Achieving 3D hand-object pose estimation in interaction scenarios is challenging due to the severe occlusion generated during the interaction. Existing methods address this issue by utilizing the correlation between the hand and object poses as additional cues. They usually first extract the hand and object features from their respective regions and then refine them with each other. However, this paradigm disregards the role of a broad range of image context. To address this problem, we propose a novel and robust approach that learns a broad range of context by imposing priors. First, we build this approach using stacked transformer decoder layers. These layers are required for extracting image-wide context and regional hand or object features by constraining cross-attention operations. We share the context decoder layer parameters between the hand and object pose estimations to avoid interference in the context-learning process. This imposes a prior, indicating that the hand and object are mutually the most important context for each other, significantly enhancing the robustness of obtained context features. Second, since they play different roles, we provide customized feature maps for the context, hand, and object decoder layers. This strategy facilitates the disentanglement of these layers, reducing the feature learning complexity. Finally, we conduct extensive experiments on the popular HO3D and Dex-YCB databases. The experimental results indicate that our method significantly outperforms state-of-the-art approaches and can be applied to other hand pose estimation tasks. Code is available at https://github.com/zskuang58/LCP.

Estimating the 3D poses of interacting hands from a monocular image is challenging due to the similarity in appearance between hand parts. Therefore, utilizing the appearance features alone tends to result in unreliable pose estimation. Existing approaches directly fuse the appearance features with position features, ignoring that the two types of features are heterogeneous. Here, the appearance features are derived from the RGB values of pixels, while the position features are mapped from the coordinates of pixels or joints. To address this problem, we present a novel framework called Decoupled Feature Learning (DFL ) for 3D pose estimation of interacting hands. By decoupling the appearance and position features, we facilitate the interactions within each feature type and those between both types of features. First, we compute the appearance relationships between the joint queries and the image feature maps; we utilize these relationships to aggregate each joint's appearance and position features. Second, we compute the 3D spatial relationships between hand joints using their position features; we utilize these relationships to guide the feature enhancement of joints. Third, we calculate appearance relationships and spatial relationships between the joints and image using the appearance and position features, respectively; we utilize these complementary relationships to promote the joints' location in the image. The two processes mentioned above are conducted iteratively. Finally, only the refined position features are used for hand pose estimation. This strategy avoids the step of mapping heterogeneous appearance features to hand-joint positions. Our method significantly outperforms state-of-the-art methods on the large-scale InterHand2.6M dataset. More impressively, our method exhibits strong generalization ability on in-the-wild images.

SUMMARY: To address the challenges in single-cell metabolomics (SCM) research, we have developed an open-source Python-based modular library, named SCMeTA, for SCM data processing. We designed standardized pipeline and inter-container communication format and have developed modular components to adapt to the diverse needs of SCM studies. The validation was carried out on multiple SCM experiment data. The results demonstrated significant improvements in batch effects, accuracy of results, metabolic extraction rate, cell matching rate, as well as processing speed. This library is of great significance in advancing the practical application of SCM analysis and makes a foundation for wide-scale adoption in biological studies. AVAILABILITY AND IMPLEMENTATION: SCMeTA is freely available on https://github.com/SCMeTA/SCMeTA and https://doi.org/10.5281/zenodo.13569643.

The dynamic reservoir of the randomly generated Echo State Network(ESN) contains numerous redundant neurons, resulting in collinearity in the high-dimensional state space matrix. This collinearity impacts the prediction performance of the network. In order to address this issue, this paper introduces a self-organizing ESN structure optimization model that is based on reinforcement learning, called SR-ESN. The SR-ESN model employs pruning methods to reconstruct the reservoir using contribution and decision mechanisms. To mitigate potential instability caused by high coupling among neurons in a single reservoir, the concept of ensemble learning is applied to create multiple initial reservoir pools, thereby enhancing screening diversity. Simultaneously, the model utilizes reinforcement learning's decision mechanism to identify effective neurons. Neurons with low contribution are pruned, while those with high contribution are retained for self-organizing reconstruction. This optimization of the network structure enhances its prediction performance. Based on both artificial and real datasets, the proposed SR-ESN model demonstrates superior prediction performance with minimal structural complexity compared to other prediction models.

Joint hand and object pose estimation from a single image is extremely challenging as serious occlusion often occurs when the hand and object interact. Existing approaches typically first extract coarse hand and object features from a single backbone, then further enhance them with reference to each other via interaction modules. However, these works usually ignore that the hand and object are competitive in feature learning, since the backbone takes both of them as foreground and they are usually mutually occluded. In this paper, we propose a novel Harmonious Feature Learning Network (HFL-Net). HFL-Net introduces a new framework that combines the advantages of single-and double-stream backbones: it shares the parameters of the low-and high-level convolutional layers of a common ResNet-50 model for the hand and object, leaving the middle-level layers unshared. This strategy enables the hand and the object to be extracted as the sole targets by the middle-level layers, avoiding their competition in feature learning. The shared high-level layers also force their features to be harmonious, thereby facilitating their mutual feature enhancement. In particular, we propose to enhance the feature of the hand via concatenation with the feature in the same location from the object stream. A subsequent self-attention layer is adopted to deeply fuse the concatenated feature. Experimental results show that our proposed approach consistently outperforms state-of-the-art methods on the popular HO3D and Dex-Ycb databases. Notably, the performance of our model on hand pose estimation even surpasses that of existing works that only perform the single-hand pose estimation task. Code is available at https://github.com/lzjJf12/HFL-Net.

We consider streaming over a blockage channel with long feedback delay, as arises in, e.g., real-time satellite communication from a comm-on-the-move (COTM) terminal. For this problem, we introduce a definition of delay that captures the real-time nature of the problem, which we show grows at least as fast as O(log(k)) for memoryless channels, where k corresponds to the number of packets in the transmission. Moreover, a tradeoff exists between this delay and a natural notion of throughput we introduce to capture the bandwidth requirements of the communication. We develop and analyze an efficient "multi-burst" transmission (MBT) protocol for achieving good delay-throughput tradeoffs within this framework, which we show to be robust and near-optimal within the class of retransmission protocols with fixed schedules. The MBT protocol can be augmented with coding for additional performance gains. Simulations validate the new protocols, including when peak bandwidth and delay constraints are imposed.

It is well-known that using multiple antennas can substantially increase the data rate and robustness of communication systems in a fading environment. It was recently established that there is a tradeoff between these two types of gains, termed diversity-multiplexing tradeoff. We develop a family of short structured space-time block codes that achieves the optimal tradeoff for the two-transmit two-receive antenna system with the minimum delay of two necessary for optimality. It uses the idea of rotation of cross-diagonal entries of an uncoded system to achieve spreading of information across space and time to obtain the maximum diversity while preserving multiplexing gain. Rotation angles that are optimal in terms of a determinant criterion and universal for all rates are identified. Performance analysis and simulation results are presented to demonstrate the achieved tradeoff.

Lattice-reduction (LR) techniques are developed for enhancing the performance of multiple-input multiple-output (MIMO) digital communication systems. When used in conjunction with traditional linear and nonlinear detectors, LR techniques substantially close the gap to fundamental performance limits with little additional system complexity. Results for individual channels and ensembles are developed, and illustrated in detail for the case of small (2 /spl times/ 2), uncoded, coherent systems. For example, we show that, relative to the maximum likelihood bound, LR techniques get us within 3dB for any Gaussian channel, and allow us to achieve the same diversity on the Rayleigh fading channel, when sufficiently large constellations are used.

In the presence of bit errors, variable length (VL) codes often suffer from a loss of synchronization, which leads to spans of symbol errors. It is of our interest to investigate whether the redundancy introduced by multiple description (MD) coding is useful for improving performance. We consider a sequence of i.i.d. source symbols of known length, first quantized, then coded using MD VL codes and transmitted over a binary symmetric channel (BSC). We propose a maximum a posteriori probability (MAP) decoder, in which the optimal sequence with the right number of symbols and bits is found using the Viterbi algorithm. We compare the MD VL code performance against a conventional single description (SD) VL entropy code, and against a single description (SD) parity code.