Related papers: Daala: A Perceptually-Driven Still Picture Codec
Coding 4K data has become of vital interest in recent years, since the amount of 4K data is significantly increasing. We propose a coding chain with spatial down- and upscaling that combines the next-generation VVC codec with machine…
Recent studies suggest that context-aware low-rank approximation is a useful tool for compression and fine-tuning of modern large-scale neural networks. In this type of approximation, a norm is weighted by a matrix of input activations,…
Vision-Language-Action (VLA) models offer a compelling framework for tackling complex robotic manipulation tasks, but they are often expensive to train. In this paper, we propose a novel VLA approach that leverages the competitive…
In video-based emotion recognition, audio and visual modalities are often expected to have a complementary relationship, which is widely explored using cross-attention. However, they may also exhibit weak complementary relationships,…
We characterise some of the quirks and shortcomings in the exploration of Visual Dialogue - a sequential question-answering task where the questions and corresponding answers are related through given visual stimuli. To do so, we develop an…
Image retouching not only enhances visual quality but also serves as a means of expressing personal preferences and emotions. However, existing learning-based approaches require large-scale paired data and operate as black boxes, making the…
Latent Action Models (LAMs) enable the learning of world models from unlabeled video by inferring abstract actions between consecutive frames. However, LAMs face a fundamental trade-off between action abstraction and generation fidelity.…
In this paper we present DELTA, a deep learning based language technology platform. DELTA is an end-to-end platform designed to solve industry level natural language and speech processing problems. It integrates most popular neural network…
Recent learned image compression (LIC) leverages Mamba-style state-space models (SSMs) for global receptive fields with linear complexity. However, the standard Mamba adopts content-agnostic, predefined raster (or multi-directional) scans…
Precise camera pose control is crucial for video generation with diffusion models. Existing methods require fine-tuning with additional datasets containing paired videos and camera pose annotations, which are both data-intensive and…
Despite all the challenges and limitations, vision-based vehicle speed detection is gaining research interest due to its great potential benefits such as cost reduction, and enhanced additional functions. As stated in a recent survey [1],…
Rotation detection serves as a fundamental building block in many visual applications involving aerial image, scene text, and face etc. Differing from the dominant regression-based approaches for orientation estimation, this paper explores…
Intelligent code analysis has received increasing attention in parallel with the remarkable advances in the field of machine learning (ML) in recent years. A major challenge in leveraging ML for this purpose is to represent source code in a…
We present an efficient encoder-free approach for video-language understanding that achieves competitive performance while significantly reducing computational overhead. Current video-language models typically rely on heavyweight image…
In user-generated content (UGC) transcoding, source videos typically suffer various degradations due to prior compression, editing, or suboptimal capture conditions. Consequently, existing video compression paradigms that solely optimize…
Learning visual feature representations for video analysis is a daunting task that requires a large amount of training samples and a proper generalization framework. Many of the current state of the art methods for video captioning and…
Recent diffusion models have achieved remarkable success in image relighting, and this success has quickly been extended to video relighting. However, existing methods offer limited explicit control over illumination in the relighted…
Neural audio codecs are a fundamental component of modern generative audio pipelines. Although recent codecs achieve strong low-bitrate reconstruction and provide powerful representations for downstream tasks, most are non-streamable,…
Tracking dense 3D motion from monocular videos remains challenging, particularly when aiming for pixel-level precision over long sequences. We introduce DELTA, a novel method that efficiently tracks every pixel in 3D space, enabling…
In this paper, we propose Conceptual Codebook Learning (CoCoLe), a novel fine-tuning method for vision-language models (VLMs) to address the challenge of improving the generalization capability of VLMs while fine-tuning them on downstream…