ABSTRACT Zooplankton image classification is important for marine biodiversity monitoring and environmental research. Zooplankton image classification faces several challenges, including complex background noise, intraspecific phenotypic variation, interspecific morphological similarity and limited original data and insufficient training sets. To overcome these limitations, we propose an adaptive gate‐enhanced multi‐feature hybrid fusion‐ShuffleNetV2(AHFNet) algorithm using a transfer learning framework. ShuffleNetV2 is a lightweight convolutional neural network that has been pre‐trained on various large‐scale datasets. Therefore, we adopt the pre‐trained parameters of ShuffleNetV2 from the ImageNet dataset for fine‐tuning, adapting it to zooplankton image classification. We combine three feature channels and concatenate them to form multi‐source inputs to enhance feature complementarity. The three channels include the original feature image, global shape features obtained by Gaussian low‐pass filtering, and local texture features obtained by Gabo filtering. We designed a hybrid fusion module with a conditional gating mechanism that dynamically fuses channel attention (via the Squeeze and excitation module) and spatial attention (via the Parallelized patch‐aware mechanism). A pivotal aspect of our design is the phased network layout: we deploy a standalone SE module in Stage2 to suppress background noise, while the hybrid SE‐PPA module in Stages3 and 4 performs joint channel recalibration and multi‐scale spatial feature capture. This is the first work to adapt and synergize the PPA mechanism with SE for this specific task through optimized stage‐wise integration. Experimental results demonstrate the effectiveness of our method, which achieves accuracy on the Kaggle38 dataset and on the WHOI25 dataset, with ablation studies conclusively validating our design choices.

Text-conditioned motion generation has significant applications across various domains. However, generating natural motion remains challenging due to the vast solution space and the accumulation of errors during motion generation. To address these challenges, a novel hierarchical motion intention decoding-based motion synthesis model named Hi-Motion is proposed, which disentangles human motion into temporal intents of pivot joints and skeleton synthesis guided by intention from a new perspective. Specifically, Hi-Motion first parameterizes pivot joint motion with high-order Bézier curves and constructs a Bézier decoder to generate their trajectories, which serve as motion intention to guide skeleton generation. Secondly, we formulate the generation of skeletons as a graph node transformation problem under the condition of determined edge connections. By incorporating hierarchical joint motion intentions into the graph node features, the spatial details of each frame can be precisely synthesized. The proposed Hi-Motion effectively decouples motion generation into temporal and spatial dimensions through hierarchical motion intention decoding, ensuring coordination and naturalness in the generated motion. Extensive experiments on HumanML3D and KIT-ML datasets substantiate the motion generation capabilities of Hi-Motion. Further analysis demonstrates that Hi-Motion can accurately predict the motion intention of pivot joints and synthesize skeletal details.

Controlling the cyborg rat with the guidance of an unmanned aerial vehicle (UAV) is important yet challenging. UAV can provide a mobile bird’s eye view (BEV) with multiple shooting angles to expand the motion space of the cyborg rat. However, uncertainty is a critical problem arising from the obscure and blurry imaging from UAV and the locomotion willingness of cyborg rats. To solve this problem, we propose the collaborative Rat-UAV navigation (RUN) paradigm. The uncertainty in RUN is formulated using the partially observed Markov decision processes (POMDP) in a perceptual-control framework. First, perceptual uncertainties in rat pose estimation and environmental modeling are reduced. Second, control policies are delivered to maximize rewards and minimize control uncertainties until the cyborg rat reaches the target. To achieve this, RUN can accurately detect tiny rats with fewer parameters, dynamically plan paths with partial observations from the UAV, and stably control the rat using a locomotion willingness transition graph in a large practical arena. Our framework is tested in real-world experiments. For the first time, a cyborg rat successfully completed a navigation task with the guidance of a UAV.Note to Practitioners—This paper studies, for the first time, the problem of navigating a cyborg rat with the guidance of an unmanned aerial vehicle (UAV). Most existing researches on the autonomous navigation of cyborg rats are conducted in fully observed environments with fixed cameras, disregarding uncertainties in complex environmental perception and rat control. In this paper, we propose a collaborative Rat-UAV navigation (RUN) paradigm, which formulates uncertainties using the partially observed Markov decision processes (POMDP). Specifically, RUN enhances the cyborg rat’s interaction with the UAV in the navigation environment. First, it narrows the gap between the rat’s perceived and actual states by utilizing keypoint detection, dynamic environment modeling, and locomotion willingness estimation from the view of the UAV. Secondly, RUN constructs a policy generation module to maximize the reward of controlling the cyborg rat, based on a locomotion willingness transition graph. Experimental results demonstrate that our framework effectively guides the cyborg rat through a large maze, followed by six targets, with the assistance of the UAV. In future researches, we will investigate the real-time prediction of rat locomotion willingness using multimodal neuroethological recordings, towards a bidirectional brain computer interface between rats and UAVs.

Animal pose estimation is often constrained by the scarcity of annotations and the diversity of scenarios and species. The pseudo-label generation based unsupervised domain adaptation paradigm, which discriminates the predicted keypoints of unlabeled data based on the skeleton position consistency, has demonstrated effectiveness for such problems. However, existing methods generate pseudo-labels with massive false positives, because they cannot effectively distinguish sample pairs with the same errors. In this study, we propose a cross-domain animal pose estimation model from a novel perspective of skeleton anomaly learning. We construct a graph contrastive learning mechanism to acquire the skeleton anomaly-aware knowledge, which enables the generation of accurate pseudo-labels for target domain and imposes graph constraint on unlabeled data. And a skeleton anomaly-feedback based domain adaptation framework is designed to facilitate implicit alignment of object-specific features and joint training of cross-domain. Besides, we propose a novel rat pose dataset named UDARP-9.4K to address the gap of small-sized animal pose datasets encompassing diverse experimental scenarios. The related datasets are reviewed and evaluated in detail. Extensive experiments are conducted on UDARP-9.4K and two public datasets to demonstrate the superiority of the proposed model in cross-scenarios and cross-species animal pose estimation tasks. Further analysis reveals the effectiveness of the proposed model for skeleton structure feature learning.The UDARP-9.4K dataset is available here.

Channel attention mechanisms endeavor to recalibrate channel weights to enhance representation abilities of networks. However, mainstream methods often rely solely on global average pooling as the feature squeezer, which significantly limits the overall potential of models. In this paper, we investigate the statistical moments of feature maps within a neural network. Our findings highlight the critical role of high-order moments in enhancing model capacity. Consequently, we introduce a flexible and comprehensive mechanism termed Extensive Moment Aggregation (EMA) to capture the global spatial context. Building upon this mechanism, we propose the Moment Channel Attention (MCA) framework, which efficiently incorporates multiple levels of moment-based information while minimizing additional computation costs through our Cross Moment Convolution (CMC) module. The CMC module via channel-wise convolution layer to capture multiple order moment information as well as cross channel features. The MCA block is designed to be lightweight and easily integrated into a variety of neural network architectures. Experimental results on classical image classification, object detection, and instance segmentation tasks demonstrate that our proposed method achieves state-of-the-art results, outperforming existing channel attention methods.

In the field of pose estimation, keypoint representations can take the form of Gaussian heatmaps, classification vectors, or direct coordinates. However, the current networks suffer from a lack of consistency with these keypoint representations. They only accommodate these representations in the final layer, resulting in suboptimal efficiency and requiring a high number of parameters or computational resources. In this paper, we propose a simple yet efficient plug-and-play module, named the Implicit Decouple Module (IDM), which decouples features into two parts along the x-y axes and aggregates features in a direction-aware manner. This approach implicitly fuses direction-specific coordinate information, improving the consistency with the keypoint representations, especially in vector form. Furthermore, we introduce a fully convolutional backbone network, named the Implicit Decouple Network (IDN), which incorporates IDM without the need to maintain high-resolution features, dense multi-level feature fusion, or lots of repeated stages, while still achieving high performance. In experiments on the COCO dataset, our basic IDN without pre-training can outperform HRNet (28.5M) by 2.4 AP with 18.2M parameters, and even surpass some transformer-based methods. In the lightweight model scenario, our model outstrips Lite-HRNet by 3.9 AP with only 2.5M parameters. We also evaluate our model on the person instance segmentation task and other datasets, demonstrating its generality and effectiveness. http(s)://znk.ink/su/mm23idn.

Domain adaptation tries to adapt a model trained from a source domain to a different but related target domain. Currently, prevailing methods for domain adaptation rely on either instance reweighting or feature transformation. Unfortunately, instance reweighting has difficulty in estimating the sample weights as the dimension increases, whereas feature transformation sometimes fails to make the transformed source and target distributions similar when the cross-domain discrepancy is large. In order to overcome the shortcomings of both methodologies, in this article, we model the unsupervised domain adaptation problem under the generalized covariate shift assumption and adapt the source distribution to the target distribution in a subspace by applying a distribution adaptation function. Accordingly, we propose two frameworks: Bregman-divergence-embedded structural risk minimization (BSRM) and joint structural risk minimization (JSRM). In the proposed frameworks, the subspace distribution adaptation function and the target prediction model are jointly learned. Under certain instantiations, convex optimization problems are derived from both frameworks. Experimental results on the synthetic and real-world text and image data sets show that the proposed methods outperform the state-of-the-art domain adaptation techniques with statistical significance.

The problem of recovering missing data of an incomplete tensor has drawn more and more attentions in the fields of pattern recognition, machine learning, data mining, computer vision, and signal processing. Researches on this problem usually share a common assumption that the original tensor is of low-rank. One of the important ways to capture the low-rank structure of the incomplete tensor is based on tensor factorization. For the traditional tensor factorization algorithms, the tensor ranks should be specified ahead, which is not reasonable in real applications. To overcome this drawback, an adaptive algorithm is first presented based on sequentially truncated higher order singular value decomposition (ST-HOSVD) for fast low-rank approximation of complete tensor, in which the tensor ranks can be obtained adaptively. Then for tensor with missing data, we use adaptive ST-HOSVD and the average operator of low-rank approximation to improve the accuracy of the fulfilled tensor. Convergence analysis of the proposed algorithm is also given in this paper. The experimental results on 14 image datasets and three video datasets show that the proposed method outperforms the state-of-the-art methods in terms of running time and the accuracy.

The simultaneous removal of noise and preservation of the integrity of 3-D magnetic resonance (MR) images is a difficult and important task. In this paper, we consider characterizing MR images with 3-D operators, and present a novel 4-D transform-domain method termed 'modified nonlocal tensor-SVD (MNL-tSVD)' for MR image denoising. The proposed method is based on the grouping, hard-thresholding and aggregation paradigms, and can be viewed as a generalized nonlocal extension of tensor-SVD (t-SVD). By keeping MR images in its natural three-dimensional form, and collaboratively filtering similar patches, MNL-tSVD utilizes both the self-similarity property and 3-D structure of MR images to preserve more actual details and minimize the introduction of new artifacts. We show the adaptability of MNL-tSVD by incorporating it into a two-stage denoising strategy with a few adjustments. In addition, analysis of the relationship between MNL-tSVD and current the state-of-the-art 4-D transforms is given. Experimental comparisons over simulated and real brain data sets at different Rician noise levels show that MNL-tSVD can produce competitive performance compared with related approaches.