Related papers: Target-Oriented Deformation of Visual-Semantic Emb…

Multimodal learning robust to missing modality has attracted increasing attention due to its practicality. Existing methods tend to address it by learning a common subspace representation for different modality combinations. However, we…

Network embedding is a highly effective method to learn low-dimensional node vector representations with original network structures being well preserved. However, existing network embedding algorithms are mostly developed for a single…

Cross-modality magnetic resonance (MR) image synthesis can be used to generate missing modalities from given ones. Existing (supervised learning) methods often require a large number of paired multi-modal data to train an effective…

We study the problem of learning graph dynamics of deformable objects that generalizes to unknown physical properties. Our key insight is to leverage a latent representation of elastic physical properties of cloth-like deformable objects…

The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects. Through an examination of its adaptive behavior, we observe that while the spatial support for its neural…

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…

Visual grounding focuses on establishing fine-grained alignment between vision and natural language, which has essential applications in multimodal reasoning systems. Existing methods use pre-trained query-agnostic visual backbones to…

This paper introduces Dynamic Embeddings with Task-Oriented prompting (DETOT), a novel approach aimed at improving the adaptability and efficiency of machine learning models by implementing a flexible embedding layer. Unlike traditional…

Multimodal multitask learning has attracted an increasing interest in recent years. Singlemodal models have been advancing rapidly and have achieved astonishing results on various tasks across multiple domains. Multimodal learning offers…

Multi-modal medical image segmentation plays an essential role in clinical diagnosis. It remains challenging as the input modalities are often not well-aligned spatially. Existing learning-based methods mainly consider sharing trainable…

Data association-based multiple object tracking (MOT) involves multiple separated modules processed or optimized differently, which results in complex method design and requires non-trivial tuning of parameters. In this paper, we present an…

A convolutional neural network (ConvNet) is usually trained and then tested using images drawn from the same distribution. To generalize a ConvNet to various tasks often requires a complete training dataset that consists of images drawn…

Object goal navigation aims to steer an agent towards a target object based on observations of the agent. It is of pivotal importance to design effective visual representations of the observed scene in determining navigation actions. In…

Multi-modal brain images from MRI scans are widely used in clinical diagnosis to provide complementary information from different modalities. However, obtaining fully paired multi-modal images in practice is challenging due to various…

This study aims to address the problem of incomplete information in unimodal images for semantic segmentation and object detection tasks. Existing multimodal fusion methods suffer from limited capability in discriminative modeling of…

The area of Video Camouflaged Object Detection (VCOD) presents unique challenges in the field of computer vision due to texture similarities between target objects and their surroundings, as well as irregular motion patterns caused by both…

Driven by Convolutional Neural Networks, object detection and semantic segmentation have gained significant improvements. However, existing methods on the basis of a full top-down module have limited robustness in handling those two tasks…

Humans can robustly learn novel visual concepts even when images undergo various deformations and lose certain information. Mimicking the same behavior and synthesizing deformed instances of new concepts may help visual recognition systems…

Aerial-ground localization is difficult due to large viewpoint and modality gaps between ground-level LiDAR and overhead imagery. We propose TransLocNet, a cross-modal attention framework that fuses LiDAR geometry with aerial semantic…

Despite the good results that have been achieved in unimodal segmentation, the inherent limitations of individual data increase the difficulty of achieving breakthroughs in performance. For that reason, multi-modal learning is increasingly…