Recently, weakly supervised temporal sentence grounding in videos (TSGV) has attracted extensive attention because it does not require precise start-end time annotations during training, and it can quickly retrieve interesting segments according ...

• Global query text may lack detailed knowledge of the query.
• Multi-scale modeling of joint representations helps generate diverse candidates.
• Word-level interaction and multi-scale modeling help leverage query knowledge.

Integrating models from diverse sources has attracted substantial interest in developing advanced time series forecasting technologies. However, current research lacks a comprehensive and deep fusion model to integrate multiple forecasting ...

The fusion of facial expression and Electroencephalogram (EEG) signals in a multi-modal framework is a comprehensive and accurate method for emotion recognition. However, current methods often tend to directly concatenate two modalities, thereby ...

Empathy, the ability to understand and respond to others’ emotions, is critical in dialogue systems, particularly for applications such as psychological counselling and casual conversation. However, existing approaches often struggle to ...

Unsupervised domain adaptation (UDA) for person re-identification (re-ID) aims to bridge the domain gap by transferring knowledge from the labeled source domain to the unlabeled target domain. Recently, pseudo-label-based approaches have become ...

• We propose an attention-disentangled re-ID network to explore more discriminative feature representations to resolve the contradiction between intra-class diversity and the stability of pseudo labels.
• We propose a spatial attention-...

In the domain of multi-agent networks, distributed online mirror descent (DOMD) and distributed online dual averaging (DODA) play pivotal roles as fundamental algorithms for distributed online convex optimization. However, in contrast to DODA, ...

• We introduce two new DOMD variants, addressing issues with dynamic learning rates, and provide regret bounds.
• Enhancing our dual-stabilized DOMD with a lazy subgradient descent step, we establish a connection with re-indexed DODA.
• ...

This paper presents the first neural process-based model for traffic prediction, the Memory-augmented Conditional Neural Process (MemCNP). Spatio-temporal traffic prediction involves predicting future traffic patterns based on historical traffic ...

• The first neural process-based model, MemCNP, for traffic prediction with limited data.
• MemCNP introduces a novel framework for uncertainty estimation.
• A novel memory network module acquires a representative contextual reference.

Display Omitted

Deep learning systems have been shown to be vulnerable to adversarial examples, but most existing works focus on manipulating and attacking images in the digital domain. Although some recent research has proposed physical attacks using ...

Current knowledge distillation methods typically transfer knowledge on data from the same batch. Nevertheless, these methodologies neglect the significance of leveraging the knowledge accumulated by the teacher model from past batches. In ...

Recently, Large Language Models (LLMs) has demonstrated unparalleled capabilities in understanding and generation, hence holding promising prospects for applying LLMs to table-to-text generation. However, the generation process with LLMs lacks a ...

• A new perspective on adapting LLMs to challenging tasks.
• A controllable method for table-to-text generation.
• State-of-the-art results on the few-shot table-to-text generation dataset.

Text generation is a vital natural language processing task that generates a sequence given an input text. Most recent text generation models have mainly utilized the power of pre-trained language models (PLMs) and achieved promising results. ...

• A model that takes into account auxiliary tasks for text generation is proposed.
• The proposed model achieves promising results on 10 datasets in three text generation tasks.
• Deep analyses of several aspects of the model are ...

Unmanned aerial vehicles (UAVs) are advanced flight systems. However, their positioning systems cause distance-dependent errors during flight. This study seeks to solve the UAV path planning problem with positioning error correction (UPEC) with ...

Feature extraction plays a crucial role in capturing data correlations, thereby improving the performance of multi-label learning models. Popular approaches mainly include feature space manipulation techniques, such as recursive feature ...

• We propose a feature extraction technique embedding instance correlation.
• We propose a parallel–serial architecture for multi-label learning.
• We propose a strategy to balance self-supervision and instance correlation.

The feature selection algorithm based on dictionary learning has been widely studied for its excellent interpretability. In the feature selection process, many algorithms only consider the global or local geometric structure information of the ...

Deep neural networks have gained popularity due to their outstanding performance across various domains. However, because of their lack of explainability, they are vulnerable to some kinds of threats including the trojan or backdoor attack, in ...

Display Omitted

• A trojan attack on neural networks is presented that uses more than one trigger.
• The attacker might need to try a few triggers before succeeding.
• While attack success rate of each trigger is low, total attack success rate is high.

Despite the affordability, simplicity, and efficiency of controller area network (CAN) protocols, the security vulnerability remains a major challenge. Currently, a machine learning-based intrusion detection system (IDS) is considered an ...

Data stream learning is a very relevant paradigm because of the increasing real-world scenarios generating data at high velocities and in unbounded sequences. Stream learning aims at developing models that can process instances as they arrive, so ...

The echo-like spiking neural P (ESNP) system is a variant of the echo-state network (ESN) that integrates the nonlinear spiking neural P (NSNP) system. In this study, we propose a deep echo-like spiking neural P system, called the Deep-ESNP model,...

Due to the differences in shape, material, and color of objects, the detection of planar grasps by robots remains challenging. Traditional methods rely on discrete grasp configurations for annotation, ignoring many possible grasp configurations. ...

As Transformer-based models have achieved impressive performance across various time series tasks, Long-Term Series Forecasting (LTSF) has garnered extensive attention in recent years. The intricate complexity of the Attention mechanism leads to ...