21 accepted papers
Fully Few-shot Class-incremental Audio Classification (FFCAC) is challenging since the training samples are limited both in the incremental sessions and in the base session. Existing few-shot learning methods suffer from catastrophic forgetting and overfitting when applied to FFCAC.Pre-trained Audio
Recently, generating 3D assets using visual priors from pretrained diffusion models has shown remarkable results. However, due to the inherent lack of 3D geometric priors in 2D diffusion, the synthesized results often suffer from spatial hallucination and multi-view inconsistency. To address this li
Direct Preference Optimization has achieved remarkable success in aligning diffusion models with human feedback. However, existing methods heavily rely on image-level preferences, which suffer from sparse rewards in the spatial dimension. This creates a fundamental misalignment: while an image may b
Conditional semantic textual similarity (C-STS) assesses the similarity between pairs of sentence representations under different conditions. The current method encounters the over-estimation issue of positive and negative samples. Specifically, the similarity within positive samples is excessively…
In deep reinforcement learning (DRL), the presence of dormant neurons leads to a significant reduction in network capacity, which results in sub-optimal performance and limited sample efficiency. Existing training techniques, especially those relying on periodic resetting (PR), exacerbate this issue
Temporal knowledge graph (TKG) reasoning has become a hot topic due to its great value in many practical tasks. The key to TKG reasoning is modeling the structural information and evolutional patterns of the TKGs. While great efforts have been devoted to TKG reasoning, the structural and evolutional…
Online continual learning (OCL) is a strict setting of continual learning (CL), where the OCL agent faces a never-ending data stream and encounters each new sample only once. An OCL agent suffers more serious catastrophic forgetting (i.e., forgetting previous knowledge of old classes) than a CL agen…
Detecting fake news in short videos is crucial for combating misinformation. Existing methods utilize topic modeling and co-attention mechanism, overlooking the modality heterogeneity and resulting in suboptimal performance. To address this issue, we introduce Text-Guided Fine-grained Counterfactual…
Knowledge Distillation (KD) is a promising approach for unsupervised Anomaly Detection (AD). However, the student network's over-generalization often diminishes the crucial representation differences between teacher and student in anomalous regions, leading to detection failures. To address this pro…
Multi-goal conversational recommender system (MG-CRS) which is more in line with realistic scenarios has attracted a lot of attention. MG-CRS can dynamically capture the demands of users in conversation, continuously engage their interests, and make recommendations. The key of accomplishing these ta…
Zeroth-order optimization algorithms are widely used for black-box optimization problems, such as those in machine learning and prompt engineering, where the gradients are approximated using function evaluations. Recently, a generalization result was provided for zeroth-order stochastic gradient des…
Meta-learning has emerged as a prominent technology for few-shot text classification and has achieved promising performance. However, existing methods often encounter difficulties in drawing accurate class prototypes from support set samples, primarily due to probable large intra-class differences a…
Temporal knowledge graph completion is a critical task within the knowledge graph domain. Existing approaches encompass deep neural network-based methods for temporal knowledge graph embedding and rule-based logical symbolic reasoning. However, the former may not adequately account for structural de…
Reasoning over the Temporal Knowledge Graph (TKG) that predicts facts in the future has received much attention. Most previous works attempt to model temporal dynamics with knowledge graphs and graph convolution networks. However, these methods lack the consideration of high-order interactions betwe…
Short video fake news detection is crucial for combating the spread of misinformation. Current detection methods tend to aggregate features from individual modalities into multimodal features, overlooking the implicit opinions and the evolving nature of opinions across modalities. In this paper, we…
Video question answering involves understanding video content to generate accurate answers to questions. Recent studies have successfully modeled video features and achieved diverse multimodal interaction, yielding impressive outcomes. However, they have overlooked the fact that the video contains r…
Emotion recognition in conversation (ERC) enables a deeper understanding of emotion for each utterance within a conversation. Recent progress on ERC has proved that using Graph Neural Networks (GNN) to model conversational context is effective for identifying emotions. However, existing GNN-based ap…
*Warning: This paper contains several contents that may be toxic, harmful, or offensive.*In the last few years, text-to-image generative models have gained remarkable success in generating images with unprecedented quality accompanied by a breakthrough of inference speed. Despite their rapid progres…
Multi-modality support has become an integral part of creating a seamless user experience with modern voice assistants with smart displays. Users refer to images, video thumbnails, or the accompanying text descriptions on the screen through voice communication with AI powered devices. This raises th…
Current spoken language understanding systems heavily rely on the best hypothesis (ASR 1-best) generated by automatic speech recognition, which is used as the input for downstream models such as natural language understanding (NLU) modules. However, the potential errors and misrecognition in ASR 1-b…
Currently, in spoken language understanding (SLU) systems, the automatic speech recognition (ASR) module produces multiple interpretations (or hypotheses) for the input audio signal and the natural language understanding (NLU) module takes the one with the highest confidence score for domain or inte…