Temporal action localization is an important yet challenging task in video understanding. Typically, such a task aims at inferring both the action category and localization of the start and end frame for each action instance in a long, untrimmed video.While most current models achieve good results by using pre-defined anchors and numerous actionness, such methods could be bothered with both large number of outputs and heavy tuning of locations and sizes corresponding to different anchors. Instead, anchor-free methods is lighter, getting rid of redundant hyper-parameters, but gains few attention. In this paper, we propose the first purely anchor-free temporal localization method, which is both efficient and effective. Our model includes (i) an end-to-end trainable basic predictor, (ii) a saliency-based refinement module to gather more valuable boundary features for each proposal with a novel boundary pooling, and (iii) several consistency constraints to make sure our model can find the accurate boundary given arbitrary proposals. Extensive experiments show that our method beats all anchor-based and actionness-guided methods with a remarkable margin on THUMOS14, achieving state-of-the-art results, and comparable ones on ActivityNet v1.3. Code is available at https://github.com/TencentYoutuResearch/ActionDetection-AFSD.
School of Automation, Northwestern Polytechnical University（西北工业大学自动化学院）；School of Mechano-Electronic Engineering, Xidian University（西安电子科技大学机电工程学院）；Microsoft Research Asia（微软亚洲研究院）
Most of the current action localization methods follow an anchor-based pipeline: depicting action instances by pre-defined anchors, learning to select the anchors closest to the ground truth, and predicting the confidence of anchors with refinements. Pre-defined anchors set prior about the location and duration for action instances, which facilitates the localization for common action instances but limits the flexibility for tackling action instances with drastic varieties, especially for extremely short or extremely long ones. To address this problem, this paper proposes a novel anchor-free a…
Temporal action localization (TAL) is a task of identifying a set of actions in a video, which involves localizing the start and end frames and classifying each action instance. Existing methods have addressed this task by using predefined anchor windows or heuristic bottom-up boundary-matching strategies, which are major bottlenecks in inference time. Additionally, the main challenge is the inability to capture long-range actions due to a lack of global contextual information. In this paper, we present a novel anchor-free framework, referred to as HTNet, which predicts a set of <start time, e…
University of Chinese Academy of Science（中国科学院大学）；Australian Institute for Machine Learning, The University of Adelaide（阿德莱德大学澳大利亚机器学习研究所）；Peng Cheng Laboratory（鹏城实验室）；University of California, Merced（加州大学默塞德分校）；University of Trento（特伦托大学）
Crowd localization aims to predict the spatial position of humans in a crowd scenario. We observe that the performance of existing methods is challenged from two aspects: (i) ranking inconsistency between test and training phases; and (ii) fixed anchor resolution may underfit or overfit crowd densities of local regions. To address these problems, we design a supervision target reassignment strategy for training to reduce ranking inconsistency and propose an anchor pyramid scheme to adaptively determine the anchor density in each image region. Extensive experimental results on three widely adop…
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 t…
Hierarchical Salient Patch Identification for Interpretable Fundus Disease Localization
School of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；Shanghai Eye Disease Prevention and Treatment Center（上海眼病防治中心）；School of Information Science and Technology, Fudan University（复旦大学信息科学与技术学院）
Tokyo Institute of Technology（东京工业大学）；Olympus Corporation（奥林巴斯公司）
In this paper we introduce a new camera localization strategy designed for image sequences captured in challenging industrial situations such as industrial parts inspection. To deal with peculiar appearances that hurt standard 3D reconstruction pipeline, we exploit pre-knowledge of the scene by selecting key frames in the sequence (called as anchors) which are roughly connected to a certain location. Our method then seek the location of each frame in time-order, while recursively updating an augmented 3D model which can provide current camera location and surrounding 3D structure. In an experi…
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）
Since many safety-critical systems, such as surgical robots and autonomous driving cars operate in unstable environments with sensor noise and incomplete data, it is desirable for object detectors to take the localization uncertainty into account. However, there are several limitations of the existing uncertainty estimation methods for anchor-based object detection. 1) They model the uncertainty of the heterogeneous object properties with different characteristics and scales, such as location (center point) and scale (width, height), which could be difficult to estimate. 2) They model box offs…
Facial landmark localization aims to detect the predefined points of human faces, and the topic has been rapidly improved with the recent development of neural network based methods. However, it remains a challenging task when dealing with faces in unconstrained scenarios, especially with large pose variations. In this paper, we target the problem of facial landmark localization across large poses and address this task based on a split-and-aggregate strategy. To split the search space, we propose a set of anchor templates as references for regression, which well addresses the large variations …
National University of Singapore（新加坡国立大学）；Nanjing University of Posts and Telecommunications（南京邮电大学）；Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东科学院））
Temporal representation is the cornerstone of modern action detection techniques. State-of-the-art methods mostly rely on a dense anchoring scheme, where anchors are sampled uniformly over the temporal domain with a discretized grid, and then regress the accurate boundaries. In this paper, we revisit this foundational stage and introduce Recurrent Continuous Localization (RCL), which learns a fully continuous anchoring representation. Specifically, the proposed representation builds upon an explicit model conditioned with video embeddings and temporal coordinates, which ensure the capability o…
This paper is about action segmentation under weak supervision in training, where the ground truth provides only a set of actions present, but neither their temporal ordering nor when they occur in a training video. We use a Hidden Markov Model (HMM) grounded on a multilayer perceptron (MLP) to label video frames, and thus generate a pseudo-ground truth for the subsequent pseudo-supervised training. In testing, a Monte Carlo sampling of action sets seen in training is used to generate candidate temporal sequences of actions, and select the maximum posterior sequence. Our key contribution is a …
School of Automation, Beijing Institute of Technology（北京理工大学自动化学院）
Arbitrary-oriented objects widely appear in natural scenes, aerial photographs, remote sensing images, etc., thus arbitrary-oriented object detection has received considerable attention. Many current rotation detectors use plenty of anchors with different orientations to achieve spatial alignment with ground truth boxes, then Intersection-over-Union (IoU) is applied to sample the positive and negative candidates for training. However, we observe that the selected positive anchors cannot always ensure accurate detections after regression, while some negative samples can achieve accurate localiz…
University of Electronic Science and Technology of China（电子科技大学）；Inception Institute of Artificial Intelligence (IIAI)（人工智能初始研究所）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Existing CNNs-based salient object detection (SOD) heavily depends on the large-scale pixel-level annotations, which is labor-intensive, time-consuming, and expensive. By contrast, the sparse annotations become appealing to the salient object detection community. However, few efforts are devoted to learning salient object detection from sparse annotations, especially in the remote sensing field. In addition, the sparse annotation usually contains scanty information, which makes it challenging to train a well-performing model, resulting in its performance largely lagging behind the fully-superv…
Recent works on salient object detection have made use of multi-scale features in a way such that high-level features and low-level features can collaborate in locating salient objects. Many of the previous methods have achieved great performance in salient object detection. By merging the high-level and low-level features, a large number of feature information can be extracted. Generally, they are doing these in a one-way framework, and interweaving the variable features all the way to the final feature output. Which may cause some blurring or inaccurate localization of saliency maps. To over…
Wuhan University of Technology（武汉理工大学）；National University of Singapore（新加坡国立大学）
Computer vision based fine-grained recognition has received great attention in recent years. Existing works focus on discriminative part localization and feature learning. In this paper, to improve the performance of fine-grained recognition, we try to precisely locate as many salient parts of object as possible at first. Then, we figure out the classification probability that can be obtained by using separate parts for object classification. Finally, through extracting efficient features from each part and combining them, then feeding to a classifier for recognition, an improved accuracy over…
We present a model for temporally precise action spotting in videos, which uses a dense set of detection anchors, predicting a detection confidence and corresponding fine-grained temporal displacement for each anchor. We experiment with two trunk architectures, both of which are able to incorporate large temporal contexts while preserving the smaller-scale features required for precise localization: a one-dimensional version of a u-net, and a Transformer encoder (TE). We also suggest best practices for training models of this kind, by applying Sharpness-Aware Minimization (SAM) and mixup data …
Huazhong University of Science and Technology（华中科技大学）
For most of the anchor-based detectors, Intersection over Union(IoU) is widely utilized to assign targets for the anchors during training. However, IoU pays insufficient attention to the closeness of the anchor's center to the truth box's center. This results in two problems: (1) only one anchor is assigned to most of the slender objects which leads to insufficient supervision information for the slender objects during training and the performance on the slender objects is hurt; (2) IoU can not accurately represent the alignment degree between the receptive field of the feature at the anchor's…
Local feature matching is essential for many applications, such as localization and 3D reconstruction. However, it is challenging to match feature points accurately in various camera viewpoints and illumination conditions. In this paper, we propose a framework that robustly extracts and describes salient local features regardless of changing light and viewpoints. The framework suppresses illumination variations and encourages structural information to ignore the noise from light and to focus on edges. We classify the elements in the feature covariance matrix, an implicit feature map informatio…
Zhejiang University（浙江大学）；Tencent AI Lab（腾讯人工智能实验室）；University of Rochester（罗切斯特大学）；National University of Singapore（新加坡国立大学）；Zhejiang University of Science and Technology（浙江科技大学）
We aim to address the problem of Natural Language Video Localization (NLVL)-localizing the video segment corresponding to a natural language description in a long and untrimmed video. State-of-the-art NLVL methods are almost in one-stage fashion, which can be typically grouped into two categories: 1) anchor-based approach: it first pre-defines a series of video segment candidates (e.g., by sliding window), and then does classification for each candidate; 2) anchor-free approach: it directly predicts the probabilities for each video frame as a boundary or intermediate frame inside the positive …
Learning to Anchor Visual Odometry: KAN-Based Pose Regression for Planetary Landing
University of Chinese Academy of Sciences（中国科学院大学）；Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences（中国科学院空间利用技术与工程中心）
Typically, a salient object detection (SOD) model faces opposite requirements in processing object interiors and boundaries. The features of interiors should be invariant to strong appearance change so as to pop-out the salient object as a whole, while the features of boundaries should be selective to slight appearance change to distinguish salient objects and background. To address this selectivity-invariance dilemma, we propose a novel boundary-aware network with successive dilation for image-based SOD. In this network, the feature selectivity at boundaries is enhanced by incorporating a bou…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）；Peking University（北京大学）
Modern object detectors rely heavily on rectangular bounding boxes, such as anchors, proposals and the final predictions, to represent objects at various recognition stages. The bounding box is convenient to use but provides only a coarse localization of objects and leads to a correspondingly coarse extraction of object features. In this paper, we present \textbf{RepPoints} (representative points), a new finer representation of objects as a set of sample points useful for both localization and recognition. Given ground truth localization and recognition targets for training, RepPoints learn to…
IRA Labs Ltd（IRA实验室有限公司）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术学院）；Kharkevich Institute for Information Transmission Problems（哈尔克维奇信息传输问题研究所）；Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Health Care Department（莫斯科卫生部诊断与远程医疗技术研究实践临床中心）；Osimis SA（Osimis股份公司）；Artificial Intelligence Research Institute（人工智能研究所）
Vertebral body compression fractures are early signs of osteoporosis. Though these fractures are visible on Computed Tomography (CT) images, they are frequently missed by radiologists in clinical settings. Prior research on automatic methods of vertebral fracture classification proves its reliable quality; however, existing methods provide hard-to-interpret outputs and sometimes fail to process cases with severe abnormalities such as highly pathological vertebrae or scoliosis. We propose a new two-step algorithm to localize the vertebral column in 3D CT images and then detect individual verteb…
Indian Institute of Technology, Kharagpur（印度理工学院克勒格布尔分校）
Extraction of discriminative features from salient facial patches plays a vital role in effective facial expression recognition. The accurate detection of facial landmarks improves the localization of the salient patches on face images. This paper proposes a novel framework for expression recognition by using appearance features of selected facial patches. A few prominent facial patches, depending on the position of facial landmarks, are extracted which are active during emotion elicitation. These active patches are further processed to obtain the salient patches which contain discriminative f…
ActiveScope: Actively Seeking and Correcting Perception for MLLMs
University of Chinese Academy of Sciences（中国科学院大学）；State Key Lab of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China（中国科学院人工智能安全国家重点实验室，计算技术研究所，北京，中国）；Harbin Institute of Technology (Weihai)（哈尔滨工业大学（威海））
Salient object detection has achieved great improvement by using the Fully Convolution Network (FCN). However, the FCN-based U-shape architecture may cause the dilution problem in the high-level semantic information during the up-sample operations in the top-down pathway. Thus, it can weaken the ability of salient object localization and produce degraded boundaries. To this end, in order to overcome this limitation, we propose a novel pyramid self-attention module (PSAM) and the adoption of an independent feature-complementing strategy. In PSAM, self-attention layers are equipped after multi-s…
Pattern Recognition and Intelligent Vision Lab, Beijing University of Posts and Telecommunications（北京邮电大学模式识别与智能视觉实验室）
In object detection, offset-guided and point-guided regression dominate anchor-based and anchor-free method separately. Recently, point-guided approach is introduced to anchor-based method. However, we observe points predicted by this way are misaligned with matched region of proposals and score of localization, causing a notable gap in performance. In this paper, we propose CPM R-CNN which contains three efficient modules to optimize anchor-based point-guided method. According to sufficient evaluations on the COCO dataset, CPM R-CNN is demonstrated efficient to improve the localization accura…
