Related papers: Shifting More Attention to Visual Backbone: Query-…
Fine-grained image recognition is a longstanding computer vision challenge that focuses on differentiating objects belonging to multiple subordinate categories within the same meta-category. Since images belonging to the same meta-category…
Accurate classification of fine-grained images remains a challenge in backbones based on convolutional operations or self-attention mechanisms. This study proposes novel dual-current neural networks (DCNN), which combine the advantages of…
Visual Grounding, also known as Referring Expression Comprehension and Phrase Grounding, aims to ground the specific region(s) within the image(s) based on the given expression text. This task simulates the common referential relationships…
We propose an end-to-end trainable Convolutional Neural Network (CNN), named GridDehazeNet, for single image dehazing. The GridDehazeNet consists of three modules: pre-processing, backbone, and post-processing. The trainable pre-processing…
The integration of deep learning based systems in clinical practice is often impeded by challenges rooted in limited and heterogeneous medical datasets. In addition, the field has increasingly prioritized marginal performance gains on a…
Convolutional Neural Networks (CNNs) frequently "cheat" by exploiting superficial correlations, raising concerns about whether they make predictions for the right reasons. Inspired by cognitive science, which highlights the role of…
Current visual grounding models are either based on a Multimodal Large Language Model (MLLM) that performs auto-regressive decoding, which is slow and risks hallucinations, or on re-aligning an LLM with vision features to learn new special…
3D visual grounding consists of identifying the instance in a 3D scene which is referred by an accompanying language description. While several architectures have been proposed within the commonly employed grounding-by-selection framework,…
Semantic segmentation of remote sensing images plays an important role in a wide range of applications including land resource management, biosphere monitoring and urban planning. Although the accuracy of semantic segmentation in remote…
Deep neural networks have shown excellent performance in stereo matching task. Recently CNN-based methods have shown that stereo matching can be formulated as a supervised learning task. However, less attention is paid on the fusion of…
Bridging the semantic gap between image and question is an important step to improve the accuracy of the Visual Question Answering (VQA) task. However, most of the existing VQA methods focus on attention mechanisms or visual relations for…
Tool-integrated visual reasoning (TiVR) has demonstrated great potential in enhancing multimodal problem-solving. However, existing TiVR paradigms mainly focus on integrating various visual tools through reinforcement learning, while…
Within (semi-)automated visual inspection, learning-based approaches for assessing visual defects, including deep neural networks, enable the processing of otherwise small defect patterns in pixel size on high-resolution imagery. The…
Recent semantic segmentation research has increasingly moved toward stronger context modeling, dense attention, and transformer-based architectures. Although these models achieve impressive performance, classical CNN-based segmentation…
This paper studies the task of Visual Question Answering (VQA), which is topical in Multimedia community recently. Particularly, we explore two critical research problems existed in VQA: (1) efficiently fusing the visual and textual…
Given a degraded input image, image restoration aims to recover the missing high-quality image content. Numerous applications demand effective image restoration, e.g., computational photography, surveillance, autonomous vehicles, and remote…
Multimodal information processing has become increasingly important for enhancing image classification performance. However, the intricate and implicit dependencies across different modalities often hinder conventional methods from…
Grounded Multimodal Named Entity Recognition (GMNER) is an emerging information extraction (IE) task, aiming to simultaneously extract entity spans, types, and corresponding visual regions of entities from given sentence-image pairs data.…
3D face alignment of monocular images is a crucial process in the recognition of faces with disguise.3D face reconstruction facilitated by alignment can restore the face structure which is helpful in detcting disguise interference.This…
Visual understanding requires comprehending complex visual relations between objects within a scene. Here, we seek to characterize the computational demands for abstract visual reasoning. We do this by systematically assessing the ability…