Related papers: Symmetric Entropy-Constrained Video Coding for Mac…
Task-driven semantic video/image coding has drawn considerable attention with the development of intelligent media applications, such as license plate detection, face detection, and medical diagnosis, which focuses on maintaining the…
Code has emerged as a precise and executable medium for reasoning and action in the agent era. Yet, progress has largely focused on language-centric tasks such as program synthesis and debugging, leaving visual-centric coding underexplored.…
In this paper, we propose a high-efficiency deep joint source-channel coding (JSCC) method for video transmission based on conditional coding with asymmetric context. The conditional coding-based neural video compression requires to predict…
Vision-Language Models (VLMs) have achieved remarkable success in various multi-modal tasks, but they are often bottlenecked by the limited context window and high computational cost of processing high-resolution image inputs and videos.…
Vision-Language Pretraining (VLP) has shown impressive results on diverse downstream tasks by offline training on large-scale datasets. Regarding the growing nature of real-world data, such an offline training paradigm on ever-expanding…
Distinct from attention-based compression methods, this paper presents an information uniqueness driven video compression framework, termed UniComp, which aims to maximize the information fidelity of video representations under constrained…
Semantic maps are increasingly utilized in areas such as robotics, autonomous systems, and extended reality, motivating the investigation of efficient compression methods that preserve structured semantic information. This paper studies…
Image Compression for Machines (ICM) aims to compress images for machine vision tasks rather than human viewing. Current works predominantly concentrate on high-level tasks like object detection and semantic segmentation. However, the…
Increasingly, visual signals such as images, videos and point clouds are being captured solely for the purpose of automated analysis by computer vision models. Applications include traffic monitoring, robotics, autonomous driving, smart…
Vision-Language Models (VLMs) have demonstrated strong capabilities in multimodal understanding and generation tasks. However, their application to long video understanding remains hindered by the quadratic complexity of standard attention…
Satellite imagery differs fundamentally from natural images: its aerial viewpoint, very high resolution, diverse scale variations, and abundance of small objects demand both region-level spatial reasoning and holistic scene understanding.…
Most Neural Video Codecs (NVCs) only employ temporal references to generate temporal-only contexts and latent prior. These temporal-only NVCs fail to handle large motions or emerging objects due to limited contexts and misaligned latent…
Feature coding for machines (FCM) is a lossy compression paradigm for split-inference. The transmitter encodes the outputs of the first part of a neural network before sending them to the receiver for completing the inference. Practical FCM…
Balancing temporal resolution and spatial detail under limited compute budget remains a key challenge for video-based multi-modal large language models (MLLMs). Existing methods typically compress video representations using predefined…
Optimized for pixel fidelity metrics, images compressed by existing image codec are facing systematic challenges when used for visual analysis tasks, especially under low-bitrate coding. This paper proposes a visual analysis-motivated…
Large Vision-Language Models (LVLMs) encode visual inputs as dense sequences of patch-level tokens to capture fine-grained semantics. These visual tokens often outnumber their textual counterparts by a large margin, leading to substantial…
We present READMem (Robust Embedding Association for a Diverse Memory), a modular framework for semi-automatic video object segmentation (sVOS) methods designed to handle unconstrained videos. Contemporary sVOS works typically aggregate…
Current large vision-language models (VLMs) often encounter challenges such as insufficient capabilities of a single visual component and excessively long visual tokens. These issues can limit the model's effectiveness in accurately…
Recent advances in Multi-modal Large Language Models (MLLMs) have shown significant progress in open-world Visual Question Answering (VQA). However, integrating visual information increases the number of processed tokens, leading to higher…
In recent years, the field of learned video compression has witnessed rapid advancement, exemplified by the latest neural video codecs DCVC-DC that has outperformed the upcoming next-generation codec ECM in terms of compression ratio.…