Related papers: Separable Temporal Convolution plus Temporally Poo…

Under modern test-time compute and agentic paradigms, language models process ever-longer sequences. Efficient text generation with transformer architectures is increasingly constrained by the Key-Value cache memory footprint and bandwidth.…

Toward the goal of automatic production for sports broadcasts, a paramount task consists in understanding the high-level semantic information of the game in play. For instance, recognizing and localizing the main actions of the game would…

The computing power of mobile devices limits the end-user applications in terms of storage size, processing, memory and energy consumption. These limitations motivate researchers for the design of more efficient deep models. On the other…

With the expansion of AI-powered virtual assistants, there is a need for low-power keyword spotting systems providing a "wake-up" mechanism for subsequent computationally expensive speech recognition. One promising approach is the use of…

Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity. A possible remedy is to reduce the sequence length in the intermediate layers by pooling fixed-length segments…

We propose smoothed max pooling loss and its application to keyword spotting systems. The proposed approach jointly trains an encoder (to detect keyword parts) and a decoder (to detect whole keyword) in a semi-supervised manner. The…

Self-supervised learning (SSL) models have achieved considerable improvements in automatic speech recognition (ASR). In addition, ASR performance could be further improved if the model is dedicated to audio content information learning…

Spoken keyword spotting (KWS) deals with the identification of keywords in audio streams and has become a fast-growing technology thanks to the paradigm shift introduced by deep learning a few years ago. This has allowed the rapid embedding…

Keyword spotting (KWS) has become an indispensable part of many intelligent devices surrounding us, as audio is one of the most efficient ways of interacting with these devices. The accuracy and performance of KWS solutions have been the…

In this paper, we propose a new video representation learning method, named Temporal Squeeze (TS) pooling, which can extract the essential movement information from a long sequence of video frames and map it into a set of few images, named…

The recognition of rare named entities, such as personal names and terminologies, is challenging for automatic speech recognition (ASR) systems, especially when they are not frequently observed in the training data. In this paper, we…

The continual learning (CL) ability is vital for deploying large language models (LLMs) in the dynamic world. Existing methods devise the learning module to acquire task-specific knowledge with parameter-efficient tuning (PET) block and the…

Generating video descriptions automatically is a challenging task that involves a complex interplay between spatio-temporal visual features and language models. Given that videos consist of spatial (frame-level) features and their temporal…

While Transformer self-attention offers strong parallelism, the Key-Value (KV) cache grows linearly with sequence length and becomes a bottleneck for inference efficiency. Multi-head latent attention was recently developed to compress the…

Lip-reading has attracted a lot of research attention lately thanks to advances in deep learning. The current state-of-the-art model for recognition of isolated words in-the-wild consists of a residual network and Bidirectional Gated…

Convolutional Pose Machine is a popular neural network architecture for articulated pose estimation. In this work we explore its empirical receptive field and realize, that it can be enhanced with integration of a global context. To do so…

We present a novel model designed for resource-efficient multichannel speech enhancement in the time domain, with a focus on low latency, lightweight, and low computational requirements. The proposed model incorporates explicit spatial and…

We present a motion-adaptive temporal attention mechanism for parameter-efficient video generation built upon frozen Stable Diffusion models. Rather than treating all video content uniformly, our method dynamically adjusts temporal…

Robustness against temporal variations is important for emotion recognition from speech audio, since emotion is ex-pressed through complex spectral patterns that can exhibit significant local dilation and compression on the time axis…

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide array of text-centric tasks. However, their `large' scale introduces significant computational and storage challenges, particularly in…