26 accepted papers
Real-world fraud detection applications benefit from graph learning techniques that jointly exploit node features—often rich in textual data—and graph structural information. Recently, Graph-Enhanced LLMs have emerged as a promising graph learning approach that converts graph information into prompt
Heterogeneous Graph Neural Networks (HGNNs) are widely used for deep learning on heterogeneous graphs. Typical end-to-end HGNNs require repetitive message passing during training, limiting efficiency for large-scale real-world graphs. Pre-computation-based HGNNs address this by performing message pa
Isolated cold-start node classification on multimodal graphs is challenging because such nodes have no edges and often have missing modalities (e.g., absent text or image features). Existing methods address structural isolation by degrading graph learning models to multilayer perceptrons (MLPs) for
Graph Neural Networks (GNNs) face significant computational challenges when handling large-scale graphs. To address this, Graph Condensation (GC) methods aim to compress large graphs into smaller, synthetic ones that are more manageable for GNN training. Recently, trajectory matching methods have sh…
Entity Alignment (EA) is essential for integrating Knowledge Graphs (KGs) by matching equivalent entities across diverse KGs. With the rise of multi-modal KGs, which emerged to better depict real-world KGs by integrating visual, textual, and structured data, Multi-Modal Entity Alignment (MMEA) has b…
Although masked image generation models and masked diffusion models are designed with different motivations and objectives, we observe that they can be unified within a single framework. Building upon this insight, we carefully explore the design space of training and sampling, identifying key facto…
The capabilities of large language models (LLMs) are widely regarded as relying on autoregressive models (ARMs). We challenge this notion by introducing *LLaDA*, a diffusion model trained from scratch under the pre-training and supervised fine-tuning (SFT) paradigm. LLaDA employs a forward data mask…
Multimodal knowledge graph completion (MKGC) aims to predict missing triples in MKGs using multimodal information. Recent research typically either extracts information from each modality separately to predict, then ensembles the predictions at the decision stage, or projects multiple modalities int…
Visual Place Recognition (VPR) is crucial for various computer vision and robotics applications. Traditional VPR techniques relying on handcrafted features, have been enhanced by using Convolutional Neural Networks (CNNs). Recently, MixVPR has set new benchmarks in VPR by using advanced feature aggr
Multimodal recommendation systems can learn users' preferences from existing user-item interactions as well as the semantics of multimodal data associated with items. Many existing methods model this through a multimodal user-item graph, approaching multimodal recommendation as a graph learning task…
While LiDAR and cameras are becoming ubiquitous for unmanned aerial vehicles (UAVs) but can be ineffective in challenging environments, 4D millimeter-wave (MMW) radars that can provide robust 3D ranging and Doppler velocity measurements are less exploited for aerial navigation. In this paper, we dev
Large Language Models (LLMs) can assist multimodal fake news detection by predicting pseudo labels. However, LLM-generated pseudo labels alone demonstrate poor performance compared to traditional detection methods, making their effective integration non-trivial. In this paper, we propose Global Labe…
Socially Assistive Robotics (SAR) has shown promise in supporting emotion regulation for neurodivergent children. Recently, there has been increasing interest in leveraging advanced technologies to assist parents in co-regulating emotions with their children. However, limited research has explored t
Explaining multi-agent systems (MAS) is urgent as these systems become increasingly prevalent in various applications. Previous work has provided explanations for the actions or states of agents, yet falls short in understanding the blackboxed agent’s importance within a MAS and the overall team str…
Text-to-Visualization (Text2Vis) aims to democratize data insights for non-expert users by transforming natural language query (NLQ) into visualization specification (VS). In view of the high dependence of rule-based methods on predefined VS templates and poor NLQ understanding ability of small data…
Open set recognition is a crucial research theme for open-environment machine learning. For this problem, a common solution is to learn compact representations of known classes and identify unknown samples by measuring deviations from these known classes. However, the aforementioned methods (1) lack…
Graph Anomaly Detection (GAD) has surfaced as a significant field of research, predominantly due to its substantial influence in production environments. Although existing approaches for node anomaly detection have shown effectiveness, they have yet to fully address two major challenges: operating i…
Channel-spatial attention mechanisms have been extensively investigated in computer vision. However, it is still a difficult problem that how to efficiently utilize global and local contextual information laid in a feature tensor to generate an accurate 3D attention map. This paper proposes a novel…
The paper introduces a novel Visual Place Recognition (VPR) method called Lightweight Pooling-centric Saliency-aware VPR (LPS-VPR), a high-performance VPR method capable of exploiting saliency information without computational burden. The key contribution of the method is a pooling-based saliency en
While Global Navigation Satellite System (GNSS) is often used to provide global positioning if available, its intermittency and/or inaccuracy calls for fusion with other sensors. In this paper, we develop a novel GNSS-Visual-Inertial Navigation System (GVINS) that fuses visual, inertial, and raw GNS…
A robotic workshop assistant has been a long-standing grand challenge for robotics, speech, computer vision, and artificial intelligence (AI) research. We revisit the goal of visual identification of tools from human queries in the current era of Large Vision-and-Language models (like GPT-4). We fin…
Most existing multiple object tracking (MOT) methods that solely rely on appearance features struggle in tracking highly deformable objects. Other MOT methods that use motion clues to associate identities across frames have difficulty handling egocentric videos effectively or efficiently. In this wo…
This paper addresses the problem of visual-inertial odometry (VIO) with a downward facing monocular camera when a micro aerial vehicle (MAV) flying at high altitude (over 100 meters). It is important to note that large scene depth causes visual motion constraints significantly less informative than…
Applying feature dependent network weights have been proved to be effective in many fields. However, in practice, restricted by the enormous size of model parameters and memory footprints, scalable and versatile dynamic convolutions with per-pixel adapted filters are yet to be fully explored. In thi…
Despite the valuable information contained in software chat messages, disentangling them into distinct conversations is an essential prerequisite for any in-depth analyses that utilize this information. To provide a better understanding of the current state-of-the-art, we evaluate five popular dialo…
We present SELL-CORPUS, a multiple accented speech corpus for L2 English learning in China, aiming at the potential research of multiple accented acoustic model, mispronunciation detection and pronunciation assessment for future nationwide oral English tests. Our corpus contains 31.6 hour speech rec…