In this technical report, we describe our solution to temporal action proposal (task 1) in ActivityNet Challenge 2019. First, we fine-tune a ResNet-50-C3D CNN on ActivityNet v1.3 based on Kinetics pretrained model to extract snippet-level video representations and then we design a Relation-Aware Pyramid Network (RapNet) to generate temporal multiscale proposals with confidence score. After that, we employ a two-stage snippet-level boundary adjustment scheme to re-rank the order of generated proposals. Ensemble methods are also been used to improve the performance of our solution, which helps us achieve 2nd place.
CloudWalk Technology Co., Ltd（云从科技股份有限公司）；Cooperative Medianet Innovation Center, Shanghai Jiao Tong University（上海交通大学协同媒体创新中心）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）
Accurate temporal action proposals play an important role in detecting actions from untrimmed videos. The existing approaches have difficulties in capturing global contextual information and simultaneously localizing actions with different durations. To this end, we propose a Relation-aware pyramid Network (RapNet) to generate highly accurate temporal action proposals. In RapNet, a novel relation-aware module is introduced to exploit bi-directional long-range relations between local features for context distilling. This embedded module enhances the RapNet in terms of its multi-granularity temp…
Academy for Engineering and Technology, Fudan University（复旦大学工程与应用技术研究院）；Fudan Zhangjiang Institute（复旦张江研究院）；Sensetime Research（商汤科技研究院）；School of Computer Science, Fudan University（复旦大学计算机科学技术学院）；The Hong Kong Polytechnic University（香港理工大学）
It has been found that temporal action proposal generation, which aims to discover the temporal action instances within the range of the start and end frames in the untrimmed videos, can largely benefit from proper temporal and semantic context exploitation. The latest efforts were dedicated to considering the temporal context and similarity-based semantic contexts through self-attention modules. However, they still suffer from cluttered background information and limited contextual feature learning. In this paper, we propose a novel Pyramid Region-based Slot Attention (PRSlot) module to addre…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Horizon Robotics, Inc（地平线机器人公司）；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）
Recently, proposal-free instance segmentation has received increasing attention due to its concise and efficient pipeline. Generally, proposal-free methods generate instance-agnostic semantic segmentation labels and instance-aware features to group pixels into different object instances. However, previous methods mostly employ separate modules for these two sub-tasks and require multiple passes for inference. We argue that treating these two sub-tasks separately is suboptimal. In fact, employing multiple separate modules significantly reduces the potential for application. The mutual benefits …
Open-vocabulary object detection aims to provide object detectors trained on a fixed set of object categories with the generalizability to detect objects described by arbitrary text queries. Previous methods adopt knowledge distillation to extract knowledge from Pretrained Vision-and-Language Models (PVLMs) and transfer it to detectors. However, due to the non-adaptive proposal cropping and single-level feature mimicking processes, they suffer from information destruction during knowledge extraction and inefficient knowledge transfer. To remedy these limitations, we propose an Object-Aware Dis…
University of Southern California（南加州大学）；Samsung Research America（三星美国研究院）
Face detection is a widely studied problem over the past few decades. Recently, significant improvements have been achieved via the deep neural network, however, it is still challenging to directly apply these techniques to mobile devices for its limited computational power and memory. In this work, we present a proposal generation acceleration framework for real-time face detection. More specifically, we adopt a popular cascaded convolutional neural network (CNN) as the basis, then apply our acceleration approach on the basic framework to speed up the model inference time. We are motivated by…
Lung nodules suffer large variation in size and appearance in CT images. Nodules less than 10mm can easily lose information after down-sampling in convolutional neural networks, which results in low sensitivity. In this paper, a combination of 3D image and feature pyramid is exploited to integrate lower-level texture features with high-level semantic features, thus leading to a higher recall. However, 3D operations are time and memory consuming, which aggravates the situation with the explosive growth of medical images. To tackle this problem, we propose a general curriculum training strategy …
The Chinese University of Hong Kong（香港中文大学）；ETH Zurich（苏黎世联邦理工学院）
Detecting actions in untrimmed videos is an important yet challenging task. In this paper, we present the structured segment network (SSN), a novel framework which models the temporal structure of each action instance via a structured temporal pyramid. On top of the pyramid, we further introduce a decomposed discriminative model comprising two classifiers, respectively for classifying actions and determining completeness. This allows the framework to effectively distinguish positive proposals from background or incomplete ones, thus leading to both accurate recognition and localization. These …
Semantic Segmentation (SS) is a task to assign semantic label to each pixel of the images, which is of immense significance for autonomous vehicles, robotics and assisted navigation of vulnerable road users. It is obvious that in different application scenarios, different objects possess hierarchical importance and safety-relevance, but conventional loss functions like cross entropy have not taken the different levels of importance of diverse traffic elements into consideration. To address this dilemma, we leverage and re-design an importance-aware loss function, throwing insightful hints on h…
Tencent AI Lab（腾讯人工智能实验室）；Southeast University（东南大学）；Columbia University（哥伦比亚大学）
Temporal action proposal generation is an important task, aiming to localize the video segments containing human actions in an untrimmed video. In this paper, we propose a multi-granularity generator (MGG) to perform the temporal action proposal from different granularity perspectives, relying on the video visual features equipped with the position embedding information. First, we propose to use a bilinear matching model to exploit the rich local information within the video sequence. Afterwards, two components, namely segment proposal producer (SPP) and frame actionness producer (FAP), are co…
East China Normal University（华东师范大学）；Shanghai Advanced Research Institute, CAS（中国科学院上海高等研究院）；University of Washington（华盛顿大学）
Locating actions in long untrimmed videos has been a challenging problem in video content analysis. The performances of existing action localization approaches remain unsatisfactory in precisely determining the beginning and the end of an action. Imitating the human perception procedure with observations and refinements, we propose a novel three-phase action localization framework. Our framework is embedded with an Actionness Network to generate initial proposals through frame-wise similarity grouping, and then a Refinement Network to conduct boundary adjustment on these proposals. Finally, th…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Electronics and Telecommunications Research Institute (ETRI)（电子与电信研究院）；Hanbat National University（韩巴国立大学）
Recent temporal action proposal generation approaches have suggested integrating segment- and snippet score-based methodologies to produce proposals with high recall and accurate boundaries. In this paper, different from such a hybrid strategy, we focus on the potential of the snippet score-based approach. Specifically, we propose a new snippet score-based method, named Snippet Relatedness-based Generator (SRG), with a novel concept of "snippet relatedness". Snippet relatedness represents which snippets are related to a specific action instance. To effectively learn this snippet relatedness, w…
Northeastern University（东北大学）；Science and Technology on Space Physics Laboratory（空间物理实验室）
RoIPool/RoIAlign is an indispensable process for the typical two-stage object detection algorithm, it is used to rescale the object proposal cropped from the feature pyramid to generate a fixed size feature map. However, these cropped feature maps of local receptive fields will heavily lose global context information. To tackle this problem, we propose a novel end-to-end trainable framework, called Global Context Aware (GCA) RCNN, aiming at assisting the neural network in strengthening the spatial correlation between the background and the foreground by fusing global context information. The c…
Sheikh Zayed Institute of Pediatric and Surgical Innovation（谢赫·扎耶德儿科与外科创新研究所）；George Washington University（乔治华盛顿大学）
State-of-the-art methods for object detection use region proposal networks (RPN) to hypothesize object location. These networks simultaneously predicts object bounding boxes and \emph{objectness} scores at each location in the image. Unlike natural images for which RPN algorithms were originally designed, most medical images are acquired following standard protocols, thus organs in the image are typically at a similar location and possess similar geometrical characteristics (e.g. scale, aspect-ratio, etc.). Therefore, medical image acquisition protocols hold critical localization and geometric…
The University of Hong Kong（香港大学）；TCL Corporate Research（TCL企业研究）；HKU-TCL Joint Research Centre for Artificial Intelligence（港大-TCL人工智能联合研究中心）
Temporal Action Detection (TAD) is an essential and challenging topic in video understanding, aiming to localize the temporal segments containing human action instances and predict the action categories. The previous works greatly rely upon dense candidates either by designing varying anchors or enumerating all the combinations of boundaries on video sequences; therefore, they are related to complicated pipelines and sensitive hand-crafted designs. Recently, with the resurgence of Transformer, query-based methods have tended to become the rising solutions for their simplicity and flexibility. …
KAUST（阿卜杜拉国王科技大学）；Boston University（波士顿大学）；Institute of Software, CAS（中国科学院软件研究所）
Activity detection is a fundamental problem in computer vision. Detecting activities of different temporal scales is particularly challenging. In this paper, we propose the contextual multi-scale region convolutional 3D network (CMS-RC3D) for activity detection. To deal with the inherent temporal scale variability of activity instances, the temporal feature pyramid is used to represent activities of different temporal scales. On each level of the temporal feature pyramid, an activity proposal detector and an activity classifier are learned to detect activities of specific temporal scales. Temp…
Hefei University（合肥学院）；School of Artificial Intelligence and Big Data, Hefei University（合肥学院人工智能与大数据学院）；Institute of Applied Optimization, School of Artificial Intelligence and Big Data, Hefei University（合肥学院人工智能与大数据学院应用优化研究所）；School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；University of Science and Technology of China（中国科学技术大学）
Recently, with the availability of cost-effective depth cameras coupled with real-time skeleton estimation, the interest in skeleton-based human action recognition is renewed. Most of the existing skeletal representation approaches use either the joint location or the dynamics model. Differing from the previous studies, we propose a new method called Denoising Autoencoder with Temporal and Categorical Constraints (DAE_CTC)} to study the skeletal representation in a view of skeleton reconstruction. Based on the concept of learning under privileged information, we integrate action categories and…
