11 citations · 43 across the 18 of their papers we have counts for
18 papers
A Vlogger-augmented Graph Neural Network Model for Micro-video Recommendation
Weijiang Lai, Beihong Jin, Beibei Li +2
Existing micro-video recommendation models exploit the interactions between users and micro-videos and/or multi-modal information of micro-videos to predict the next micro-video a…
TOPIC: A Parallel Association Paradigm for Multi-Object Tracking under Complex Motions and Diverse Scenes
Xiaoyan Cao, Yiyao Zheng, Yao Yao +3
Video data and algorithms have been driving advances in multi-object tracking (MOT). While existing MOT datasets focus on occlusion and appearance similarity, complex motion patter…
Experimental verification of a coherence factorization law for quantum states
Yi Zheng, Cheng-Jie Zhang, Zheng-Hao Liu +4
As a quantum resource, quantum coherence plays an important role in modern physics. Many coherence measures and their relations with entanglement have been proposed, and the dynami…
Evolution equation for quantum coherence
Xinzhi Zhao, Jianwei Shao, Yi Zheng +2
Quantum coherence plays an important role in quantum resource theory, which is strongly related with entanglement. Similar to the entanglement evolution equation, we find the coher…
Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs
Yizhen Zheng, He Zhang, Vincent CS Lee +3
Real-world graphs generally have only one kind of tendency in their connections. These connections are either homophily-prone or heterophily-prone. While graphs with homophily-pron…
Deep Neural Networks in Video Human Action Recognition: A Review
Zihan Wang, Yang Yang, Zhi Liu +1
Currently, video behavior recognition is one of the most foundational tasks of computer vision. The 2D neural networks of deep learning are built for recognizing pixel-level inform…
Egalitarian ORAM: Wear-Leveling for ORAM
Yi Zheng, Aasheesh Kolli, Shaizeen Aga
While non-volatile memories (NVMs) provide several desirable characteristics like better density and comparable energy efficiency than DRAM, DRAM-like performance, and disk-like du…
Realization of all-optical underdamped stochastic Stirling engine
Chuang Li, Shaochong Zhu, Peitong He +6
We experimentally demonstrate a nano-scale stochastic Stirling heat engine operating in the underdamped regime. The setup involves an optically levitated silica particle that is su…
Recognition and Prediction of Surgical Gestures and Trajectories Using Transformer Models in Robot-Assisted Surgery
Chang Shi, Yi Zheng, Ann Majewicz Fey
Surgical activity recognition and prediction can help provide important context in many Robot-Assisted Surgery (RAS) applications, for example, surgical progress monitoring and est…
A Random Forest and Current Fault Texture Feature-Based Method for Current Sensor Fault Diagnosis in Three-Phase PWM VSR
Lei Kou, Xiao-dong Gong, Yi Zheng +4
Three-phase PWM voltage-source rectifier (VSR) systems have been widely used in various energy conversion systems, where current sensors are the key component for state monitoring…
Improving Micro-video Recommendation by Controlling Position Bias
Yisong Yu, Beihong Jin, Jiageng Song +3
As the micro-video apps become popular, the numbers of micro-videos and users increase rapidly, which highlights the importance of micro-video recommendation. Although the micro-vi…
Toward practical weak measurement wavefront sensing: spatial resolution and achromatism
Yi Zheng, Mu Yang, Zheng-Hao Liu +3
The weak measurement wavefront sensor detects the phase gradient of light like the Shack-Hartmann sensor does. However, the use of one thin birefringent crystal to displace light b…
Improving Micro-video Recommendation via Contrastive Multiple Interests
Beibei Li, Beihong Jin, Jiageng Song +3
With the rapid increase of micro-video creators and viewers, how to make personalized recommendations from a large number of candidates to viewers begins to attract more and more a…
Multi-Level Attention for Unsupervised Person Re-Identification
Yi Zheng
The attention mechanism is widely used in deep learning because of its excellent performance in neural networks without introducing additional information. However, in unsupervised…
Flatland Competition 2020: MAPF and MARL for Efficient Train Coordination on a Grid World
Florian Laurent, Manuel Schneider, Christian Scheller +24
The Flatland competition aimed at finding novel approaches to solve the vehicle re-scheduling problem (VRSP). The VRSP is concerned with scheduling trips in traffic networks and th…
Homophone-based Label Smoothing in End-to-End Automatic Speech Recognition
Yi Zheng, Xianjie Yang, Xuyong Dang
A new label smoothing method that makes use of prior knowledge of a language at human level, homophone, is proposed in this paper for automatic speech recognition (ASR). Compared w…
A method for detecting text of arbitrary shapes in natural scenes that improves text spotting
Qitong Wang, Yi Zheng, Margrit Betke
Understanding the meaning of text in images of natural scenes like highway signs or store front emblems is particularly challenging if the text is foreshortened in the image or the…
On Evaluating the Renaissance Benchmarking Suite: Variety, Performance, and Complexity
Aleksandar Prokopec, Andrea Rosà, David Leopoldseder +9
The recently proposed Renaissance suite is composed of modern, real-world, concurrent, and object-oriented workloads that exercise various concurrency primitives of the JVM. Renais…