26 accepted papers
Temporal embeddings play a crucial role in dynamic graph neural networks (DGNNs) by capturing the temporal dynamics of interactions. However, existing Random Fourier Feature (RFF)-based methods in DGNNs directly sample Fourier frequencies from a fixed, data-independent distribution $p(\omega)$, negl
With rapid advances in audio-visual generative models, reliable forgery detection becomes increasingly critical. Existing methods for audio-visual deepfake detection typically rely on cross-modal inconsistencies. In singing, rhythmic vocalization weakens this coupling and introduces a nontrivial dom…
Foundation models for medical image segmentation struggle under out-of-distribution (OOD) shifts, often producing fragmented false positives on OOD tumors. We introduce **R^2-Seg**, a **training-free** framework for robust OOD tumor segmentation that operates via a two-stage **Reason-and-Reject** pr
Crystal materials play an important role in the development of society. The discovery of new materials is critical to achieving sustainable development goals (SDGs), such as climate change mitigation, affordable and clean energy, and fostering innovation in industry and infrastructure. Recent advanc…
Healthcare data frequently contain a substantial proportion of missing values, necessitating effective time series imputation to support downstream disease diagnosis tasks. However, existing imputation methods focus on discrete data points and are unable to effectively model sparse data, resulting i
This paper reports on learning a reward map for social navigation in dynamic environments where the robot can reason about its path at any time, given agent trajectories and scene geometry. Humans navigating in dense and dynamic indoor environments often work with several implied social rules. A rul
Recent advancements in large language models (LLMs) have revolutionized research discovery across various scientific disciplines, including materials science. The discovery of novel materials, particularly crystal materials, is essential for achieving sustainable development goals (SDGs), as they dr
Neural Representations for Videos (NeRV) has emerged as a promising implicit neural representation (INR) approach for video analysis, which represents videos as neural networks with frame indexes as inputs. However, NeRV-based methods are time-consuming when adapting to a large number of diverse v…
Decoding natural visual scenes from brain activity has flourished, with extensive research in single-subject tasks and, however, less in cross-subject tasks. Reconstructing high-quality images in cross-subject tasks is a challenging problem due to profound individual differences between subjects and…
Contrast-enhanced 3D Medical imaging (e.g., CT, MRI) leverages phase sequences to uncover temporal dynamics vital for diagnosing tumors, lesions, and vascular issues. However, current retrieval models primarily focus on spatial features, neglecting phase-specific progression detailed in clinical rep
Predicting the performance of deep learning (DL) models, such as execution time and resource utilization, is crucial for Neural Architecture Search (NAS), DL cluster schedulers, and other technologies that advance deep learning. The representation of a model is the foundation for its performance pre
Developing models for protein-ligand interactions holds substantial significance for drug discovery. Supervised methods often failed due to the lack of labeled data for predicting the protein-ligand binding energy, like antibodies. Therefore, unsupervised approaches are urged to make full use of the…
Generating high-fidelity talking heads that maintain stable head poses and achieve robust lip sync remains a significant challenge. Although methods based on 3D Gaussian Splatting (3DGS) offer a promising solution via point-based deformation, they suffer from inconsistent head dynamics and mismatche
Retinal vessel segmentation is critical for medical diagnosis, yet existing models often struggle to generalize across domains due to appearance variability, limited annotations, and complex vascular morphology. We propose GraphSeg, a variational Bayesian framework that integrates anatomical graph p…
"Implicit Neural Representation (INR) has gained increasing popularity as a data representation method, serving as a prerequisite for innovative generation models. Unlike gradient-based methods, which exhibit lower efficiency in inference, the adoption of hyper-network for generating parameters in M…
Motif scaffolding seeks to design scaffold structures for constructing proteins with functions derived from the desired motif, which is crucial for the design of vaccines and enzymes. Previous works approach the problem by inpainting or conditional generation. Both of them can only scaffold motifs w…
Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, leading to rapid advancements in multimodal studies. However, CLIP faces a notable challenge in terms of *inefficient data utilization*. It relies on a single contrastive supervision for each image-text pair during repres…
Reconstruction of static visual stimuli from non-invasion brain activity fMRI achieves great success, owning to advanced deep learning models such as CLIP and Stable Diffusion. However, the research on fMRI-to-video reconstruction remains limited since decoding the spatiotemporal perception of conti…
Vision Transformer (ViT) has achieved remarkable performance in computer vision. However, positional encoding in ViT makes it substantially difficult to learn the intrinsic equivariance in data. Ini- tial attempts have been made on designing equiv- ariant ViT but are proved defective in some cases i…
Implicit neural representations (INRs) aim to learn a continuous function (i.e., a neural network) to represent an image, where the input and output of the function are pixel coordinates and RGB/Gray values, respectively. However, images tend to consist of many objects whose colors are not perfectly…
Deep-learning based methods that aim to extract effective high-level features have steadily improved the performance on the speech emotion recognition. However, low-level features that contain important emotion-related information have not gained much attention. In this paper, we propose a novel low…
Multi-view Speech Emotion Recognition (SER) based on the pre-trained model has achieved success in speaker-independent scenarios. However, the existing SER methods rely on excessive feature views and have complicated feature fusion strategies. In this paper, we propose a novel method to learn effect…
Speech emotion recognition (SER) based on multi-view learning has made some progress on speaker-independent scenarios. How-ever, the existing SER methods always rely on excessive feature views and ignore the importance of heterogeneous feature learning. In this paper, we propose a novel multi-level…
During training, artificial neural networks might not converge to a global minimum. Usually, using gradient descent, the training procedure cause the network to stroll in the high-dimensional weights’ space. This stroll passes adjacently to local minima and locations in the geometry of loss landscap…
Superconductivity allows electrical current to flow without any energy loss, and thus making solids superconducting is a grand goal of physics, material science, and electrical engineering. More than 16 Nobel Laureates have been awarded for their contribution in superconductivity research. Supercond…
Non-intrusive load monitoring (a.k.a. power disaggregation) refers to identifying and extracting the consumption patterns of individual appliances from the mains which records the whole-house energy consumption. Recently, deep learning has been shown to be a promising method to solve this problem an…