Arrow Research search

Author name cluster

Di Ma

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers
1 author row

Possible papers

3

EAAI Journal 2025 Journal Article

Low-light image enhancement using dual cross attention

  • Yudi Ruan
  • Hao Ma
  • Di Ma
  • Weikai Li
  • Xiao Wang

Low-light image enhancement (LLIE) aims to improve the perceptibility and interpretability of images captured in poorly illuminated environments. Existing LLIE methods often fail to capture the local self-similarity and long-range dependencies at the same time, causing the loss of complementary information between multiple modules or network layers, ultimately resulting in the loss of image details. To alleviate this issue, we design a hierarchical mutual Enhancement via a dual cross-attention transformer (ECAFormer), which introduces an architecture that enables concurrent propagation and interaction of multiple disentangling features. To capture the local self-similarity, we design a Dual Multi-head Self-Attention (DMSA), which leverages the disentangled visual and semantic features across different scales, allowing them to guide and complement each other. Further, a cross-scale DMSA block is incorporated to capture residual connections, thereby integrating cross-layer information and capturing the long-range dependencies. Experimental results show that the ECAFormer reaches competitive performance across multiple benchmarks, yielding nearly a 3. 7% improvement in Peak Signal-to-Noise Ratio (PSNR) over the suboptimal method, demonstrating the effectiveness of information interaction in LLIE. For facilitating the efforts to replicate our results, our implementation is available on GitHub 1 1 https: //github. com/ruanyudi/ECAFormer.

IJCAI Conference 2018 Conference Paper

Layered Optical Flow Estimation Using a Deep Neural Network with a Soft Mask

  • Xi Zhang
  • Di Ma
  • Xu Ouyang
  • Shanshan Jiang
  • Lin Gan
  • Gady Agam

Using a layered representation for motion estimation has the advantage of being able to cope with discontinuities and occlusions. In this paper, we learn to estimate optical flow by combining a layered motion representation with deep learning. Instead of pre-segmenting the image to layers, the proposed approach automatically generates a layered representation of optical flow using the proposed soft-mask module. The essential components of the soft-mask module are maxout and fuse operations, which enable a disjoint layered representation of optical flow and more accurate flow estimation. We show that by using masks the motion estimate results in a quadratic function of input features in the output layer. The proposed soft-mask module can be added to any existing optical flow estimation networks by replacing their flow output layer. In this work, we use FlowNet as the base network to which we add the soft-mask module. The resulting network is tested on three well-known benchmarks with both supervised and unsupervised flow estimation tasks. Evaluation results show that the proposed network achieve better results compared with the original FlowNet.

I&C Journal 2004 Journal Article

Stack size analysis for interrupt-driven programs

  • Krishnendu Chatterjee
  • Di Ma
  • Rupak Majumdar
  • Tian Zhao
  • Thomas A. Henzinger
  • Jens Palsberg

We study the problem of determining stack boundedness and the exact maximum stack size for three classes of interrupt-driven programs. Interrupt-driven programs are used in many real-time applications that require responsive interrupt handling. In order to ensure responsiveness, programmers often enable interrupt processing in the body of lower-priority interrupt handlers. In such programs a programming error can allow interrupt handlers to be interrupted in a cyclic fashion to lead to an unbounded stack, causing the system to crash. For a restricted class of interrupt-driven programs, we show that there is a polynomial-time procedure to check stack boundedness, while determining the exact maximum stack size is PSPACE-complete. For a larger class of programs, the two problems are both PSPACE-complete, and for the largest class of programs we consider, the two problems are PSPACE-hard and can be solved in exponential time. While the complexities are high, our algorithms are exponential only in the number of handlers, and polynomial in the size of the program.

v2026.09.13