Related papers: MOoSE: Multi-Orientation Sharing Experts for Open-…

Continual test-time adaptation adapts a source-pretrained model to non-stationary, unlabeled target streams while retaining past competence, yet texture-biased backbones risk error accumulation and catastrophic forgetting. Drawing…

In this work, our objective is to address the problems of generalization and flexibility for text recognition in documents. We introduce a new model that exploits the repetitive nature of characters in languages, and decouples the visual…

Graphs offer a natural way to formulate Multiple Object Tracking (MOT) and Multiple Object Tracking and Segmentation (MOTS) within the tracking-by-detection paradigm. However, they also introduce a major challenge for learning methods, as…

With the novel and fast advances in the area of deep neural networks, several challenging image-based tasks have been recently approached by researchers in pattern recognition and computer vision. In this paper, we address one of these…

Multimodal speech emotion recognition (SER) has emerged as pivotal for improving human-machine interaction. Researchers are increasingly leveraging both speech and textual information obtained through automatic speech recognition (ASR) to…

Multimodal Sentiment Analysis is an active area of research that leverages multimodal signals for affective understanding of user-generated videos. The predominant approach, addressing this task, has been to develop sophisticated fusion…

Humans recognize the visual world at multiple levels: we effortlessly categorize scenes and detect objects inside, while also identifying the textures and surfaces of the objects along with their different compositional parts. In this…

Cross-modal feature extraction and integration have led to steady performance improvements in few-shot learning tasks due to generating richer features. However, existing multi-modal object detection (MM-OD) methods degrade when facing…

Scene text detection methods based on neural networks have emerged recently and have shown promising results. Previous methods trained with rigid word-level bounding boxes exhibit limitations in representing the text region in an arbitrary…

Incidental scene text detection, especially for multi-oriented text regions, is one of the most challenging tasks in many computer vision applications. Different from the common object detection task, scene text often suffers from a large…

Mixture-of-experts (MoE) architectures have expanded from language modeling to automatic speech recognition (ASR). Traditional MoE methods, such as the Switch Transformer, route experts independently within each layer. Our analysis reveals…

Multi-modal object Re-IDentification (ReID) aims to obtain complete identity features across heterogeneous modalities. However, most existing methods rely on implicit feature fusion modules, making it difficult to model fine-grained…

The Sparsely-Activated Mixture-of-Experts (MoE) has gained increasing popularity for scaling up large language models (LLMs) without exploding computational costs. Despite its success, the current design faces a challenge where all experts…

Scene Text Image Super-Resolution (STISR) aims to restore high-resolution details in low-resolution text images, which is crucial for both human readability and machine recognition. Existing methods, however, often depend on external…

Recent works in the text recognition area have pushed forward the recognition results to the new horizons. But for a long time a lack of large human-labeled natural text recognition datasets has been forcing researchers to use synthetic…

Amodal segmentation targets to predict complete object masks, covering both visible and occluded regions. This task poses significant challenges due to complex occlusions and extreme shape variation, from rigid furniture to highly…

Arbitrary-oriented text detection in the wild is a very challenging task, due to the aspect ratio, scale, orientation, and illumination variations. In this paper, we propose a novel method, namely Arbitrary-oriented Text (or ArbText for…

Text in natural images is of arbitrary orientations, requiring detection in terms of oriented bounding boxes. Normally, a multi-oriented text detector often involves two key tasks: 1) text presence detection, which is a classification…

In visual Reinforcement Learning (RL), learning from pixel-based observations poses significant challenges on sample efficiency, primarily due to the complexity of extracting informative state representations from high-dimensional data.…

The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence. Where those basic building blocks share meaningful properties, interactions and other regularities across scenes, such decompositions…