Related papers: Causal Context Adjustment Loss for Learned Image C…

Recently, numerous end-to-end optimized image compression neural networks have been developed and proved themselves as leaders in rate-distortion performance. The main strength of these learnt compression methods is in powerful nonlinear…

While multimodal data integrating diverse imaging and clinical tabular records is crucial for accurate medical diagnosis, the arbitrary absence of specific modalities is prevalent in clinical practice, severely degrading the performance of…

Learned Image Compression (LIC) has recently become the trending technique for image transmission due to its notable performance. Despite its popularity, the robustness of LIC with respect to the quality of image reconstruction remains…

Contrastive Language-Image Pretraining (CLIP) excels at learning generalizable image representations but often falls short in zero-shot inference on certain downstream datasets. Test-time adaptation (TTA) mitigates this issue by adjusting…

Long-context inputs in large language models (LLMs) often suffer from the "lost in the middle" problem, where critical information becomes diluted or ignored due to excessive length. Context compression methods aim to address this by…

Task-agnostic prompt compression leverages the redundancy in natural language to reduce computational overhead and enhance information density within prompts, especially in long-context scenarios. Existing methods predominantly rely on…

Recent advances in generalized image understanding have seen a surge in the use of deep convolutional neural networks (CNN) across a broad range of image-based detection, classification and prediction tasks. Whilst the reported performance…

Learned Image Compression (LIC) models have achieved superior rate-distortion performance than traditional codecs. Existing LIC models use CNN, Transformer, or Mixed CNN-Transformer as basic blocks. However, limited by the shifted window…

Lossy compression introduces complex compression artifacts, particularly blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restore sharpened…

There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ranking of training samples, but strongly overfit semantically inconsistent labels and require a…

Neural cellular automata represent an evolution of the traditional cellular automata model, enhanced by the integration of a deep learning-based transition function. This shift from a manual to a data-driven approach significantly increases…

Context-Aware Emotion Recognition (CAER) is a crucial and challenging task that aims to perceive the emotional states of the target person with contextual information. Recent approaches invariably focus on designing sophisticated…

By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words. However, for real-world voice assistants, always biasing on such personalized words…

Convolutional neural networks (CNNs) achieve state-of-the-art accuracy in a variety of tasks in computer vision and beyond. One of the major obstacles hindering the ubiquitous use of CNNs for inference on low-power edge devices is their…

Modern large vision-language models (LVLMs) convert each input image into a large set of tokens that far outnumber the text tokens. Although this improves visual perception, it also introduces severe image token redundancy. Because image…

There is often a trade-off between performance and latency in streaming automatic speech recognition (ASR). Traditional methods such as look-ahead and chunk-based methods, usually require information from future frames to advance…

Autoregressive transformers have recently shown impressive image generation quality and efficiency on par with state-of-the-art diffusion models. Unlike diffusion architectures, autoregressive models can naturally incorporate arbitrary…

In recent deep image compression neural networks, the entropy model plays a critical role in estimating the prior distribution of deep image encodings. Existing methods combine hyperprior with local context in the entropy estimation…

The popularity of Convolutional Neural Network (CNN) in the field of Image Processing and Computer Vision has motivated researchers and industrialist experts across the globe to solve different challenges with high accuracy. The simplest…

A deep image compression scheme is proposed in this paper, offering the state-of-the-art compression efficiency, against the traditional JPEG, JPEG2000, BPG and those popular learning based methodologies. This is achieved by a novel…