a two-stream model where the category and attribute feature…
Zhejiang University（浙江大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Inception Institute of Artificial Intelligence（Inception人工智能研究院）
In this paper, we present an Intersection-over-Union (IoU) guided two-stage 3D object detector with a voxel-to-point decoder. To preserve the necessary information from all raw points and maintain the high box recall in voxel based Region Proposal Network (RPN), we propose a residual voxel-to-point decoder to extract the point features in addition to the map-view features from the voxel based RPN. We use a 3D Region of Interest (RoI) alignment to crop and align the features with the proposal boxes for accurately perceiving the object position. The RoI-Aligned features are finally aggregated wi…
School of Automation, Beijing Institute of Technology（北京理工大学自动化学院）
Oriented object detection in remote sensing images has made great progress in recent years. However, most of the current methods only focus on detecting targets, and cannot distinguish fine-grained objects well in complex scenes. In this technical report, we analyzed the key issues of fine-grained object recognition, and use an oriented feature alignment network (OFA-Net) to achieve high-performance fine-grained oriented object recognition in optical remote sensing images. OFA-Net achieves accurate object localization through a rotated bounding boxes refinement module. On this basis, the bound…
Convolutional neural networks have emerged as the leading method for the classification and segmentation of images. In some cases, it is desirable to focus the attention of the net on a specific region in the image; one such case is the recognition of the contents of transparent vessels, where the vessel region in the image is already known. This work presents a valve filter approach for focusing the attention of the net on a region of interest (ROI). In this approach, the ROI is inserted into the net as a binary map. The net uses a different set of convolution filters for the ROI and backgrou…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
Image classification, which classifies images by pre-defined categories, has been the dominant approach to visual representation learning over the last decade. Visual learning through image-text alignment, however, has emerged to show promising performance, especially for zero-shot recognition. We believe that these two learning tasks are complementary, and suggest combining them for better visual learning. We propose a deep fusion method with three adaptations that effectively bridge two learning tasks, rather than shallow fusion through naive multi-task learning. First, we modify the previou…
The University of Adelaide（阿德莱德大学）；Meituan Inc.（美团公司）；Zhejiang University（浙江大学）
We propose a simple yet effective framework for instance and panoptic segmentation, termed CondInst (conditional convolutions for instance and panoptic segmentation). In the literature, top-performing instance segmentation methods typically follow the paradigm of Mask R-CNN and rely on ROI operations (typically ROIAlign) to attend to each instance. In contrast, we propose to attend to the instances with dynamic conditional convolutions. Instead of using instance-wise ROIs as inputs to the instance mask head of fixed weights, we design dynamic instance-aware mask heads, conditioned on the insta…
Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences（中国科学院智能信息处理重点实验室）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Recent advances in deep learning have heightened interest among researchers in the field of visual speech recognition (VSR). Currently, most existing methods equate VSR with automatic lip reading, which attempts to recognise speech by analysing lip motion. However, human experience and psychological studies suggest that we do not always fix our gaze at each other's lips during a face-to-face conversation, but rather scan the whole face repetitively. This inspires us to revisit a fundamental yet somehow overlooked problem: can VSR models benefit from reading extraoral facial regions, i.e. beyon…
Video action detection approaches usually conduct actor-centric action recognition over RoI-pooled features following the standard pipeline of Faster-RCNN. In this work, we first empirically find the recognition accuracy is highly correlated with the bounding box size of an actor, and thus higher resolution of actors contributes to better performance. However, video models require dense sampling in time to achieve accurate recognition. To fit in GPU memory, the frames to backbone network must be kept low-resolution, resulting in a coarse feature map in RoI-Pooling layer. Thus, we revisit RCNN …
ShanghaiTech University（上海科技大学）；Megvii Technology（旷视科技）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程技术研究中心）；Shanghai Institute of Microsystem and Information Technology（上海微系统与信息技术研究所）
Despite the recent success of deep neural networks, it remains challenging to effectively model the long-tail class distribution in visual recognition tasks. To address this problem, we first investigate the performance bottleneck of the two-stage learning framework via ablative study. Motivated by our discovery, we propose a unified distribution alignment strategy for long-tail visual recognition. Specifically, we develop an adaptive calibration function that enables us to adjust the classification scores for each data point. We then introduce a generalized re-weight method in the two-stage l…
National University of Singapore（新加坡国立大学）；University of Bonn（波恩大学）
Modeling the visual changes that an action brings to a scene is critical for video understanding. Currently, CNNs process one local neighbourhood at a time, thus contextual relationships over longer ranges, while still learnable, are indirect. We present TROI, a plug-and-play module for CNNs to reason between mid-level feature representations that are otherwise separated in space and time. The module relates localized visual entities such as hands and interacting objects and transforms their corresponding regions of interest directly in the feature maps of convolutional layers. With TROI, we a…
Hikvision Research Institute（海康威视研究院）；Zhejiang University（浙江大学）
In facial action unit (AU) recognition tasks, regional feature learning and AU relation modeling are two effective aspects which are worth exploring. However, the limited representation capacity of regional features makes it difficult for relation models to embed AU relationship knowledge. In this paper, we propose a novel multi-level adaptive ROI and graph learning (MARGL) framework to tackle this problem. Specifically, an adaptive ROI learning module is designed to automatically adjust the location and size of the predefined AU regions. Meanwhile, besides relationship between AUs, there exis…
Shaheed Bhagat Singh College of Engineering & Technology（沙希德·巴加特·辛格工程技术学院）
Human Computer Interaction (HCI) is the biggest goal of computer vision researchers. Features form the different facial images are able to provide a very deep knowledge about the activities performed by the different facial movements. In this paper we presented a technique for feature extraction from various regions of interest with the help of Skin color segmentation technique, Thresholding, knowledge based technique for face recognition.
A fingerprint region of interest (roi) segmentation algorithm is designed to separate the foreground fingerprint from the background noise. All the learning based state-of-the-art fingerprint roi segmentation algorithms proposed in the literature are benchmarked on scenarios when both training and testing databases consist of fingerprint images acquired from the same sensors. However, when testing is conducted on a different sensor, the segmentation performance obtained is often unsatisfactory. As a result, every time a new fingerprint sensor is used for testing, the fingerprint roi segmentati…
Queensland University of Technology（昆士兰科技大学）；Monash University（莫纳什大学）
We present a novel learning framework for vehicle recognition from a single RGB image. Unlike existing methods which only use attention mechanisms to locate 2D discriminative information, our work learns a novel 3D perspective feature representation of a vehicle, which is then fused with 2D appearance feature to predict the category. The framework is composed of a global network (GN), a 3D perspective network (3DPN), and a fusion network. The GN is used to locate the region of interest (RoI) and generate the 2D global feature. With the assistance of the RoI, the 3DPN estimates the 3D bounding …
University of New South Wales（新南威尔士大学）；The Commonwealth Scientific and Industrial Research Organisation (CSIRO)（联邦科学与工业研究组织（CSIRO））
Coronavirus Disease 2019 (COVID-19) has spread globally and become a health crisis faced by humanity since first reported. Radiology imaging technologies such as computer tomography (CT) and chest X-ray imaging (CXR) are effective tools for diagnosing COVID-19. However, in CT and CXR images, the infected area occupies only a small part of the image. Some common deep learning methods that integrate large-scale receptive fields may cause the loss of image detail, resulting in the omission of the region of interest (ROI) in COVID-19 images and are therefore not suitable for further processing. To…
Beckman Institute, University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校贝克曼研究所）
Visual recognition research often assumes a sufficient resolution of the region of interest (ROI). That is usually violated in practice, inspiring us to explore the Very Low Resolution Recognition (VLRR) problem. Typically, the ROI in a VLRR problem can be smaller than $16 \times 16$ pixels, and is challenging to be recognized even by human experts. We attempt to solve the VLRR problem using deep learning methods. Taking advantage of techniques primarily in super resolution, domain adaptation and robust regression, we formulate a dedicated deep learning method and demonstrate how these techniq…
CUNY City College（纽约市立大学城市学院）；CUNY Graduate Center（纽约市立大学研究生中心）
Action Unit (AU) detection becomes essential for facial analysis. Many proposed approaches face challenging problems in dealing with the alignments of different face regions, in the effective fusion of temporal information, and in training a model for multiple AU labels. To better address these problems, we propose a deep learning framework for AU detection with region of interest (ROI) adaptation, integrated multi-label learning, and optimal LSTM-based temporal fusing. First, ROI cropping nets (ROI Nets) are designed to make sure specifically interested regions of faces are learned independen…
The Chinese University of Hong Kong（香港中文大学）；University of Science and Technology of China（中国科学技术大学）；Chinese Academy of Sciences（中国科学院）；SenseTime Group Limited（商汤集团有限公司）；Nanyang Technological University（南洋理工大学）
Recognizing visual relationships <subject-predicate-object> among any pair of localized objects is pivotal for image understanding. Previous studies have shown remarkable progress in exploiting linguistic priors or external textual information to improve the performance. In this work, we investigate an orthogonal perspective based on feature interactions. We show that by encouraging deep message propagation and interactions between local object features and global predicate features, one can achieve compelling performance in recognizing complex relationships without using any linguistic priors…
Shanghai Jiao Tong University（上海交通大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
Person search aims to simultaneously localize and identify a query person from realistic, uncropped images. To achieve this goal, state-of-the-art models typically add a re-id branch upon two-stage detectors like Faster R-CNN. Owing to the ROI-Align operation, this pipeline yields promising accuracy as re-id features are explicitly aligned with the corresponding object regions, but in the meantime, it introduces high computational overhead due to dense object anchors. In this work, we present an anchor-free approach to efficiently tackling this challenging task, by introducing the following de…
This paper studies how to introduce viewpoint-invariant feature representations that can help action recognition and detection. Although we have witnessed great progress of action recognition in the past decade, it remains challenging yet interesting how to efficiently model the geometric variations in large scale datasets. This paper proposes a novel Spatial-Temporal Alignment Network (STAN) that aims to learn geometric invariant representations for action recognition and action detection. The STAN model is very light-weighted and generic, which could be plugged into existing action recogniti…
South China University of Technology（华南理工大学）；Lenovo Research（联想研究院）
Text recognition has attracted considerable research interests because of its various applications. The cutting-edge text recognition methods are based on attention mechanisms. However, most of attention methods usually suffer from serious alignment problem due to its recurrency alignment operation, where the alignment relies on historical decoding results. To remedy this issue, we propose a decoupled attention network (DAN), which decouples the alignment operation from using historical decoding results. DAN is an effective, flexible and robust end-to-end text recognizer, which consists of thr…
Dramatic appearance variation due to pose constitutes a great challenge in fine-grained recognition, one which recent methods using attention mechanisms or second-order statistics fail to adequately address. Modern CNNs typically lack an explicit understanding of object pose and are instead confused by entangled pose and appearance. In this paper, we propose a unified object representation built from a hierarchy of pose-aligned regions. Rather than representing an object by regions aligned to image axes, the proposed representation characterizes appearance relative to the object's pose using p…
Reading text from images remains challenging due to multi-orientation, perspective distortion and especially the curved nature of irregular text. Most of existing approaches attempt to solve the problem in two or multiple stages, which is considered to be the bottleneck to optimize the overall performance. To address this issue, we propose an end-to-end trainable network architecture, named TextNet, which is able to simultaneously localize and recognize irregular text from images. Specifically, we develop a scale-aware attention mechanism to learn multi-scale image features as a backbone netwo…
The Hong Kong University of Science and Technology（香港科技大学）；Kuaishou Technology（快手科技）
Human actions involve complex pose variations and their 2D projections can be highly ambiguous. Thus 3D spatio-temporal or 4D (i.e., 3D+T) human skeletons, which are photometric and viewpoint invariant, are an excellent alternative to 2D+T skeletons/pixels to improve action recognition accuracy. This paper proposes a new 4D dataset HAA4D which consists of more than 3,300 RGB videos in 300 human atomic action classes. HAA4D is clean, diverse, class-balanced where each class is viewpoint-balanced with the use of 4D skeletons, in which as few as one 4D skeleton per class is sufficient for trainin…
LITIS Laboratory（LITIS实验室）；Rouen University（鲁昂大学）；Normandie University（诺曼底大学）；INSA of Rouen（鲁昂国立应用科学学院）
Unconstrained handwriting recognition is an essential task in document analysis. It is usually carried out in two steps. First, the document is segmented into text lines. Second, an Optical Character Recognition model is applied on these line images. We propose the Simple Predict & Align Network: an end-to-end recurrence-free Fully Convolutional Network performing OCR at paragraph level without any prior segmentation stage. The framework is as simple as the one used for the recognition of isolated lines and we achieve competitive results on three popular datasets: RIMES, IAM and READ 2016. The…
MAPRPose: Mask-Aware Proposal and Amodal Refinement for Multi-Object 6D Pose Estimation
State Key Laboratory of Robotics and Systems, Harbin Institute of Technology（机器人系统国家重点实验室，哈尔滨工业大学）；School of Civil Engineering, Harbin Institute of Technology（土木工程学院，哈尔滨工业大学）；Shenzhen Infinite Meta Robot Co., Ltd（深圳无限元机器人有限公司）
ShanghaiTech University（上海科技大学）；University of Chinese Academy of Sciences（中国科学院大学）
Zero-shot learning (ZSL) aims to recognize objects of novel classes without any training samples of specific classes, which is achieved by exploiting the semantic information and auxiliary datasets. Recently most ZSL approaches focus on learning visual-semantic embeddings to transfer knowledge from the auxiliary datasets to the novel classes. However, few works study whether the semantic information is discriminative or not for the recognition task. To tackle such problem, we propose a coupled dictionary learning approach to align the visual-semantic structures using the class prototypes, wher…
Carnegie Mellon University（卡内基梅隆大学）；Microsoft Research Asia（微软亚洲研究院）；Tsinghua University（清华大学）
Temporal modeling is crucial for various video learning tasks. Most recent approaches employ either factorized (2D+1D) or joint (3D) spatial-temporal operations to extract temporal contexts from the input frames. While the former is more efficient in computation, the latter often obtains better performance. In this paper, we attribute this to a dilemma between the sufficiency and the efficiency of interactions among various positions in different frames. These interactions affect the extraction of task-relevant information shared among frames. To resolve this issue, we prove that frame-by-fram…
Electronics and Telecommunications Research Institute (ETRI)（韩国电子通信研究院）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
For the past decades, face recognition (FR) has been actively studied in computer vision and pattern recognition society. Recently, due to the advances in deep learning, the FR technology shows high performance for most of the benchmark datasets. However, when the FR algorithm is applied to a real-world scenario, the performance has been known to be still unsatisfactory. This is mainly attributed to the mismatch between training and testing sets. Among such mismatches, face misalignment between training and testing faces is one of the factors that hinder successful FR. To address this limitati…
Few-shot learning aims to recognize instances from novel classes with few labeled samples, which has great value in research and application. Although there has been a lot of work in this area recently, most of the existing work is based on image classification tasks. Video-based few-shot action recognition has not been explored well and remains challenging: 1) the differences of implementation details among different papers make a fair comparison difficult; 2) the wide variations and misalignment of temporal sequences make the video-level similarity comparison difficult; 3) the scarcity of la…
Signal alignment has become a popular problem in robotics due in part to its fundamental role in action recognition. Currently, the most successful algorithms for signal alignment are Dynamic Time Warping (DTW) and its variant 'Fast' Dynamic Time Warping (FastDTW). Here we introduce a new framework for signal alignment, namely the Globally Optimal Reparameterization Algorithm (GORA). We review the algorithm's mathematical foundation and provide a numerical verification of its theoretical basis. We compare the performance of GORA with that of the DTW and FastDTW algorithms, in terms of computat…
Deep learning-based palmprint recognition algorithms have shown great potential. Most of them are mainly focused on identifying samples from the same dataset. However, they may be not suitable for a more convenient case that the images for training and test are from different datasets, such as collected by embedded terminals and smartphones. Therefore, we propose a novel Joint Pixel and Feature Alignment (JPFA) framework for such cross-dataset palmprint recognition scenarios. Two stage-alignment is applied to obtain adaptive features in source and target datasets. 1) Deep style transfer model …
Automatic facial action unit (AU) recognition is a challenging task due to the scarcity of manual annotations. To alleviate this problem, a large amount of efforts has been dedicated to exploiting various weakly supervised methods which leverage numerous unlabeled data. However, many aspects with regard to some unique properties of AUs, such as the regional and relational characteristics, are not sufficiently explored in previous works. Motivated by this, we take the AU properties into consideration and propose two auxiliary AU related tasks to bridge the gap between limited annotations and th…
BrainCast: A Spatio-Temporal Forecasting Model for Whole-Brain fMRI Time Series Prediction
Institute of Advanced Technology, University of Science and Technology of China（科学技术大学先进技术研究院）；MoE Key Laboratory of Brain-Inspired Intelligence Perception and Cognition, University of Science and Technology of China（科学技术大学脑启发智能感知与认知教育部重点实验室）；School of Mathematics and Computer Sciences, Nanchang University（南昌大学数学与计算机科学学院）；School of Data Science, University of Virginia（弗吉尼亚大学数据科学学院）；Department of Biomedical Engineering, Tulane University（路易斯安那大学医学工程系）
