This technical report introduces our 2nd place solution to Kinetics-TPS Track on Part-level Action Parsing in ICCV DeeperAction Workshop 2021. Our entry is mainly based on YOLOF for instance and part detection, HRNet for human pose estimation, and CSN for video-level action recognition and frame-level part state parsing. We describe technical details for the Kinetics-TPS dataset, together with some experimental results. In the competition, we achieved 61.37% mAP on the test set of Kinetics-TPS.
University of Electronic Science and Technology of China（电子科技大学）；Zhejiang Lab（之江实验室）
Part-level Action Parsing aims at part state parsing for boosting action recognition in videos. Despite of dramatic progresses in the area of video classification research, a severe problem faced by the community is that the detailed understanding of human actions is ignored. Our motivation is that parsing human actions needs to build models that focus on the specific problem. We present a simple yet effective approach, named disentangled action parsing (DAP). Specifically, we divided the part-level action parsing into three stages: 1) person detection, where a person detector is adopted to de…
The Shenzhen International Graduate School, Tsinghua University, China（清华大学深圳国际研究生院）；School of Computer Science and Information Engineering, Hefei University of Technology, China（合肥工业大学计算机科学与信息工程学院）
It Takes Two: Accurate Gait Recognition in the Wild via Cross-granularity Alignment
Hangzhou Dianzi University（杭州电子科技大学）；Lishui Institute of Hangzhou Dianzi University（杭州电子科技大学丽水学院）；JD Explore Academy（京东探索研究院）；The Experimental High School Attached To Beijing Normal University（北京师范大学附属实验中学）；University of Science and Technology of China（中国科学技术大学）
Visual Computing Group, Ping An Property & Casualty Insurance Company（平安财产保险股份有限公司视觉计算组）；Ping An Technology Company（平安科技公司）
This paper presents our solution for ICDAR 2021 competition on scientific literature parsing taskB: table recognition to HTML. In our method, we divide the table content recognition task into foursub-tasks: table structure recognition, text line detection, text line recognition, and box assignment.Our table structure recognition algorithm is customized based on MASTER [1], a robust image textrecognition algorithm. PSENet [2] is used to detect each text line in the table image. For text linerecognition, our model is also built on MASTER. Finally, in the box assignment phase, we associatedthe te…
Cranberry-Lemon University（蔓越莓柠檬大学）；University of the Witwatersrand（威特沃特斯兰德大学）
We propose a new method for fine-grained few-shot recognition via deep object parsing. In our framework, an object is made up of K distinct parts and for each part, we learn a dictionary of templates, which is shared across all instances and categories. An object is parsed by estimating the locations of these K parts and a set of active templates that can reconstruct the part features. We recognize test instances by comparing its active templates and the relative geometry of its part locations against those of the presented few-shot instances. Our method is end-to-end trainable to learn part t…
School of Computer Science, Peking University（北京大学计算机学院）；School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机学院）；School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Peking University（北京大学深圳研究生院电子与计算机工程学院）
The key of Human-Object Interaction(HOI) recognition is to infer the relationship between human and objects. Recently, the image's Human-Object Interaction(HOI) detection has made significant progress. However, there is still room for improvement in video HOI detection performance. Existing one-stage methods use well-designed end-to-end networks to detect a video segment and directly predict an interaction. It makes the model learning and further optimization of the network more complex. This paper introduces the Spatial Parsing and Dynamic Temporal Pooling (SPDTP) network, which takes the ent…
For a given video-based Human-Object Interaction scene, modeling the spatio-temporal relationship between humans and objects are the important cue to understand the contextual information presented in the video. With the effective spatio-temporal relationship modeling, it is possible not only to uncover contextual information in each frame but also to directly capture inter-time dependencies. It is more critical to capture the position changes of human and objects over the spatio-temporal dimension when their appearance features may not show up significant changes over time. The full use of ap…
MinerU.Chem: A High-Precision System for Optical Chemical Structure and Reaction Recognition
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；East China Normal University（华东师范大学）；Tongji University（同济大学）；Fudan University（复旦大学）；East China University of Science and Technology（华东理工大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Shanghai Jiao Tong University（上海交通大学）；Jilin University（吉林大学）；Beihang University（北京航空航天大学）；South China Normal University（华南师范大学）；Peking University（北京大学）；Northwestern Polytechnical University（西北工业大学）
