Related papers: Dial-MAE: ConTextual Masked Auto-Encoder for Retri…

Trajectory prediction has been a crucial task in building a reliable autonomous driving system by anticipating possible dangers. One key issue is to generate consistent trajectory predictions without colliding. To overcome the challenge, we…

In multiple access channels (MAC), multiple users share a transmission medium to communicate with a common receiver. Traditional constellations like quadrature amplitude modulation are optimized for point-to-point systems and lack…

Perceiving multi-modal information and fulfilling dialogues with humans is a long-term goal of artificial intelligence. Pre-training is commonly regarded as an effective approach for multi-modal dialogue. However, due to the limited…

Pre-training a transformer-based model for the language modeling task in a large dataset and then fine-tuning it for downstream tasks has been found very useful in recent years. One major advantage of such pre-trained language models is…

Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision Transformers (ViT) for natural image analysis. By reconstructing full images from partially masked inputs, a ViT encoder aggregates contextual…

Generative autoencoders offer a promising approach for controllable text generation by leveraging their latent sentence representations. However, current models struggle to maintain coherent latent spaces required to perform meaningful text…

Audio classification and restoration are among major downstream tasks in audio signal processing. However, restoration derives less of a benefit from pretrained models compared to the overwhelming success of pretrained models in…

Effective spoken dialog systems should facilitate natural interactions with quick and rhythmic timing, mirroring human communication patterns. To reduce response times, previous efforts have focused on minimizing the latency in automatic…

Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual representation learning. It operates by randomly masking image patches and reconstructing these masked patches using the unmasked ones. A key limitation…

Dialogue discourse parsing aims to uncover the internal structure of a multi-participant conversation by finding all the discourse~\emph{links} and corresponding~\emph{relations}. Previous work either treats this task as a series of…

Deep learning-based models have greatly advanced the performance of speech enhancement (SE) systems. However, two problems remain unsolved, which are closely related to model generalizability to noisy conditions: (1) mismatched noisy…

Masked Autoencoders (MAEs) learn rich low-level representations from unlabeled data but require substantial labeled data to effectively adapt to downstream tasks. Conversely, Instance Discrimination (ID) emphasizes high-level semantics,…

With the exponential growth of multimedia data, leveraging multimodal sensors presents a promising approach for improving accuracy in human activity recognition. Nevertheless, accurately identifying these activities using both video data…

Masked Image Modeling (MIM) methods, like Masked Autoencoders (MAE), efficiently learn a rich representation of the input. However, for adapting to downstream tasks, they require a sufficient amount of labeled data since their rich features…

Understanding how the brain responds to sensory inputs is challenging: brain recordings are partial, noisy, and high dimensional; they vary across sessions and subjects and they capture highly nonlinear dynamics. These challenges have led…

Establishing correspondence between images or scenes is a significant challenge in computer vision, especially given occlusions, viewpoint changes, and varying object appearances. In this paper, we present Siamese Masked Autoencoders…

Network traffic classification using self-supervised pre-training models based on Masked Autoencoders (MAE) has demonstrated a huge potential. However, existing methods are confined to isolated byte-level reconstruction of individual flows,…

Multiturn dialogue models aim to generate human-like responses by leveraging conversational context, consisting of utterances from previous exchanges. Existing methods often neglect the interactions between these utterances or treat all of…

For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally…

Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised learning methods have achieved good performances with…