Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos

Skeleton Action Recognition (SAR) involves identifying human actions using skeletal joint coordinates and their interconnections. While plain Transformers have been attempted for this task, they still fall short compared to the current leading methods, which are rooted in Graph Convolutional Networks (GCNs) due to the absence of structural priors. Recently, a novel selective state space model, Mamba, has surfaced as a compelling alternative to the attention mechanism in Transformers, offering efficient modeling of long sequences. In this work, to the utmost extent of our awareness, we present the first SAR framework incorporating Mamba. Each fundamental block of our model adopts a novel U-ShiftGCN architecture with Mamba as its core component. The encoder segment of the U-ShiftGCN is devised to extract spatial features from the skeletal data using downsampling vanilla Shift S-GCN blocks. These spatial features then undergo intermediate temporal modeling facilitated by the Mamba block before progressing to the encoder section, which comprises vanilla upsampling Shift S-GCN blocks. Additionally, a Shift T-GCN (ShiftTCN) temporal modeling unit is employed before the exit of each fundamental block to refine temporal representations. This particular integration of downsampling spatial, intermediate temporal, upsampling spatial, and ultimate temporal subunits yields promising results for skeleton action recognition. We dub the resulting model \textbf{Simba}, which attains state-of-the-art performance across three well-known benchmark skeleton action recognition datasets: NTU RGB+D, NTU RGB+D 120, and Northwestern-UCLA. Interestingly, U-ShiftGCN (Simba without Intermediate Mamba Block) by itself is capable of performing reasonably well and surpasses our baseline.

LATIS: Lambda Abstraction-based Thermal Image Super-resolution

Single image super-resolution (SISR) is an effective technique to improve the quality of low-resolution thermal images. Recently, transformer-based methods have achieved significant performance in SISR. However, in the SR task, only a small number of pixels are involved in the transformers self-attention (SA) mechanism due to the computational complexity of the attention mechanism. The lambda abstraction is a promising alternative to SA in modeling long-range interactions while being computationally more efficient. This paper presents lambda abstraction-based thermal image super-resolution (LATIS), a novel lightweight architecture for SISR of thermal images. LATIS sequentially captures local and global information using the local and global feature block (LGFB). In LGFB, we introduce a global feature extraction (GFE) module based on the lambda abstraction mechanism, channel-shuffle and convolution (CSConv) layer to encode local context. Besides, to improve the performance further, we propose a differentiable patch-wise histogram-based loss function. Experimental results demonstrate that our LATIS, with the least model parameters and complexity, achieves better or comparable performance with state-of-the-art methods across multiple datasets.

Histopathological Image Analysis with Style-Augmented Feature Domain Mixing for Improved Generalization

Histopathological images are essential for medical diagnosis and treatment planning, but interpreting them accurately using machine learning can be challenging due to variations in tissue preparation, staining and imaging protocols. Domain generalization aims to address such limitations by enabling the learning models to generalize to new datasets or populations. Style transfer-based data augmentation is an emerging technique that can be used to improve the generalizability of machine learning models for histopathological images. However, existing style transfer-based methods can be computationally expensive, and they rely on artistic styles, which can negatively impact model accuracy. In this study, we propose a feature domain style mixing technique that uses adaptive instance normalization to generate style-augmented versions of images. We compare our proposed method with existing style transfer-based data augmentation methods and found that it performs similarly or better, despite requiring less computation and time. Our results demonstrate the potential of feature domain statistics mixing in the generalization of learning models for histopathological image analysis.

Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance

The adaptation capability to a wide range of domains is crucial for scene text spotting models when deployed to real-world conditions. However, existing state-of-the-art (SOTA) approaches usually incorporate scene text detection and recognition simply by pretraining on natural scene text datasets, which do not directly exploit the intermediate feature representations between multiple domains. Here, we investigate the problem of domain-adaptive scene text spotting, i.e., training a model on multi-domain source data such that it can directly adapt to target domains rather than being specialized for a specific domain or scenario. Further, we investigate a transformer baseline called Swin-TESTR to focus on solving scene-text spotting for both regular and arbitrary-shaped scene text along with an exhaustive evaluation. The results clearly demonstrate the potential of intermediate representations to achieve significant performance on text spotting benchmarks across multiple domains (e.g. language, synth-to-real, and documents). both in terms of accuracy and efficiency.

ViLP: Knowledge Exploration using Vision, Language, and Pose Embeddings for Video Action Recognition

Video Action Recognition (VAR) is a challenging task due to its inherent complexities. Though different approaches have been explored in the literature, designing a unified framework to recognize a large number of human actions is still a challenging problem. Recently, Multi-Modal Learning (MML) has demonstrated promising results in this domain. In literature, 2D skeleton or pose modality has often been used for this task, either independently or in conjunction with the visual information (RGB modality) present in videos. However, the combination of pose, visual information, and text attributes has not been explored yet, though text and pose attributes independently have been proven to be effective in numerous computer vision tasks. In this paper, we present the first pose augmented Vision-language model (VLM) for VAR. Notably, our scheme achieves an accuracy of 92.81% and 73.02% on two popular human video action recognition benchmark datasets, UCF-101 and HMDB-51, respectively, even without any video data pre-training, and an accuracy of 96.11% and 75.75% after kinetics pre-training.

FAST: Font-Agnostic Scene Text Editing

Scene Text Editing (STE) is a challenging research problem, and it aims to modify existing texts in an image while preserving the background and the font style of the original text of the image. Due to its various real-life applications, researchers have explored several approaches toward STE in recent years. However, most of the existing STE methods show inferior editing performance because of (1) complex image backgrounds, (2) various font styles, and (3) varying word lengths within the text. To address such inferior editing performance issues, in this paper, we propose a novel font-agnostic scene text editing framework, named FAST, for simultaneously generating text in arbitrary styles and locations while preserving a natural and realistic appearance through combined mask generation and style transfer. The proposed approach differs from the existing methods as they directly modify all image pixels. Instead, the proposed method has introduced a filtering mechanism to remove background distractions, allowing the network to focus solely on the text regions where editing is required. Additionally, a text-style transfer module has been designed to mitigate the challenges posed by varying word lengths. Extensive experiments and ablations have been conducted, and the results demonstrate that the proposed method outperforms the existing methods both qualitatively and quantitatively.

DySTreSS: Dynamically Scaled Temperature in Self-Supervised Contrastive Learning

In contemporary self-supervised contrastive algorithms like SimCLR, MoCo, etc., the task of balancing attraction between two semantically similar samples and repulsion between two samples from different classes is primarily affected by the presence of hard negative samples. While the InfoNCE loss has been shown to impose penalties based on hardness, the temperature hyper-parameter is the key to regulating the penalties and the trade-off between uniformity and tolerance. In this work, we focus our attention to improve the performance of InfoNCE loss in SSL by studying the effect of temperature hyper-parameter values. We propose a cosine similarity-dependent temperature scaling function to effectively optimize the distribution of the samples in the feature space. We further analyze the uniformity and tolerance metrics to investigate the optimal regions in the cosine similarity space for better optimization. Additionally, we offer a comprehensive examination of the behavior of local and global structures in the feature space throughout the pre-training phase, as the temperature varies. Experimental evidence shows that the proposed framework outperforms or is at par with the contrastive loss-based SSL algorithms. We believe our work (DySTreSS) on temperature scaling in SSL provides a foundation for future research in contrastive learning.

SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation

Document layout analysis is a known problem to the documents research community and has been vastly explored yielding a multitude of solutions ranging from text mining, and recognition to graph-based representation, visual feature extraction, etc. However, most of the existing works have ignored the crucial fact regarding the scarcity of labeled data. With growing internet connectivity to personal life, an enormous amount of documents had been available in the public domain and thus making data annotation a tedious task. We address this challenge using self-supervision and unlike, the few existing self-supervised document segmentation approaches which use text mining and textual labels, we use a complete vision-based approach in pre-training without any ground-truth label or its derivative. Instead, we generate pseudo-layouts from the document images to pre-train an image encoder to learn the document object representation and localization in a self-supervised framework before fine-tuning it with an object detection model. We show that our pipeline sets a new benchmark in this context and performs at par with the existing methods and the supervised counterparts, if not outperforms. The code is made publicly available at: https://github.com/MaitySubhajit/SelfDocSeg

MMC: Multi-Modal Colorization of Images using Textual Descriptions

Handling various objects with different colors is a significant challenge for image colorization techniques. Thus, for complex real-world scenes, the existing image colorization algorithms often fail to maintain color consistency. In this work, we attempt to integrate textual descriptions as an auxiliary condition, along with the grayscale image that is to be colorized, to improve the fidelity of the colorization process. To do so, we have proposed a deep network that takes two inputs (grayscale image and the respective encoded text description) and tries to predict the relevant color components. Also, we have predicted each object in the image and have colorized them with their individual description to incorporate their specific attributes in the colorization process. After that, a fusion model fuses all the image objects (segments) to generate the final colorized image. As the respective textual descriptions contain color information of the objects present in the image, text encoding helps to improve the overall quality of predicted colors. In terms of performance, the proposed method outperforms existing colorization techniques in terms of LPIPS, PSNR and SSIM metrics.

Global Context-Aware Person Image Generation

We propose a data-driven approach for context-aware person image generation. Specifically, we attempt to generate a person image such that the synthesized instance can blend into a complex scene. In our method, the position, scale, and appearance of the generated person are semantically conditioned on the existing persons in the scene. The proposed technique is divided into three sequential steps. At first, we employ a Pix2PixHD model to infer a coarse semantic mask that represents the new person's spatial location, scale, and potential pose. Next, we use a data-centric approach to select the closest representation from a precomputed cluster of fine semantic masks. Finally, we adopt a multi-scale, attention-guided architecture to transfer the appearance attributes from an exemplar image. The proposed strategy enables us to synthesize semantically coherent realistic persons that can blend into an existing scene without altering the global context. We conclude our findings with relevant qualitative and quantitative evaluations.