相关论文: Global-Local Distillation Network-Based Audio-Visu…

Pre-trained multilingual language models (LMs) have achieved state-of-the-art results in cross-lingual transfer, but they often lead to an inequitable representation of languages due to limited capacity, skewed pre-training data, and…

State-of-the-art CNN based recognition models are often computationally prohibitive to deploy on low-end devices. A promising high level approach tackling this limitation is knowledge distillation, which let small student model mimic…

Real-time speech-driven 3D facial animation has been attractive in academia and industry. Traditional methods mainly focus on learning a deterministic mapping from speech to animation. Recent approaches start to consider the…

Active speaker detection (ASD) is a multi-modal task that aims to identify who, if anyone, is speaking from a set of candidates. Current audio-visual approaches for ASD typically rely on visually pre-extracted face tracks (sequences of…

Existing Transformer-based RGBT tracking methods either use cross-attention to fuse the two modalities, or use self-attention and cross-attention to model both modality-specific and modality-sharing information. However, the significant…

Deepfakes are synthetic media generated using deep generative algorithms and have posed a severe societal and political threat. Apart from facial manipulation and synthetic voice, recently, a novel kind of deepfakes has emerged with either…

Lipreading is a challenging cross-modal task that aims to convert visual lip movements into spoken text. Existing lipreading methods often extract visual features that include speaker-specific lip attributes (e.g., shape, color, texture),…

The increased amount of multi-modal medical data has opened the opportunities to simultaneously process various modalities such as imaging and non-imaging data to gain a comprehensive insight into the disease prediction domain. Recent…

We present SDTracker, a method that harnesses the potential of synthetic data for multi-object tracking of real-world scenes in a domain generalization and semi-supervised fashion. First, we use the ImageNet dataset as an auxiliary to…

We introduce 3D-Speaker-Toolkit, an open-source toolkit for multimodal speaker verification and diarization, designed for meeting the needs of academic researchers and industrial practitioners. The 3D-Speaker-Toolkit adeptly leverages the…

Visual anomaly detection is a challenging open-set task aimed at identifying unknown anomalous patterns while modeling normal data. The knowledge distillation paradigm has shown remarkable performance in one-class anomaly detection by…

Unsupervised anomaly detection encompasses diverse applications in industrial settings where a high-throughput and precision is imperative. Early works were centered around one-class-one-model paradigm, which poses significant challenges in…

Deep learning has shown its efficacy in extracting useful features to solve various computer vision tasks. However, when the structure of the data is complex and noisy, capturing effective information to improve performance is very…

Satellite videos provide continuous observations of surface dynamics but pose significant challenges for multi-object tracking (MOT), especially under unstabilized conditions where platform jitter and the weak appearance of tiny objects…

Generative retrieval is a promising new paradigm in text retrieval that generates identifier strings of relevant passages as the retrieval target. This paradigm leverages powerful generative language models, distinct from traditional sparse…

Reconstructing high-fidelity flow fields from low-fidelity observations is a central problem in scientific machine learning, yet recent diffusion and flow-matching models typically rely on iterative sampling, making them costly for…

Rehearsal-based video incremental learning often employs knowledge distillation to mitigate catastrophic forgetting of previously learned data. However, this method faces two major challenges for video task: substantial computing resources…

Compared to large speech foundation models, small distilled models exhibit degraded noise robustness. The student's robustness can be improved by introducing noise at the inputs during pre-training. Despite this, using the standard…

Most existing federated learning algorithms are based on the vanilla FedAvg scheme. However, with the increase of data complexity and the number of model parameters, the amount of communication traffic and the number of iteration rounds for…

The deep complex convolution recurrent network (DCCRN) achieves excellent speech enhancement performance by utilizing the audio spectrum's complex features. However, it has a large number of model parameters. We propose a smaller model,…