Recent diffusion–graph frameworks such as DiffPose have advanced monocular 2D-to-3D pose lifting by coupling graph convolutional networks (GCNs) with denoising diffusion models. However, their depth is still bounded by the number of explicit attention–GCN blocks, limiting the receptive field under a fixed parameter budget. We propose IDiffPose, short for Implicit Diffusion Pose, an equilibrium substitution that replaces a selected deep block with a weight-tied operator whose representation is computed via a small number of unrolled fixed-point iterations. The training objective remains standard DDPM-style denoising, inference uses a deterministic DDIM sampler, and the forward process injects heteroscedastic Gaussian noise scaled by 2D heat-map uncertainty. Because the same weights are re-used across iterations, the model attains large effective depth with a compact parameter footprint; when non-equilibrium blocks are frozen, the number of trainable parameters drops substantially. On Human3.6M, substituting only the middle block improves MPJPE from 31.55 to 31.10 mm and P-MPJPE from 24.72 to 24.47 mm with 167,521 trainable parameters (vs. 1,025,674 explicit), while making all blocks implicit reaches 30.90/24.51 mm. These results show equilibrium substitution is a practical drop-in upgrade for diffusion-based pose lifting, yielding consistent accuracy with favorable efficiency controls.

Advancements in computer vision research have put transformer architecture as the state-of-the-art in computer vision tasks . One of the known drawbacks of the transformer architecture is the high number of parameters, this can lead to a more complex and inefficient algorithm. This paper aims to reduce the number of parameters and in turn, made the transformer more efficient. We present Sparse Transformer (SparTa) Block, a modified transformer block with an addition of a sparse token converter that reduces the dimension of high-level features to the number of latent tokens. We implemented the SparTa Block within the Swin-T architecture (SparseSwin) to leverage Swin's proficiency in extracting low-level features and enhance its capability to extract information from high-level features while reducing the number of parameters. The proposed SparseSwin model outperforms other state-of-the-art models in image classification with an accuracy of 87.26%, 97.43%, and 85.35% on the ImageNet100, CIFAR10, and CIFAR100 datasets respectively. Despite its fewer parameters, the result highlights the potential of a transformer architecture using a sparse token converter with a limited number of tokens to optimize the use of the transformer and improve its performance. The code is available at https://github.com/KrisnaPinasthika/SparseSwin .

One of the problems experienced by micro, small, and medium enterprises (MSMEs) during this pandemic is that most MSME actors do not understand plan-making during a crisis. This situation was exacerbated by erratic commodity prices, which resulted in several MSME players choosing to temporarily close because their turnover got a drastic decline. To help MSME actors maintain their business by knowing commodity price predictions, we propose a deep learning model using the long short-term memory (LSTM) method to predict commodity prices in Indonesia. LSTM is a type of recurrent neural network (RNN) with a memory cell to store information and solve the vanishing gradient problem in RNN. Furthermore, multivariate LSTM leverages the model to predict datasets with more than one feature. This study used a dataset collected from the Pusat Informasi Harga Pangan Strategis Nasional (PIHPS Nasional) managed by the Indonesian Ministry of Finance and Bank Indonesia consisting of significantly contributed food commodities to the formation of (strategic) inflation rates in Indonesia. The time range of commodity prices is from August 1, 2017, to July 30, 2021. There are 11 commodity price features in the dataset, namely, rice, chicken meat, eggs, onions, garlic, large red chilies, curly red chilies, red chilies, green chilies, cooking oil, and sugar. The lowest mean absolute error (MAE) on prediction is up to 255.998 obtained by the attention multivariate LSTM model with the Adam optimizer, adding batch normalization (Batchnorm) layer, reducing LSTM layer, hidden size, and grouped features. It makes the prediction more accurate and avoids overfitting and underfitting in this case.

This paper proposes an texture segmentation algorithm. In the proposed texture segmentation algorithm, the feature vectors at each pixel of an input image are extracted by using the deep neural networks such as the deep convolutional network (CNN) or the Siamese Network. Then they are used as input of the hierarchical region merging. Unlike the semantic segmentation such as fully connected network (FCN) or U-Net which are based on the supervised learning, the proposed algorithm can correctly segment the texture regions whose texture is taken from the other types of the texture. The effectiveness of the proposed texture segmentation algorithm is experimentally confirmed by using the famous texture images taken from book by P. Brodatz.

We propose method for fast action recognition and comparable performance using local autocorrelation of optical flows over time. To capture action movement, dense optical flows is generated along sequence of video. Optical flows sometimes yield noise of motions that distract object of interest from another object motions and background. We suppress this by using edge based optical flow. The HOF vector is extracted from each window resolution and correlate its consecutive flow fields within cycle using local autocorrelation over time. It will gather richer information from movement while also gaining discriminative features than standard histogram methods. Comparison shows that the comparable performance is achieved over state of the arts.