Sorry, you need to enable JavaScript to visit this website.

In recent years, the rapid proliferation of multi-modal fake news has posed potential harm across various sectors of society, making the detection of multi-modal fake news crucial. Most existing methods can not effectively reduce the redundant information and preserve both semantic and structural information. To address these problems, this paper proposes a semantic distillation and structural alignment (SDSA) network. We design an semantic distillation module for modality-specific features to preserve task-relevant semantic information and eliminate redundant information.

Text Normalization (TN) is a pivotal pre-processing procedure in speech synthesis systems, which converts diverse forms of text into a canonical form suitable for correct synthesis. This work introduces a novel model, TNFormer, which innovatively transforms the TN task into a next token prediction problem, leveraging the structure of GPT with only Transformer decoders for efficient, single-pass TN. The strength of TNFormer lies not only in its ability to identify Non-Standard Words that require normalization but also in its aptitude for context-driven normalization in a single pass.

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 objects and camera movement. In this paper, we introduce TokenMotion (TMNet), which employs a transformer-based model to enhance VCOD by extracting motion-guided features using a learnable token selection. Evaluated on the challenging MoCA-Mask dataset, TMNet achieves state-of-the-art performance in VCOD.

Most works in class incremental learning (CIL) assume disjoint sets of classes as tasks. Although a few works deal with overlapped sets of classes, they either assume a balanced data distribution or assume a mild imbalanced distribution. Instead, in this paper, we explore one of the understudied real-world CIL settings where (1) different tasks can share some classes but with new data samples, and (2) the training data of each task follows a long-tail distribution. We call this setting CIL-LT.

Rich image and text features can largely improve the training of image captioning tasks. However, rich image and text features mean the incorporation of a large amount of unnecessary information. In our work, in order to fully explore and utilize the key information in images and text, we view the combination of image and text features as a data screening problem. The combination of image and text features is dynamically screened through a series of inference strategies with the aim of selecting the optimal image and text features.

For the purpose of computational efficiency, we propose two subspace-based methods, but without eigendecomposition, to address the two typical problems in nested array processing, i.e., direction-of-arrival (DOA) estimation and noise elimination. In detail, to estimate DOA parameters, we judiciously arrange the segments extracted from the co-array model and then introduce a novel co-array-based orthogonal propagator method (COPM).

Person search is a unified system aimed at jointly localizing and identifying a person of interest from a gallery of whole scene images. Due to the inherent properties of the person search, it faces significant challenges of large-scale variations, inaccurate detection boxes, and crowded scenes. To address these issues, we proposed an uncertainty-guided framework coupled with auxiliary shallow feature exploration, which includes a shallow feature fusion module and an uncertaintyguided module.

Grapheme-to-Phoneme (G2P) is an essential first step in any modern, high-quality Text-to-Speech (TTS) system. Most of the current G2P systems rely on carefully hand-crafted lexicons developed by experts. This poses a two-fold problem. Firstly, the lexicons are generated using a fixed phoneme set, usually, ARPABET or IPA, which might not be the most optimal way to represent phonemes for all languages. Secondly, the man-hours required to produce such an expert lexicon are very high.

Grapheme-to-Phoneme (G2P) is an essential first step in any modern, high-quality Text-to-Speech (TTS) system. Most of the current G2P systems rely on carefully hand-crafted lexicons developed by experts. This poses a two-fold problem. Firstly, the lexicons are generated using a fixed phoneme set, usually, ARPABET or IPA, which might not be the most optimal way to represent phonemes for all languages. Secondly, the man-hours required to produce such an expert lexicon are very high.

The vast majority of approaches to speaker anonymization involve the extraction of fundamental frequency estimates, linguistic features and a speaker embedding which is perturbed to obfuscate the speaker identity before an anonymized speech waveform is resynthesized using a vocoder.
Recent work has shown that x-vector transformations are difficult to control consistently: other sources of speaker information contained within fundamental frequency and linguistic features are re-entangled upon vocoding, meaning that anonymized speech signals still contain speaker information.