亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整的填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

Video Coding for Machines: Compact Visual Representation Compression for Intelligent Collaborative Analytics

计算机科学 人工智能 机器学习 视觉分析 编码(社会科学) 机器视觉 分析 可扩展性 分类 人机交互 计算机视觉 可视化 数据科学 数据库 数学 统计
作者
Wenhan Yang,Haofeng Huang,Yueyu Hu,Ling‐Yu Duan,Jiaying Liu
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [Institute of Electrical and Electronics Engineers]
卷期号:: 1-18 被引量:5
标识
DOI:10.1109/tpami.2024.3367293
摘要

As an emerging research practice leveraging recent advanced AI techniques, e.g. deep models based prediction and generation, Video Coding for Machines (VCM) is committed to bridging to an extent separate research tracks of video/image compression and feature compression, and attempts to optimize compactness and efficiency jointly from a unified perspective of high accuracy machine vision and full fidelity human vision. With the rapid advances of deep feature representation and visual data compression in mind, in this paper, we summarize VCM methodology and philosophy based on existing academia and industrial efforts. The development of VCM follows a general rate-distortion optimization, and the categorization of key modules or techniques is established including feature-assisted coding, scalable coding, intermediate feature compression/optimization, and machine vision targeted codec, from broader perspectives of vision tasks, analytics resources, etc. From previous works, it is demonstrated that, although existing works attempt to reveal the nature of scalable representation in bits when dealing with machine and human vision tasks, there remains a rare study in the generality of low bit rate representation, and accordingly how to support a variety of visual analytic tasks. Therefore, we investigate a novel visual information compression for the analytics taxonomy problem to strengthen the capability of compact visual representations extracted from multiple tasks for visual analytics. A new perspective of task relationships versus compression is revisited. By keeping in mind the transferability among different machine vision tasks (e.g. high-level semantic and mid-level geometry-related), we aim to support multiple tasks jointly at low bit rates. In particular, to narrow the dimensionality gap between neural network generated features extracted from pixels and a variety of machine vision features/labels (e.g. scene class, segmentation labels), a codebook hyperprior is designed to compress the neural network-generated features. As demonstrated in our experiments, this new hyperprior model is expected to improve feature compression efficiency by estimating the signal entropy more accurately, which enables further investigation of the granularity of abstracting compact features among different tasks.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
2秒前
ccc完成签到 ,获得积分10
4秒前
斯文败类应助梨梨lilili采纳,获得10
8秒前
47秒前
1分钟前
执着夏山发布了新的文献求助10
1分钟前
1分钟前
uikymh完成签到 ,获得积分0
1分钟前
2分钟前
李伟发布了新的文献求助10
2分钟前
2分钟前
皎皎完成签到,获得积分10
2分钟前
乐乐应助科研通管家采纳,获得10
2分钟前
cjx完成签到,获得积分10
3分钟前
3分钟前
3分钟前
henrychyeung发布了新的文献求助10
3分钟前
皎皎发布了新的文献求助10
3分钟前
4分钟前
4分钟前
包佳梁完成签到,获得积分10
4分钟前
henrychyeung完成签到,获得积分10
4分钟前
5分钟前
5分钟前
筱灬发布了新的文献求助10
5分钟前
5分钟前
狂野乌冬面完成签到 ,获得积分10
6分钟前
桐桐应助jjjjjj采纳,获得10
6分钟前
6分钟前
太叔夜南发布了新的文献求助10
6分钟前
太叔夜南完成签到,获得积分10
6分钟前
6分钟前
7分钟前
李剑鸿发布了新的文献求助200
7分钟前
炫哥IRIS完成签到,获得积分10
7分钟前
斯文败类应助执着夏山采纳,获得10
7分钟前
爆米花应助炫哥IRIS采纳,获得10
7分钟前
Hello应助执着夏山采纳,获得10
8分钟前
充电宝应助科研通管家采纳,获得10
8分钟前
8分钟前
高分求助中
Evolution 10000
Sustainability in Tides Chemistry 2800
The Young builders of New china : the visit of the delegation of the WFDY to the Chinese People's Republic 1000
юрские динозавры восточного забайкалья 800
English Wealden Fossils 700
叶剑英与华南分局档案史料 500
Foreign Policy of the French Second Empire: A Bibliography 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3146739
求助须知:如何正确求助?哪些是违规求助? 2798045
关于积分的说明 7826588
捐赠科研通 2454566
什么是DOI,文献DOI怎么找? 1306391
科研通“疑难数据库(出版商)”最低求助积分说明 627708
版权声明 601527