Related papers: Tiled Squeeze-and-Excite: Channel Attention With L…
Selective image encryption is common in remote sensing systems because it protects sensitive regions of interest (ROI) while limiting computational cost. However, many selective designs enable cross-tile structural leakage under…
Sound Event Localization and Detection (SELD) is a problem related to the field of machine listening whose objective is to recognize individual sound events, detect their temporal activity, and estimate their spatial location. Thanks to the…
Developing a robust speech emotion recognition (SER) system in noisy conditions faces challenges posed by different noise properties. Most previous studies have not considered the impact of human speech noise, thus limiting the application…
Transformers have revolutionized natural language processing, but their quadratic complexity with respect to sequence length remains a fundamental bottleneck for long-range modeling. While sparse attention mechanisms like RingAttention…
Scene Text Recognition (STR), the task of recognizing text against complex image backgrounds, is an active area of research. Current state-of-the-art (SOTA) methods still struggle to recognize text written in arbitrary shapes. In this…
Standard transformer attention computes pairwise token similarity but treats all tokens as equally salient and all positions as equally local, regardless of the informational structure of the input. We identify two complementary inductive…
The attention mechanism within the transformer architecture enables the model to weigh and combine tokens based on their relevance to the query. While self-attention has enjoyed major success, it notably treats all queries $q$ in the same…
The Vision Transformer (ViT) has gained prominence for its superior relational modeling prowess. However, its global attention mechanism's quadratic complexity poses substantial computational burdens. A common remedy spatially groups tokens…
We present SegNeXt, a simple convolutional network architecture for semantic segmentation. Recent transformer-based models have dominated the field of semantic segmentation due to the efficiency of self-attention in encoding spatial…
Targeted syntactic evaluation of subject-verb number agreement in English (TSE) evaluates language models' syntactic knowledge using hand-crafted minimal pairs of sentences that differ only in the main verb's conjugation. The method…
Transformers often struggle to generalize to longer sequences than those seen during training, a limitation known as length extrapolation. Most existing Relative Positional Encoding (RPE) methods attempt to address this by introducing…
We developed a new and computationally simple local block-wise self attention based normal structures segmentation approach applied to head and neck computed tomography (CT) images. Our method uses the insight that normal organs exhibit…
Autoencoders have been widely used as a nonlinear tool for data dimensionality reduction. While autoencoders don't utilize the label information, Centroid-Encoders (CE)\cite{ghosh2022supervised} use the class label in their learning…
This paper presents TE-NeXt, a novel and efficient architecture for Traversability Estimation (TE) from sparse LiDAR point clouds based on a residual convolution block. TE-NeXt block fuses notions of current trends such as attention…
Recent advances in time series generation have shown promise, yet controlling properties in generated sequences remains challenging. Time Series Editing (TSE) - making precise modifications while preserving temporal coherence - consider…
Target speech extraction (TSE) typically relies on pre-recorded high-quality enrollment speech, which disrupts user experience and limits feasibility in spontaneous interaction. In this paper, we propose Enroll-on-Wakeup (EoW), a novel…
Spatial attention mechanism has been widely used in semantic segmentation of remote sensing images given its capability to model long-range dependencies. Many methods adopting spatial attention mechanism aggregate contextual information…
Target speech extraction (TSE) isolates the speech of a specific speaker from a multi-talker overlapped speech mixture. Most existing TSE models rely on discriminative methods, typically predicting a time-frequency spectrogram mask for the…
This work is an improved system that we submitted to task 1 of DCASE2023 challenge. We propose a method of low-complexity acoustic scene classification by a parallel attention-convolution network which consists of four modules, including…
We propose listen to extract (LExt), a highly-effective while extremely-simple algorithm for monaural target speaker extraction (TSE). Given an enrollment utterance of a target speaker, LExt aims at extracting the target speaker from the…