Yaqun Fang

Personalized Task Dependency Graphs for Mitigating Signal Erosion in Multi-Task Recommendation

Fuyuan Liu, Tiandeng Wu, Yaqun Fang, Wei Zhou et autres

Optimizing multiple conversion objectives is a core challenge in industrial recommendation, often limited by signal erosion in rigid architectures. Existing Multi-Task Learning (MTL) methods typically enforce uniform dependency strengths across a static conversion funnel, overlooking how task correlations naturally vary based on …

CAGNet: a context-aware graph neural network for detecting social relationships in videos

Fan Yu, Yaqun Fang, Zhixiang Zhao, Jia Bei et autres

Abstract Social relationships, such as parent-offspring and friends, are crucial and stable connections between individuals, especially at the person level, and are essential for accurately describing the semantics of videos. In this paper, we analogize such a task to scene graph generation, …

cn (code pays fourni par la source)

Reproducibility Companion Paper of "MMSF: A Multimodal Sentiment-Fused Method to Recognize Video Speaking Style"

Fan Yu, Beibei Zhang, Yaqun Fang, Jia Bei et autres

To support the replication of "MMSF: A Multimodal Sentiment-Fused Method to Recognize Video Speaking Style", which was presented at ICMR'23, this companion paper provides the details of the artifacts. Speaking style recognition is aimed at recognizing the styles of conversations, which provides …

cn, jp, ch (code pays fourni par la source)

Semantic-guided RGB-Thermal Crowd Counting with Segment Anything Model

Yaqun Fang, Yi Fang Shi, Jia Bei, Tongwei Ren

RGB-Thermal (RGB-T) crowd counting leverages the complementary nature of visible light and thermal modalities for accurate counting. However, real-world scenarios often introduce challenges, such as misidentifying background elements like trees and lampposts as individuals, leading to inaccurate counts. Existing methods utilize segmentation …

cn (code pays fourni par la source)

ADNet: An Asymmetric Dual-Stream Network for RGB-T Salient Object Detection

Yaqun Fang, Ruichao Hou, Jia Bei, Tongwei Ren et autres

RGB-Thermal salient object detection (RGB-T SOD) aims to locate salient objects in images that include both RGB and thermal information. Previous approaches often suggest designing a symmetric network structure to tackle the challenge of dealing with low-quality RGB or thermal images. However, …

cn (code pays fourni par la source)

Deep Video Understanding with Video-Language Model

Runze Liu, Yaqun Fang, Fan Yu, Ruiming Tian et autres

Pre-trained video-language models (VLMs) have shown superior performance in high-level video understanding tasks, analyzing multi-modal information, aligning with Deep Video Understanding Challenge (DVUC) requirements.In this paper, we explore pre-trained VLMs' potential in multimodal question answering for long-form videos. We propose a solution …

cn, ca (code pays fourni par la source)

MMSF: A Multimodal Sentiment-Fused Method to Recognize Video Speaking Style

Beibei Zhang, Yaqun Fang, Fan Yu, Jia Bei et autres

As talking takes a large proportion of human lives, it is necessary to perform deeper understanding of human conversations. Speaking style recognition is aimed at recognizing the styles of conversations, which provides a fine-grained description about talking. Current works focus on adopting …

cn (code pays fourni par la source)

Measurement of the polarisation of single top quarks and antiquarks produced in the $t$-channel at $\sqrt{s}=13$ TeV and bounds on the $tWb$ dipole operator from the ATLAS experiment

B. Abbott, D. C. Abbott, A. Abed Abud, K. Abeling et autres

A simultaneous measurement of the three components of the top-quark and top-antiquark polarisation vectors in $t$-channel single-top-quark production is presented. This analysis is based on data from proton--proton collisions at a centre-of-mass energy of 13 TeV corresponding to an integrated luminosity of …

fr, de (code pays fourni par la source)

Search for long-lived charginos based on a disappearing-track signature using 136 fb$^{-1}$ of pp collisions at $\sqrt{s}$ = 13 TeV with the ATLAS detector

B. Abbott, J.-H. Arling, L. Halser, K. Hamano et autres

A search for long-lived charginos produced either directly or in the cascade decay of heavy prompt gluino states is presented. The search is based on proton–proton collision data collected at a centre-of-mass energy of $\sqrt{s}$ = 13 T$\text {eV}$ between 2015 and …

fr (code pays fourni par la source)

Network-Aware 5G Edge Computing for Object Detection: Augmenting Wearables to "See" More, Farther and Faster

Zhongzheng Yuan, Tommy Azzino, Yixuan Lyu, Haoyang Pei et autres

Advanced wearable devices are increasingly incorporating high-resolution multi-camera systems. As state-of-the-art neural networks for processing the resulting image data are computationally demanding, there has been growing interest in leveraging fifth generation (5G) wireless connectivity and mobile edge computing for offloading this processing …

Search for heavy particles in the $b$-tagged dijet mass distribution with additional $b$-tagged jets in proton-proton collisions at $\sqrt s$= 13 TeV with the ATLAS experiment

B. Abbott, D. C. Abbott, K. Abeling, D. K. Abhayasinghe et autres

A search optimized for new heavy particles decaying to two $b$-quarks and produced in association with additional b-quarks is reported. The sensitivity is improved by $b$-tagging at least one lower-p$_T$ jet in addition to the two highest-p$_T$ jets. The data used in …

de (code pays fourni par la source)

Observation of electroweak production of two jets in association with an isolated photon and missing transverse momentum, and search for a Higgs boson decaying into invisible particles at 13 TeV with the ATLAS detector

G. Aad, B. Abbott, D. C. Abbott, A. Abed Abud et autres

This paper presents a measurement of the electroweak production of two jets in association with a $Z\gamma$ pair, with the $Z$ boson decaying into two neutrinos. It also presents a search for invisible or partially invisible decays of a Higgs boson with …