20 accepted papers
Audio-Visual Segmentation (AVS) aims to accurately segment sounding objects in video frames by leveraging audio-visual correspondence cues. However, it remains challenging due to the intrinsic semantic incompleteness within a single modality and the semantic gap between audio and visual representati
Traffic forecasting is evolving, with world models emerging as a powerful framework applicable to tasks such as core state, trajectory, event, and demand forecasting. These tasks involve both visual and spatiotemporal data, yet most existing methods treat them separately, hindering a unified underst
Vision-language-action models (VLAs) have garnered significant attention for their potential in advancing robotic manipulation. However, previous approaches predominantly rely on the general comprehension capabilities of vision-language models (VLMs) to generate action signals, often overlooking the…
Monitoring real-time air quality is essential for safeguarding public health and fostering social progress. However, the widespread deployment of air quality monitoring stations is constrained by their significant costs. To address this limitation, we introduce AirRadar, a deep neural network design…
Long-horizon reasoning and task execution are crucial for complex mobile manipulation tasks in household environments. Existing benchmarks and methods primarily focus on single-room or single-object mobile manipulation scenarios, limiting the scope of long-horizon planning and scene-level understand
Deep learning-based approaches have demonstrated significant advancements in time series forecasting. Despite these ongoing developments, the complex dynamics of time series make it challenging to establish the rule of thumb for designing the golden model architecture. In this study, we argue that r
Class Incremental Learning (CIL) aims to enable models to learn new classes sequentially while retaining knowledge of previous ones. Although current methods have alleviated catastrophic forgetting (CF), recent studies highlight that the performance of CIL models is highly sensitive to the order of…
Augmentation and knowledge distillation (KD) are well-established techniques employed in audio classification tasks, aimed at enhancing performance and reducing model sizes on the widely recognized Audioset (AS) benchmark. Although both techniques are effective individually, their combined use, call…
Vision-Language Navigation (VLN) with high-level language instructions is a crucial task in robotics. Existing VLN benchmarks, such as the REVERIE challenge which has single-goal instructions and limited navigation steps, do not fully encapsulate the complexity of real-world navigation that often re…
Air pollution is a crucial issue affecting human health and livelihoods, as well as one of the barriers to economic growth. Forecasting air quality has become an increasingly important endeavor with significant social impacts, especially in emerging countries. In this paper, we present a novel Trans…
Spatio-temporal prediction plays a critical role in smart city construction. Jointly modeling multiple spatio-temporal tasks can further promote an intelligent city life by integrating their inseparable relationship. However, existing studies fail to address this joint learning problem well, which g…
The success of deep learning heavily relies on large-scale data with comprehensive labels, which is more expensive and time-consuming to fetch in 3D compared to 2D images or natural languages. This promotes the potential of utilizing models pretrained with data more than 3D as teachers for cross-mod…
Visual information can serve as an effective cue for target speaker extraction (TSE) and is vital to improving extraction performance. In this paper, we propose AV-SepFormer, a SepFormer-based attention dual-scale model that utilizes cross- and self-attention to fuse and model features from audio an…
Learning descriptive 3D features is crucial for understanding 3D scenes with diverse objects and complex structures. However, it is usually unknown whether important geometric attributes and scene context obtain enough emphasis in an end-to-end trained 3D scene understanding network. To guide 3D fea…
Robust prediction of citywide traffic flows at different time periods plays a crucial role in intelligent transportation systems. While previous work has made great efforts to model spatio-temporal correlations, existing methods still suffer from two key limitations: i) Most models collectively pred…
Keyword spotting (KWS) is a core human-machine-interaction front-end task for most modern intelligent assistants. Recently, a unified (UniKW-AT) framework has been proposed that adds additional capabilities in the form of audio tagging (AT) to a KWS model. However, previous work did not consider the…
Cross-domain recommendation (CDR) aims to alleviate the data sparsity by transferring knowledge from an informative source domain to the target domain, which inevitably proposes stern challenges to data privacy and transferability during the transfer process. A small amount of recent CDR works have…
"The success of deep learning is usually accompanied by the growth in neural network depth. However, the traditional training method only supervises the neural network at its last layer and propagates the supervision layer-by-layer, which leads to hardship in optimizing the intermediate layers. Rece…
Large-scale audio tagging datasets inevitably contain imperfect labels, such as clip-wise annotated (temporally weak) tags with no exact on- and offsets, due to a high manual labeling cost. This work proposes pseudo strong labels (PSL), a simple label augmentation framework that enhances the supervi…
Recently, there has been a growing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. In this paper, we explore the use of attention-based encoder-decoder model for Mandarin speech recognition on a voice search task. Previous attempt…