相关论文: LoFLAT: Local Feature Matching using Focused Linea…

Thinking with Images improves fine-grained VQA for MLLMs by emphasizing visual cues. However, tool-augmented methods depend on the capacity of grounding, which remains unreliable for MLLMs. In parallel, attention-driven methods to crop the…

Multimodal Large Language Models (MLLMs) have shown strong performance in multi-image cross-modal retrieval, yet suffer from severe position bias, where predictions are dominated by input order rather than semantic relevance. Through…

Weakly supervised learning can help local feature methods to overcome the obstacle of acquiring a large-scale dataset with densely labeled correspondences. However, since weak supervision cannot distinguish the losses caused by the…

Local feature matching has long been a fundamental component of 3D vision systems such as Structure-from-Motion (SfM), yet progress has lagged behind the rapid advances of modern data-driven approaches. The newer approaches, such as…

Environmental perception systems are crucial for high-precision mapping and autonomous navigation, with LiDAR serving as a core sensor providing accurate 3D point cloud data. Efficiently processing unstructured point clouds while extracting…

Vision transformers have shown great success on numerous computer vision tasks. However, its central component, softmax attention, prohibits vision transformers from scaling up to high-resolution images, due to both the computational…

Discovering inter-point connection for efficient high-dimensional feature extraction from point coordinate is a key challenge in processing point cloud. Most existing methods focus on designing efficient local feature extractors while…

Recent Vision Transformer (ViT)-based methods for Image Super-Resolution have demonstrated impressive performance. However, they suffer from significant complexity, resulting in high inference times and memory usage. Additionally, ViT…

Limited by the locality of convolutional neural networks, most existing local features description methods only learn local descriptors with local information and lack awareness of global and surrounding spatial context. In this work, we…

Transformer-based approaches have revolutionized image super-resolution by modeling long-range dependencies. However, the quadratic computational complexity of vanilla self-attention mechanisms poses significant challenges, often leading to…

Vision Transformers (ViTs) have achieved impressive results in computer vision by leveraging self-attention to model long-range dependencies. However, their emphasis on global context often comes at the expense of local feature extraction…

In this paper we revisit feature fusion, an old-fashioned topic, in the new context of text-to-video retrieval. Different from previous research that considers feature fusion only at one end, let it be video or text, we aim for feature…

Geometry problem-solving remains a significant challenge for Large Multimodal Models (LMMs), requiring not only global shape recognition but also attention to intricate local relationships related to geometric theory. To address this, we…

The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model…

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

In recent years, learned image compression (LIC) methods have achieved significant performance improvements. However, obtaining a more compact latent representation and reducing the impact of quantization errors remain key challenges in the…

Previous methods for dynamic facial expression recognition (DFER) in the wild are mainly based on Convolutional Neural Networks (CNNs), whose local operations ignore the long-range dependencies in videos. Transformer-based methods for DFER…

Recently, there is growing attention on one-stage panoptic segmentation methods which aim to segment instances and stuff jointly within a fully convolutional pipeline efficiently. However, most of the existing works directly feed the…

Vision Transformer (ViT) attains state-of-the-art performance in visual recognition, and the variant, Local Vision Transformer, makes further improvements. The major component in Local Vision Transformer, local attention, performs the…

The infrared and visible images fusion (IVIF) is receiving increasing attention from both the research community and industry due to its excellent results in downstream applications. Existing deep learning approaches often utilize…