Related papers: Bytes Are All You Need: Transformers Operating Dir…

Lack of audio-video synchronization is a common problem during television broadcasts and video conferencing, leading to an unsatisfactory viewing experience. A widely accepted paradigm is to create an error detection mechanism that…

The Transformer structures have been widely used in computer vision and have recently made an impact in the area of medical image registration. However, the use of Transformer in most registration networks is straightforward. These networks…

We introduce DeepInversion, a new method for synthesizing images from the image distribution used to train a deep neural network. We 'invert' a trained network (teacher) to synthesize class-conditional input images starting from random…

Human fashion understanding is one crucial computer vision task since it has comprehensive information for real-world applications. This focus on joint human fashion segmentation and attribute recognition. Contrary to the previous works…

We present BIEBER (Byte-IdEntical Binary parsER), the first system to model and regenerate a full working parser from instrumented program executions. To achieve this, BIEBER exploits the regularity (e.g., header fields and array-like data…

Editing images with instructions to reflect non-rigid motions, camera viewpoint shifts, object deformations, human articulations, and complex interactions, poses a challenging yet underexplored problem in computer vision. Existing…

We create a reusable Transformer, BrainBERT, for intracranial recordings bringing modern representation learning approaches to neuroscience. Much like in NLP and speech recognition, this Transformer enables classifying complex concepts,…

Modern vision backbones for 3D medical imaging typically process dense voxel grids through parameter-heavy encoder-decoder structures, a design that allocates a significant portion of its parameters to spatial reconstruction rather than…

The conventional, widely used treatment of deep learning models as black boxes provides limited or no insights into the mechanisms that guide neural network decisions. Significant research effort has been dedicated to building interpretable…

We present an end-to-end deep learning approach to denoising speech signals by processing the raw waveform directly. Given input audio containing speech corrupted by an additive background signal, the system aims to produce a processed…

While transformers demonstrate outstanding performance across various audio tasks, their application to neural vocoders remains challenging. Neural vocoders require the generation of long audio signals at the sample level, which demands…

The advent of Transformer-based models has surpassed the barriers of text. When working with speech, we must face a problem: the sequence length of an audio input is not suitable for the Transformer. To bypass this problem, a usual approach…

Human visual recognition is a sparse process, where only a few salient visual cues are attended to rather than traversing every detail uniformly. However, most current vision networks follow a dense paradigm, processing every single visual…

Most deep learning pipelines are built on real-valued operations to deal with real-valued inputs such as images, speech or music signals. However, a lot of applications naturally make use of complex-valued signals or images, such as MRI or…

A cognitive map is an internal model which encodes the abstract relationships among entities in the world, giving humans and animals the flexibility to adapt to new situations, with a strong out-of-distribution (OOD) generalization that…

Variant calling refinement is crucial for distinguishing true genetic variants from technical artifacts in high-throughput sequencing data. Manual review is time-consuming while heuristic filtering often lacks optimal solutions. Traditional…

Deep hamming hashing has gained growing popularity in approximate nearest neighbour search for large-scale image retrieval. Until now, the deep hashing for the image retrieval community has been dominated by convolutional neural network…

Deep neural speech and audio processing systems have a large number of trainable parameters, a relatively complex architecture, and require a vast amount of training data and computational power. These constraints make it more challenging…

Representation learning on networks aims to derive a meaningful vector representation for each node, thereby facilitating downstream tasks such as link prediction, node classification, and node clustering. In heterogeneous text-rich…

It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have…