Time series forecasting is essential across diverse domains. While MLP-based methods have gained attention for achieving Transformer-comparable performance with fewer parameters and better robustness, they face critical limitations including loss of weak seasonal signals, capacity constraints in weight-sharing MLPs, and insufficient channel fusion in channel-independent strategies. To address these challenges, we propose MDMLP-EIA (Multi-domain Dynamic MLPs with Energy Invariant Attention) with three key innovations. First, we develop an adaptive fused dual-domain seasonal MLP that categorizes seasonal signals into strong and weak components. It employs an adaptive zero-initialized channel fusion strategy to minimize noise interference while effectively integrating predictions. Second, we introduce an energy invariant attention mechanism that adaptively focuses on different feature channels within trend and seasonal predictions across time steps. This mechanism maintains constant total signal energy to align with the decomposition-prediction-reconstruction framework and enhance robustness against disturbances. Third, we propose a dynamic capacity adjustment mechanism for channel-independent MLPs. This mechanism scales neuron count with the square root of channel count, ensuring sufficient capacity as channels increase. Extensive experiments across nine benchmark datasets demonstrate that MDMLP-EIA achieves state-of-the-art performance in both prediction accuracy and computational efficiency.

Accurate camera calibration is essential for obtaining precise three-dimensional information of a target. However, in the froth flotation process, it is challenging to position the calibration board support surfaces correctly. This difficulty makes it hard to capture high-quality calibration images from various angles, ultimately impacting the accuracy of the calibration results. To address this issue, we propose a planar template camera calibration method based on convolutional neural networks and synthetic data augmentation. Initially, we establish a virtual imaging scene to map the relationship between the feature map and camera parameters. Then, we conduct coarse camera calibration and apply synthetic data augmentation within specific range constraints to create a comprehensive calibration dataset. After that, we develop a deep calibration network named FSC-McCNN to facilitate the correspondence between the calibration feature map and camera parameters. This network comprises feature spatial coding (FSC) and multichannel convolutional neural networks (McCNN). The proposed approach effectively compensates for changes in camera focal length and requires only a single calibration image, thereby reducing the calibration workload at flotation sites. Experiments conducted on synthetic and real flotation datasets demonstrate the effectiveness and robustness of the proposed method.

Cross-modal matching shows enormous potential to recognize objects across different sensory modalities, which is fundamental to numerous visual-language tasks like image-text retrieval and visual captioning. Existing works generally rely on massive and well-aligned data pairs for model training. Unfortunately, multimodal datasets are extremely difficult to annotate and collect. As an alternative, the co-occurred data pairs collected from the internet have been widely exploited to train a cross-modal matching model. However, the cheaply-collected dataset unavoidably contains mismatched pairs (i.e., noisy correspondence), which are detrimental to the matching model. In this paper, we propose an alternative method termed noisy correspondence rectification via Asymmetric Similarity Learning (ASL), and it allows for dealing with insufficient learning of positive and negative pairs caused by the popular triplet-based symmetric learning fashion. Specifically, the learning of positive or negative pairs within a triplet is conducted in an asymmetric fashion, and the self-paced weighting boundary is imposed on positive pairs to mitigate the effect of noise. Meanwhile, the optimization of negative samples will not be affected in the process of punishing potentially-noisy positive samples. To verify the effectiveness of our proposed approach, a series of experiments are conducted on three widely-used benchmarks (i.e., Flick30k, MS-COCO and CC152k), and the results show superior performance compared to the state-of-the-art methods.

Reinforcement Learning (RL) has emerged as a powerful tool for neural combinatorial optimization, enabling models to learn heuristics that solve complex problems without requiring expert knowledge. Despite significant progress, existing RL approaches face challenges such as diminishing reward signals and inefficient exploration in vast combinatorial action spaces, leading to inefficiency. In this paper, we propose **Preference Optimization**, a novel method that transforms quantitative reward signals into qualitative preference signals via statistical comparison modeling, emphasizing the superiority among sampled solutions. Methodologically, by reparameterizing the reward function in terms of policy and utilizing preference models, we formulate an entropy-regularized RL objective that aligns the policy directly with preferences while avoiding intractable computations. Furthermore, we integrate local search techniques into the fine-tuning rather than post-process to generate high-quality preference pairs, helping the policy escape local optima. Empirical results on various benchmarks, such as the Traveling Salesman Problem (TSP), the Capacitated Vehicle Routing Problem (CVRP) and the Flexible Flow Shop Problem (FFSP), demonstrate that our method significantly outperforms existing RL algorithms, achieving superior convergence efficiency and solution quality.

Complex imaging environments and conditions in real-world scenes pose significant challenges for stereo matching tasks. Models are susceptible to underperformance in non-Lambertian surfaces, weakly textured regions, and occluded regions, due to the difficulty in establishing accurate matching relationships between pixels. To alleviate these problems, we propose a multi-scale geometrically enhanced stereo matching model that exploits the geometric structural relationships of the objects in the scene to mitigate these problems. Firstly, a geometric structure perception module is designed to extract geometric information from the reference view. Secondly, a geometric structure-adaptive embedding module is proposed to integrate geometric information with matching similarity information. This module integrates multi-source features dynamically to predict disparity residuals in different regions. Third, a geometric-based normalized disparity correction module is proposed to improve matching robustness for pathological regions in realistic complex scenes. Extensive evaluations on popular benchmarks demonstrate that our method achieves competitive performance against leading approaches. Notably, our model provides robust and accurate predictions in challenging regions containing edges, occlusions, reflective, and non-Lambertian surfaces. Our source code will be publicly available.