Publications from 2021 to 2026
Filter Showing 10 of 659 papers
Research on methane concentration prediction method based on non-steady-state feature coupling interaction and structural perception loss
1Multi-scale investigation of copper corrosion mitigation in sulfuric acid using Gelsemium elegans extract
Multiscale decomposition and fuzzy-rule attention: A transferable cross-basin framework for long-term water quality forecasting.
Reliable measurement of double probe in low-density plasmas
Synergistic antioxidant-antimicrobial-immunomodulatory self-healing “radical sponge” hydrogel for diabetic wound regeneration via microenvironment reprogramming mediated by coordinated MAPK suppression and PI3K-AKT activation
Correctformer: A transformer architecture for correcting periodic drift in time-series forecasting.
1DDformer: Transformer with dynamic variable fusion and dynamic difference attention for multivariate time series long-term forecasting
Fabrication of catalyst-free silver-plated polystyrene microspheres and their application in epoxy conductive adhesive
Dynamic Study of a Class of Stochastic Marine Viruses with Ornstein-Uhlenbeck Process
Dual-level Adaptation for Multi-Object Tracking: Building Test-Time Calibration from Experience and Intuition
Multiple Object Tracking (MOT) has long been a fundamental task in computer vision, with broad applications in various real-world scenarios. However, due to distribution shifts in appearance, motion pattern, and catagory between the training and testing data, model performance degrades considerably during online inference in MOT. Test-Time Adaptation (TTA) has emerged as a promising paradigm to alleviate such distribution shifts. However, existing TTA methods often fail to deliver satisfactory results in MOT, as they primarily focus solely on frame-level adaptation while neglecting temporal consistency and identity association across frames and videos. Inspired by human decision-making process, this paper propose a Test-time Calibration from Experience and Intuition (TCEI) framework. In this framework, the Intuitive system utilizes transient memory to recall recently observed objects for rapid predictions, while the Experiential system leverages the accumulated experience from prior test videos to reassess and calibrate these intuitive predictions. Furthermore, both confident and uncertain objects during online testing are exploited as historical priors and reflective cases, respectively, enabling the model to adapt to the testing environment and alleviate performance degradation. Extensive experiments demonstrate that the proposed TCEI framework consistently achieves superior performance across multiple benchmark datasets and significantly enhances the model's adaptability under distribution shifts. The code will be released at https://github.com/1941Zpf/TCEI.
Read more
Copyright 2026 Cactus Communications. All rights reserved.
