A5040508380- X-ray Diffraction in Crystallography
- Crystallization and Solubility Studies
- Human Pose and Action Recognition
- Visual Attention and Saliency Detection
- Catalytic C–H Functionalization Methods
- Video Surveillance and Tracking Methods
- Advanced Neural Network Applications
- Anomaly Detection Techniques and Applications
- Advanced Image and Video Retrieval Techniques
- Face recognition and analysis
- Face Recognition and Perception
- Biometric Identification and Security
- Catalytic Alkyne Reactions
- Catalytic Cross-Coupling Reactions
- Advanced Computational Techniques and Applications
- Olfactory and Sensory Function Studies
- Video Analysis and Summarization
- Microbial Community Ecology and Physiology
- Reinforcement Learning in Robotics
- Multimodal Machine Learning Applications
- Advanced Vision and Imaging
- Manufacturing Process and Optimization
- Synthesis and Characterization of Pyrroles
- Sports Analytics and Performance
- Context-Aware Activity Recognition Systems
Beijing University of Technology
2022-2025
Nankai University
2023-2024
Qingdao University
2023
Beijing Jiaotong University
2017-2022
Hunan University of Traditional Chinese Medicine
2019-2021
South China University of Technology
2007-2018
Shanghai University of International Business and Economics
2004
World Wide Web Consortium
2001-2002
A new approach to construct 2,3-disubstituted quinolines is described via Pd-catalyzed oxidative cyclization of o-vinylanilines and alkynes with molecular oxygen. This transformation supposed undergo intermolecular amination alkyne, insertion the olefin, cleavage C–C bond sequence.
Attention mechanisms have been proven highly effective for salient object detection. Most previous works utilize attention as a self-gated module to reweigh the feature maps at different levels independently. However, they are limited certain-level guidance and could not satisfy need of both accurately detecting intact objects maintaining their detailed boundaries. In this paper, we build dense upon features from multiple simultaneously propose novel Dense Attentive Feature Enhancement...
Abstract Human action understanding (HAU) is a broad topic that involves specific tasks, such as localisation, recognition, and assessment. However, most popular HAU datasets are bound to one task based on particular actions. Combining different but relevant tasks establish unified system challenging due the disparate actions across datasets. A large‐scale comprehensive benchmark, namely SkatingVerse constructed for segmentation, proposal, focus fine‐grained sport action, hence figure...
Existing weakly supervised group activity recognition methods rely on object detectors or attention mechanisms to capture key areas automatically. However, they overlook the semantic information associated with captured areas, which may adversely affect performance. In this paper, we propose a novel framework named Visual Conceptual Knowledge Guided Action Map (VicKAM) effectively captures locations of individual actions and integrates them action semantics for recognition.It generates...
Feature pyramid network (FPN) based models, which fuse the semantics and salient details in a progressive manner, have been proven highly effective object detection. However, it is observed that these models often generate saliency maps with incomplete structures or unclear boundaries, due to \emph{indirect} information propagation among distant layers makes such fusion structure less effective. In this work, we propose novel Cross-layer Pyramid Network (CFPN), direct cross-layer...
A novel Pd-catalyzed intermolecular oxidative cyclization of bromoalkynes with <italic>N</italic>-allylamines to construct 3-bromo-pyrrole derivatives has been developed.
The vinyl moiety-assisted selective O-nucleopalladation is reported, which offers rapid constructions of cycloolefins and cyclopropanes via oxidant-induced cyclization enynes. O2 resulted in the unexpected 6-endo-Heck cyclization, while CuCl2 led to a 5-exo-trig pathway synergetic SN2-type C-C bond formation. Amide works as an O-transferred nucleophilic group activate alkyne moiety, induced divergent annulation processes. Moreover, regenerated amides could be used for further modifications.
Abstract A novel palladium‐catalyzed cyclization of alkynyl carboxylic acids with isocyanides has been successfully developed herein. The corresponding 5‐iminofuranone or 5‐iminopyrrolone derivatives were constructed in moderate to good yields which well controlled by the solvents. These reactions proceed under simple and mild reaction conditions high efficiency, feature a wide substrate scope, readily available starting materials easy operation. magnified image
Group activity recognition aims to recognize behaviors characterized by multiple individuals within a scene. Existing schemes rely on individual relation inference and usually take the as tokens. Essentially they select most relevant region of group from entire image while filtering out irrelevant background noises. However, these require bounding box labeling in both training testing stages. Since have been presented at one scale, multi-scale cannot be combined an effective way. In this...
A novel and efficient palladium-catalyzed sequential decarboxylation carbonylation of allyl alkynoates for constructing functionalized 1,4-enyne-3-ones has been demonstrated.
Recently, co-saliency detection, which aims to automatically discover common and salient objects appeared in several relevant images, has attracted increased interest the computer vision community. In this article, we present a novel graph-matching based model for detection image pairs. A solution of graph matching is proposed integrate visual appearance, saliency coherence, spatial structural continuity detecting collaboratively. Since similarity have been seamlessly integrated, such joint...
Tracking an Unmanned Aerial Vehicle (UAV) to obtain its locations and trajectory is a crucial task avoid the unlawful use of UAVs. However, most existing UAV tracking methods fail when facing cluster environments, out-of-view, occlusions because their insufficient representation global context information capacity. To mitigate these issues, we propose new tracker, namely SiamFusion, innovate dual fusion procedure that leverages advantages in both feature decision levels. In particular, novel...