Yong-Lu Li

Yong-Lu Li

Auto-generated profile, based on publicly available information

Yong-Lu Li

Shanghai Jiao Tong University

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 November 2022 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
HFHao-Shu Fang
Hao-Shu Fang
JLJiefeng Li
Jiefeng Li
HTHongyang Tang
Hongyang Tang
CXChao Xu
Chao Xu
HZHaoyi Zhu
Haoyi Zhu
CLCewu Lu
Cewu Lu
Accurate whole-body multi-person pose estimation and tracking is an important yet challenging topic in computer vision. To capture the subtle actions of humans for complex behavior analysis, whole-body pose estimation including the face, body, hand and foot is essential over conventional body-only pose estimation. In this article, we present AlphaPose, a system that can perform accurate whole-body pose estimation and tracking jointly while running in realtime. To this end, we propose several new techniques: Symmetric Integral Keypoint Regression (SIKR) for fast and fine localization, Parametric Pose Non-Maximum-Suppression (P-NMS) for eliminating redundant human detections and Pose Aware Identity Embedding for jointly pose estimation and tracking. During training, we resort to Part-Guided Proposal Generator (PGPG) and multi-domain knowledge distillation to further improve the accuracy. Our method is able to localize whole-body keypoints accurately and tracks humans simultaneously given inaccurate bounding boxes and redundant detections. We show a significant improvement over current state-of-the-art methods in both speed and accuracy on COCO-wholebody, COCO, PoseTrack, and our proposed Halpe-FullBody pose estimation dataset. Our model, source codes and dataset are made publicly available at https://github.com/MVIG-SJTU/AlphaPose.

29 December 2022 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YLYong-Lu Li
Yong-Lu Li
XLXinpeng Liu
Xinpeng Liu
XWXiaoqian Wu
Xiaoqian Wu
YLYizhuo Li
Yizhuo Li
ZQZuoyu Qiu
Zuoyu Qiu
CLCewu Lu
Cewu Lu
Human activity understanding is of widespread interest in artificial intelligence and spans diverse applications like health care and behavior analysis. Although there have been advances with deep learning, it remains challenging. The object recognition-like solutions usually try to map pixels to semantics directly, but activity patterns are much different from object patterns, thus hindering another success. In this work, we propose a novel paradigm to reformulate this task in two-stage: first mapping pixels to an intermediate space spanned by atomic activity primitives, then programming detected primitives with interpretable logic rules to infer semantics. To afford a representative primitive space, we build a knowledge base including 26+ M primitive labels and logic rules from human priors or automatic discovering. Our framework, H uman A ctivity K nowledge E ngine ( HAKE ), exhibits superior generalization ability and performance upon canonical methods on challenging benchmarks. Code and data are available at http://hake-mvig.cn/ .

28 October 2022
Verified
Book Chapter
Closed access
PDF file
XWXiaoqian Wu
Xiaoqian Wu
YLYong-Lu Li
Yong-Lu Li
XLXinpeng Liu
Xinpeng Liu
JZJunyi Zhang
Junyi Zhang
YWYuzhe Wu
Yuzhe Wu
CLCewu Lu
Cewu Lu

25 January 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YLYong-Lu Li
Yong-Lu Li
XLXinpeng Liu
Xinpeng Liu
XWXiaoqian Wu
Xiaoqian Wu
XHXijie Huang
Xijie Huang
LXLiang Xu
Liang Xu
CLCewu Lu
Cewu Lu
Human-object interaction (HOI) Detection is an important problem to understand how humans interact with objects. In this paper, we explore Interactiveness Knowledge which indicates whether human and object interact with each other or not. We found that interactiveness knowledge can be learned across HOI datasets and alleviate the gap between diverse HOI category settings. Our core idea is to exploit an Interactiveness Network to learn the general interactiveness knowledge from multiple HOI datasets and perform Non-Interaction Suppression before HOI classification in inference. On account of the generalization of interactiveness, interactiveness network is a transferable knowledge learner and can be cooperated with any HOI detection models to achieve desirable results. We utilize the human instance and body part features together to learn the interactiveness in hierarchical paradigm, i.e., instance-level and body part-level interactivenesses. Thereafter, a consistency task is proposed to guide the learning and extract deeper interactive visual clues. We extensively evaluate the proposed method on HICO-DET, V-COCO, and a newly constructed HAKE-HOI dataset. With the learned interactiveness, our method outperforms state-of-the-art HOI detection methods, verifying its efficacy and flexibility. Code is available at https://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network .

20 October 2022
Verified
Book Chapter
Closed access
PDF file
YXYue Xu
Yue Xu
YLYong-Lu Li
Yong-Lu Li
JLJiefeng Li
Jiefeng Li
CLCewu Lu
Cewu Lu