Molecular representation learning, a cornerstone for downstream tasks like molecular captioning and molecular property prediction, heavily relies on Graph Neural Networks (GNN). However, GNN suffers from the over-smoothing problem, where node-level features collapse in deep GNN layers. While existing feature projection methods with cross-attention have been introduced to mitigate this issue, they still perform poorly in deep features. This motivated our exploration of using Mamba as an alternative projector for its ability to handle complex sequences. However, we observe that while Mamba excels at preserving global topological information from deep layers, it neglects fine-grained details in shallow layers. The capabilities of Mamba and cross-attention exhibit a global-local trade-off. To resolve this critical global-local trade-off, we propose Hierarchical and Structure-Aware Network (HSA-Net), a novel framework with two modules that enables a hierarchical feature projection and fusion. Firstly, a Hierarchical Adaptive Projector (HAP) module is introduced to process features from different graph layers. It learns to dynamically switch between a cross-attention projector for shallow layers and a structure-aware Graph-Mamba projector for deep layers, producing high-quality, multi-level features. Secondly, to adaptively merge these multi-level features, we design a Source-Aware Fusion (SAF) module, which flexibly selects fusion experts based on the characteristics of the aggregation features, ensuring a precise and effective final representation fusion. Extensive experiments demonstrate that our HSA-Net framework quantitatively and qualitatively outperforms current state-of-the-art (SOTA) methods.

The complementary nature of depth images and infrared amplitude images enables their fusion to enhance target detection accuracy in vehicle cockpits. Existing detection algorithms primarily focus on single-modal inputs, while multi-modal fusion methods often lack global perception and fail to address cross-modal interaction and redundancy. Moreover, depth maps typically contain noise, limiting the effectiveness of fusion. To overcome these issues, we propose DALFNet, a lightweight CNN-Transformer-based object detection network that enhances depth map quality and effectively integrates depth and infrared amplitude modalities. TransLiteFusion (TLF) is designed to combine self-attention and cross-attention mechanisms to fuse and facilitate interaction between multimodal information. The Depth Restoration Sub-network (DRSN) is employed for ToF depth denoising and enhancement, assisting TLF in achieving accurate fusion. Experiments conducted on several public datasets indicate that DALFNet outperforms state-of-the-art algorithms. The core code is available at https://github.com/ZYH-Lightyear/DALFNet.

Timestamp supervised temporal action segmentation (TSTAS) is more cost-effective than fully supervised counterparts. However, previous approaches suffer from severe label bias due to over-reliance on sparse timestamp annotations, resulting in unsatisfactory performance. In this paper, we propose the Debiasing-TSTAS (D-TSTAS) framework by exploiting unannotated frames to alleviate this bias from two phases: 1) Initialization. To reduce the dependencies on annotated frames, we propose masked timestamp predictions (MTP) to ensure that initialized model captures more contextual information. 2) Refinement. To overcome the limitation of the expressiveness from sparsely annotated timestamps, we propose a center-oriented timestamp expansion (CTE) approach to progressively expand pseudo-timestamp groups which contain semantic-rich motion representation of action segments. Then, these pseudo-timestamp groups and the model output are used to iteratively generate pseudo-labels for refining the model in a fully supervised setup. We further introduce segmental confidence loss to enable the model to have high confidence predictions within the pseudo-timestamp groups and more accurate action boundaries. Our D-TSTAS outperforms the state-of-the-art TSTAS method as well as achieves competitive results compared with fully supervised approaches on three benchmark datasets.

Spiking neural networks (SNNs) have undergone continuous development and extensive study for decades, leading to increased biological plausibility and optimal energy efficiency. However, traditional training methods for deep SNNs have some limitations, as they rely on strategies such as pre-training and fine-tuning, indirect coding and reconstruction, and approximate gradients. These strategies lack a complete training model and require gradient approximation. To overcome these limitations, we propose a novel learning method named Joint Excitatory Inhibitory Cycle Iteration learning for Deep Spiking Neural Networks (EICIL) that integrates both excitatory and inhibitory behaviors inspired by the signal transmission of biological neurons.By organically embedding these two behavior patterns into one framework, the proposed EICIL significantly improves the bio-mimicry and adaptability of spiking neuron models, as well as expands the representation space of spiking neurons. Extensive experiments based on EICIL and traditional learning methods demonstrate that EICIL outperforms traditional methods on various datasets, such as CIFAR10 and CIFAR100, revealing the crucial role of the learning approach that integrates both behaviors during training.

Recently, deep Hamming hashing methods have been proposed for Hamming space retrieval which enables constant-time search by hash table lookups instead of linear scan. When carrying out Hamming space retrieval, for each query datapoint, there is a Hamming ball centered on the query datapoint, and only the datapoints within the Hamming ball are returned as the relevant ones, while those beyond are discarded directly. Thus, to further enhance the retrieval performance, it is a key point for the Hamming hashing methods to decrease the dissimilar datapoints within the Hamming ball. However, nearly all existing Hamming hashing methods cannot effectively penalize the dissimilar pairs within the Hamming ball to push them out. To tackle this problem, in this paper, we propose a novel Weighted Gaussian Loss based Hamming Hashing, called WGLHH, which introduces a weighted Gaussian loss to optimize hashing model. Specifically, the weighted Gaussian loss consists of three parts: a novel Gaussian-distribution based loss, a novel badly-trained-pair attention mechanism and a quantization loss. The Gaussian-distribution based loss is proposed to effectively penalize the dissimilar pairs within the Hamming ball. The badly-trained-pair attention mechanism is proposed to assign a weight for each data pair, which puts more weight on data pairs whose corresponding hash codes cannot preserve original similarity well, and less on those having already handled well. The quantization loss is used to reduce the quantization error. By incorporating the three parts, the proposed weighted Gaussian loss will penalize significantly on the dissimilar pairs within the Hamming ball to generate more compact hashing codes. Extensive experiments on two benchmark datasets show that the proposed method outperforms the state-of-the-art baselines in image retrieval task.