Related papers: AdaSFormer: Adaptive Serialized Transformers for M…
Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. However, existing neural models have been shown to lack this basic ability in learning symbolic…
It is well believed that Transformer performs better in semantic segmentation compared to convolutional neural networks. Nevertheless, the original Vision Transformer may lack of inductive biases of local neighborhoods and possess a high…
Designing mechanical mechanisms to trace specific paths is a classic yet notoriously difficult engineering problem, characterized by a vast and complex search space of discrete topologies and continuous parameters. We introduce MechaFormer,…
Adaptive gradient methods have become popular in optimizing deep neural networks; recent examples include AdaGrad and Adam. Although Adam usually converges faster, variations of Adam, for instance, the AdaBelief algorithm, have been…
Neural networks for visual content understanding have recently evolved from convolutional ones (CNNs) to transformers. The prior (CNN) relies on small-windowed kernels to capture the regional clues, demonstrating solid local expressiveness.…
End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the…
Semantic encoders and decoders for digital semantic communication (SC) often struggle to adapt to variations in unpredictable channel environments and diverse system designs. To address these challenges, this paper proposes a novel…
Monocular Semantic Scene Completion (SSC) aims to reconstruct complete 3D semantic scenes from a single RGB image, offering a cost-effective solution for autonomous driving and robotics. However, the inherently imbalanced nature of voxel…
Recently, deep autoencoders have gained traction as a powerful method for implementing goal-oriented semantic communications systems. The idea is to train a mapping from the source domain directly to channel symbols, and vice versa.…
Image segmentation is often ambiguous at the level of individual image patches and requires contextual information to reach label consensus. In this paper we introduce Segmenter, a transformer model for semantic segmentation. In contrast to…
Entropy modeling is a key component for high-performance image compression algorithms. Recent developments in autoregressive context modeling helped learning-based methods to surpass their classical counterparts. However, the performance of…
Time series forecasting (TSF) faces challenges in modeling complex intra-channel temporal dependencies and inter-channel correlations. Although recent research has highlighted the efficiency of linear architectures in capturing global…
Multivariate time series classification is a crucial task in data mining, attracting growing research interest due to its broad applications. While many existing methods focus on discovering discriminative patterns in time series,…
Spatio-temporal sensor data in real-world systems is often sparse, noisy, and irregular, making latent field reconstruction fundamentally underconstrained. Under extreme sparsity, multiple physically plausible fields may remain consistent…
Long-term weather forecasting is critical for socioeconomic planning and disaster preparedness. While recent approaches employ finetuning to extend prediction horizons, they remain constrained by the issues of catastrophic forgetting, error…
Given an input video, its associated audio, and a brief caption, the audio-visual scene aware dialog (AVSD) task requires an agent to indulge in a question-answer dialog with a human about the audio-visual content. This task thus poses a…
Depth estimation provides an alternative approach for perceiving 3D information in autonomous driving. Monocular depth estimation, whether with single-frame or multi-frame inputs, has achieved significant success by learning various types…
Real world images often have highly imbalanced content density. Some areas are very uniform, e.g., large patches of blue sky, while other areas are scattered with many small objects. Yet, the commonly used successive grid downsampling…
Transformer has shown great successes in natural language processing, computer vision, and audio processing. As one of its core components, the softmax attention helps to capture long-range dependencies yet prohibits its scale-up due to the…
Ensuring safety in autonomous driving is a complex challenge requiring handling unknown objects and unforeseen driving scenarios. We develop multiscale video transformers capable of detecting unknown objects using only motion cues. Video…