arXiv subjects

Dingwei Zhang

Publications and source records attributed to Dingwei Zhang.

6 recordsLinked to original sources

arXiv2025

Mitigating Query Selection Bias in Referring Video Object Segmentation

Recently, query-based methods have achieved remarkable performance in Referring Video Object Segmentation (RVOS) by using textual static object queries to drive cross-modal alignment. However, these static queries are easily misled by distractors with similar appearance or motion, resulting in \emph{query selection bias}. To address this issue, we propose Triple Query Former (TQF), which factorizes the referring query into three specialized components: an appearance query for static attributes, an intra-frame interaction query for spatial relations, and an inter-frame motion query for temporal association. Instead of relying solely on textual embeddings, our queries are dynamically constructed by integrating both linguistic cues and visual guidance. Furthermore, we introduce two motion-aware aggregation modules that enhance object token representations: Intra-frame Interaction Aggregation incorporates position-aware interactions among objects within a single frame, while Inter-frame Motion Aggregation leverages trajectory-guided alignment across frames to ensure temporal coherence. Extensive experiments on multiple RVOS benchmarks demonstrate the advantages of TQF and the effectiveness of our structured query design and motion-aware aggregation modules.

cs.CV↗

arXiv2023

Robust and Efficient Memory Network for Video Object Segmentation

This paper proposes a Robust and Efficient Memory Network, referred to as REMN, for studying semi-supervised video object segmentation (VOS). Memory-based methods have recently achieved outstanding VOS performance by performing non-local pixel-wise matching between the query and memory. However, these methods have two limitations. 1) Non-local matching could cause distractor objects in the background to be incorrectly segmented. 2) Memory features with high temporal redundancy consume significant computing resources. For limitation 1, we introduce a local attention mechanism that tackles the background distraction by enhancing the features of foreground objects with the previous mask. For limitation 2, we first adaptively decide whether to update the memory features depending on the variation of foreground objects to reduce temporal redundancy. Second, we employ a dynamic memory bank, which uses a lightweight and differentiable soft modulation gate to decide how many memory features need to be removed in the temporal dimension. Experiments demonstrate that our REMN achieves state-of-the-art results on DAVIS 2017, with a $\mathcal{J\&F}$ score of 86.3% and on YouTube-VOS 2018, with a $\mathcal{G}$ over mean of 85.5%. Furthermore, our network shows a high inference speed of 25+ FPS and uses relatively few computing resources.

cs.CV↗

arXiv2020

Light Nuclei ($d$, $t$) Production in Au + Au Collisions at $\sqrt{s_{NN}}$ = 7.7 - 200 GeV

In high-energy nuclear collisions, light nuclei can be regarded as a cluster of baryons and their yields are sensitive to the baryon density fluctuations. Thus, the production of light nuclei can be used to study the QCD phase transition, at which the baryon density fluctuation will be enhanced. The yield ratio of light nuclei, defined as $N(t)$$\times$$N(p)$/$N^2(d)$, is predicted to be sensitive observable to search for the 1st-order phase transition and/or QCD critical point in heavy-ion collisions. In this paper, we present the energy and centrality dependence of (anti)deuteron and triton production in Au+Au collisions at $\sqrt{s_{\mathrm{NN}}}$ = 7.7, 11.5, 14.5, 19.6, 27, 39, 54.4, 62.4, and 200 GeV measured by the STAR experiment at RHIC. We show beam-energy dependence for the coalescence parameter, $B_2(d)$ and $B_3(t)$, particle ratios, $d/p$, $t/p$, and $t/d$, and the yield ratio of $N(t)$$\times$$N(p)$/$N^2(d)$. More importantly, non-monotonic energy dependence is observed for the yield ratio, $N(t)$$\times$$N(p)$/$N^2(d)$, in 0-10\% central Au+Au collisions with a peak around 20-30 GeV. Their physics implications on QCD critical point search and change of the equation of state will be discussed.

nucl-ex↗

arXiv2020

Light Nuclei Production in Au+Au Collisions at $\sqrt{s_{\mathrm{NN}}}$ = 5-200 GeV from JAM model

Light nuclei production is sensitive to the baryon density fluctuations and can be used to probe the QCD phase transition in relativistic heavy-ion collisions. In this work, we studied the production of proton, deuteron, triton in central Au+Au collisions at $\sqrt{s_{\mathrm{NN}}}$ = 5, 7.7, 11.5, 14.5, 19.6, 27, 39, 54.4, 62.4 and 200 GeV from a transport model (JAM). Based on the coalescence production of light nuclei, we calculated the energy dependence of rapidity density $dN/dy$ and particle ratios ($d/p$, $t/p$, and $t/d$). More importantly, the yield ratio $N_{t} \times N_{p} / N_{d}^{2}$, which is sensitive to the neutron density fluctuations, shows a flat energy dependence and cannot describe the non-monotonic trend observed by the STAR experiment. Based on the nucleon coalescence, this work can provide constraint and reference to search for the QCD critical point and/or first order phase transition with light nuclei production in future heavy-ion collision experiments.

nucl-th↗

arXiv2019

Search for the QCD Critical Point by Transverse Velocity Dependence of Anti-deuteron to Deuteron Ratio

We propose the transverse velocity ($β_T$) dependence of the anti-deuteron to deuteron ratio as a new observable to search for the QCD critical point in heavy-ion collisions. The QCD critical point can attract the system evolution trajectory in the QCD phase diagram, which is known as focusing effect. To quantify this effect, we employ thermal model and hadronic transport model to simulate the dynamical particle emission along a hypothetical focusing trajectory near critical point. We found the focusing effect can lead to anomalous $β_T$ dependence of $\bar{p}/p$, $\bar{d}/d$ and $^3\overline{\text{He}}/^3\text{He}$ ratios. We examined the $β_T$ dependence of $\bar{p}/p$ and $\bar{d}/d$ ratios of central Au+Au collisions at $\sqrt{s_{NN}}$ = 7.7 to 200 GeV measured by the STAR experiment at RHIC. Surprisingly, we only observe a negative slope in $β_T$ dependence of $\bar{d}/d$ ratio at $\sqrt{s_{NN}}$ = 19.6 GeV, which indicates the trajectory evolution has passed through the critical region. In the future, we could constrain the location of the critical point and/or width of the critical region by making precise measurements on the $β_T$ dependence of $\bar{d}/d$ ratio at different energies and rapidity.

nucl-th↗

arXiv2019

Energy Dependence of Light Nuclei ($d$, $t$) Production at STAR

In high-energy nuclear collisions, the production of light nuclei is sensitive to the temperature and phase-space density of the system at freeze-out. In addition, the phase transition from QGP to the hadronic phase will lead to large baryon density fluctuation, which will be reflected in the light nuclei production. For example, the ratio of proton ($N(p)$) and triton ($N(t)$) to deuteron ($N(d)$) yields, which is defined as $N(t)$$\cdot$$N(p)$/$N^2(d)$, may be used as a sensitive observable to search for the QCD critical point. In this paper, we will report the energy dependence of light nuclei ($d$, $t$) production in Au+Au collisions at $\sqrt{s_{NN}}$ =7.7, 11.5, 14.5, 19.6, 27, 39, 62.4, and 200 GeV measured by the STAR experiment at RHIC. We will present the beam energy dependence for the coalescence parameter $B_2(d)$ and $B_3(t)$, particle ratios ($d/p$, $t/p$, and $t/d$), and the yield ratio of $N(t)$$\cdot$$N(p)$/$N^2(d)$. Their physics implications will be discussed.

nucl-ex↗