19 accepted papers
Zero-Shot Temporal Action Localization (ZS-TAL) aims to classify and localize actions in untrimmed videos that are unseen during training. Existing training-based ZS-TAL methods typically rely on fine-tuning models on large-scale annotated training data. This can be impractical in real-world applica
Masked autoencoders (MAE) have become a dominant paradigm in 3D representation learning, setting new performance benchmarks across various downstream tasks. Existing methods with fixed mask ratios neglect multi-level representational correlations and intrinsic geometric structures, while relying on
Clustering with k-means is well-established and efficient, but often struggles with complex data distributions because the clustering performance hinges on how well the centroids capture the data distribution, and conventional k-means usually fails to produce representative centroids under such cond
Zero-shot Natural Language Video Localization (NLVL) aims to automatically generate moments and corresponding pseudo queries from raw videos for the training of the localization model without any manual annotations. Existing approaches typically produce pseudo queries as simple words, which overlook…
Multiple rotation averaging plays a crucial role in computer vision and robotics domains. The conventional optimization-based methods optimize a nonlinear cost function based on certain noise assumptions, while most previous learning-based methods require ground truth labels in the supervised traini
Probabilistic path models have significantly improved generative tasks in computer vision. Researchers use diffusion model as 3D pretrained decoder, learning representation by predicting noise. However, this method requires noise addition and denoising operations throughout the entire point cloud, l
Singing voice conversion aims to transform a source singing voice into that of a target singer while preserving the original lyrics, melody, and various vocal techniques. In this paper, we propose a high-fidelity singing voice conversion system. Our system builds upon the SVCC T02 framework and cons…
The majority of point cloud registration methods currently rely on extracting features from points. However, these methods are limited by their dependence on information obtained from a single modality of points, which can result in deficiencies such as inadequate perception of global features and a
3D contrastive representation learning has exhibited remarkable efficacy across various downstream tasks. However, existing contrastive learning paradigms based on cosine similarity fail to deeply explore the potential intra-modal hierarchical and cross-modal semantic correlations about multi-modal…
As a fundamental problem in computer vision, point cloud registration aims to seek the optimal transformation for aligning a pair of point clouds. In most existing methods, the information flows are usually forward transferring, thus lacking the guidance from high-level information to low-level info
Multiview point cloud registration plays a crucial role in robotics, automation, and computer vision fields. This letter concentrates on pose graph construction and motion synchronization within multiview registration. Previous methods for pose graph construction often pruned fully connected graphs
Federated learning encounters substantial challenges with heterogeneous data, leading to performance degradation and convergence issues. While considerable progress has been achieved in mitigating such an impact, the reliability aspect of federated models has been largely disregarded. In this study,…
Label distribution learning (LDL) is a new machine learning paradigm for solving label ambiguity. Since it is difficult to directly obtain label distributions, many studies are focusing on how to recover label distributions from logical labels, dubbed label enhancement (LE). Existing LE methods esti…
Point cloud completion estimates complete shapes from incomplete point clouds to obtain higher-quality point cloud data. Most existing methods only consider global object features, ignoring spatial and semantic information of adjacent points. They cannot distinguish structural information well betwe
In this work, we focus on the challenging problem of Label Enhancement (LE), which aims to exactly recover label distributions from logical labels, and present a novel Label Information Bottleneck (LIB) method for LE. For the recovery process of label distributions, the label irrelevant information…
Recently, many excellent weakly supervised semantic segmentation (WSSS) works are proposed based on class activation mapping (CAM). However, there are few works that consider the characteristics of medical images. In this paper, we find that there are mainly two challenges of medical images in WSSS:…
Even though graphic layout generation has attracted growing attention recently, it is still challenging to synthesis realistic and diverse layouts, due to the complicated element relationships and varied element arrangements. In this work, we seek to improve the performance of layout generation by i…
Recently, the motion averaging method has been introduced as an effective means to solve the multi-view registration problem. This method aims to recover global motions from a set of relative motions, where the original method is sensitive to outliers due to using the Frobenius norm error in the opt…
This paper proposes a new model, referred to as the show and speak (SAS) model that, for the first time, is able to directly synthesize spoken descriptions of images, bypassing the need for any text or phonemes. The basic structure of SAS is an encoder-decoder architecture that takes an image as inp…