0000000001176468
AUTHOR
Yifei Zhang
Experimental Evidence for an Attractive p-φ Interaction
Physical review letters 127(17), 172301 (2021). doi:10.1103/PhysRevLett.127.172301
Incorporating depth information into few-shot semantic segmentation
International audience; Few-shot segmentation presents a significant challengefor semantic scene understanding under limited supervision.Namely, this task targets at generalizing the segmentationability of the model to new categories given a few samples.In order to obtain complete scene information, we extend theRGB-centric methods to take advantage of complementary depthinformation. In this paper, we propose a two-stream deep neuralnetwork based on metric learning. Our method, known as RDNet,learns class-specific prototype representations within RGB anddepth embedding spaces, respectively. The learned prototypesprovide effective semantic guidance on the corresponding RGBand depth query ima…
Kaon-proton strong interaction at low relative momentum via femtoscopy in Pb-Pb collisions at the LHC
Physics letters / B 822, 136708 (2021). doi:10.1016/j.physletb.2021.136708
Multiscale Attention-Based Prototypical Network For Few-Shot Semantic Segmentation
International audience; Deep learning-based image understanding techniques require a large number of labeled images for training. Few-shot semantic segmentation, on the contrary, aims at generalizing the segmentation ability of the model to new categories given only a few labeled samples. To tackle this problem, we propose a novel prototypical network (MAPnet) with multiscale feature attention. To fully exploit the representative features of target classes, we firstly extract rich contextual information of labeled support images via a multiscale feature enhancement module. The learned prototypes from support features provide further semantic guidance on the query image. Then we adaptively i…
Study of very forward energy and its correlation with particle production at midrapidity in pp and p-Pb collisions at the LHC
Journal of high energy physics 08(8), 86 (2022). doi:10.1007/JHEP08(2022)086
Analyse et fusion d’images multimodales pour la navigation autonome
Robust semantic scene understanding is challenging due to complex object types, as well as environmental changes caused by varying illumination and weather conditions. This thesis studies the problem of deep semantic segmentation with multimodal image inputs. Multimodal images captured from various sensory modalities provide complementary information for complete scene understanding. We provided effective solutions for fully-supervised multimodal image segmentation and few-shot semantic segmentation of the outdoor road scene. Regarding the former case, we proposed a multi-level fusion network to integrate RGB and polarimetric images. A central fusion framework was also introduced to adaptiv…
Λc+ Production and Baryon-to-Meson Ratios in pp and p -Pb Collisions at sNN=5.02 TeV at the LHC
The prompt production of the charm baryon Λ c + and the Λ c + / D 0 production ratios were measured at midrapidity with the ALICE detector in p p and p -Pb collisions at s NN = 5.02 TeV . These new measurements show a clear decrease of the Λ c + / D 0 ratio with increasing transverse momentum ( p T ) in both collision systems in the range 2 p T 12 GeV / c , exhibiting similarities with the light-flavor baryon-to-meson ratios p / π and Λ / K S 0 . At low p T , predictions that include additional color-reconnection mechanisms beyond the leading-color approximation, assume the existence of additional higher-mass charm-baryon states, or include hadronization via coalescence can describe the dat…
Outdoor Scenes Pixel-wise Semantic Segmentation using Polarimetry and Fully Convolutional Network
International audience; In this paper, we propose a novel method for pixel-wise scene segmentation application using polarimetry. To address the difficulty of detecting highly reflective areas such as water and windows, we use the angle and degree of polarization of these areas, obtained by processing images from a polarimetric camera. A deep learning framework, based on encoder-decoder architecture, is used for the segmentation of regions of interest. Different methods of augmentation have been developed to obtain a sufficient amount of data, while preserving the physical properties of the polarimetric images. Moreover, we introduce a new dataset comprising both RGB and polarimetric images…
First study of the two-body scattering involving charm hadrons
Physical review / D 106(5), 052010 (2022). doi:10.1103/PhysRevD.106.052010
Deep multimodal fusion for semantic image segmentation: A survey
International audience; Recent advances in deep learning have shown excellent performance in various scene understanding tasks. However, in some complex environments or under challenging conditions, it is necessary to employ multiple modalities that provide complementary information on the same scene. A variety of studies have demonstrated that deep multimodal fusion for semantic image segmentation achieves significant performance improvement. These fusion approaches take the benefits of multiple information sources and generate an optimal joint prediction automatically. This paper describes the essential background concepts of deep multimodal fusion and the relevant applications in compute…
Observation of the Dalitz decayη′→γe+e−
We report the first observation of the Dalitz decay eta' -> gamma e(+)e(-), based on a data sample of 1.31 billion J/psi events collected with the BESIII detector. The eta' mesons are produced via the J/psi -> gamma eta' decay process. The ratio (eta' -> gamma e(+)e(-))/Gamma (eta' -> gamma gamma) is measured to be (2.13 +/- 0.09(stat) +/- 0.07(sys)) x 10(-2). This corresponds to a branching fraction B(eta' -> gamma e(+)e(-)) = (4.69 +/- 0.20(stat) +/- 0.23(sys)) x 10(-4). The transition form factor is extracted and different expressions are compared to the measured dependence on the e(+)e(-) invariant mass. The results are consistent with the prediction of the vector meson dominance model.
Charm-quark fragmentation fractions and production cross section at midrapidity in pp collisions at the LHC
Physical review / D 105(1), L011103 (2022). doi:10.1103/PhysRevD.105.L011103
Characterizing the initial conditions of heavy-ion collisions at the LHC with mean transverse momentum and anisotropic flow correlations
Physics letters / B 834, 137393 (2022). doi:10.1016/j.physletb.2022.137393