AlgoFei的博客

智东西-自动驾驶系列课第4课课件-低速自动驾驶专用车的技术挑战与前景-智行者联合创始人李晓飞

Recurrent neural network based language model Word representations: A simple and general method for semi-supervised learning Natural Language Processing (Almost) from Scratch Efficient Estimation of Word Representations in Vector Space 。。。。。。 NEURAL MACHINE TRANSLATION BY JOINTLY LEARNING TO ALIGN AND TRANSLATE Learning to Compose Neural Networks for Question Answering

Human-level control through deep reinforcement learning Playing Atari with Deep Reinforcement Learning Deep Learning for Detecting Robotic Grasps Mastering the game of Go with deep neural networks and tree search ........

2010-boureau-cvpr-10.pdf 2012-farabet-pami-13.pdf 2013-10.1.1.224.9632.pdf 2013-1310.1531v1.pdf 2013-Ji_TPAMI2013.pdf 2013-wang_iccv13.pdf 2014-DeepFace-Closing-the-Gap-to-Human-Level-Performance.pdf 2014-Oquab_Learning_and_Transferring_2014_CVPR_paper.pdf 2016-1411.4389v4.pdf 2015-Xiangxue_Spatial Pyramid Pooling.pdf 。。。。。。 ....... 2016-1506.01497v3.pdf 图像识别深度学习经典论文r-cnn、faster rcnn、rpn、fcn、transfer learning等等

时间地理分布2 人工智能企业投资排名9 应用领域分析1 3 人工智能技术分支相关产业分析2 0

人工智能发展现状分析 人工智能应用现状分析 人工智能前景及市场机会分析

CVPR论文合集--SLAM DNN CNN 目标检测与目标识别 视频目标分割 图像分割 自然语言处理 自动驾驶

CVPR-2018论文合集--SLAM DNN CNN 目标检测与目标识别 视频目标分割 图像分割 自然语言处理 自动驾驶

CVPR论文合集--SLAM DNN CNN 目标检测与目标识别 视频目标分割 图像分割 自然语言处理 自动驾驶

CVPR论文合集--SLAM DNN CNN 目标检测与目标识别 视频目标分割 图像分割 自然语言处理 自动驾驶

人机融合智能是一种新型智能形式，它不同于人的智能、也不同于人工智能，是一种跨物种越属性结合的下一代智能科学体系。如果说真就是Being，善就是Should，美就是Being+Should的融合；假设机就是Being，人就是Should，那么人机就是Being+Should的融合。同时，人机融合智能也是东西方文明的共同结晶体现。

随着行业发展环境的趋好，人工智能芯片企业间的竞争将不断加剧，行业内企业间并购整合与资本运作将日趋频繁，优秀的人工智能芯片企业必须重视对行业市场的研究，特别是对企业发展环境和客户需求趋势变化的深入研究。

当前，新一轮科技革命和产业变革正在萌发，大数据的形成、理论算法的革新、计算能力的提升及网络设施的演进驱动人工智能发展进入新阶段，智能化成为技术和产业发展的重要方向。人工智能具有显著的溢出效应，将进一步带动其他技术的进步，推动战略性新兴产业总体突破，正在成为推进供给侧结构性改革的新动能、振兴实体经济的新机遇、建设制造强国和网络强国的新引擎。为落实《新一代人工智能发展规划》，深入实施“中国制造2025”，抓住历史机遇，突破重点领域，促进人工智能产业发展，提升制造业智能化水平，推动人工智能和实体经济深度融合，制订本行动计划。

汽车产业是国民经济重要的战略性、支柱，与人群 汽车产业是国民经济重要的战略性、支柱，与人群 汽车产业是国民经济重要的战略性、支柱，与人群 众生活密切相关。本世纪以来， 我国汽车产业快速发展众生活密切相关。本世纪以来， 我国汽车产业快速发展众生活密切相关。本世纪以来， 我国汽车产业快速发展产业 规 模稳居世界首位 ，综合实力显著增强。随着汽车普及程度不断 ，综合实力显著增强。随着汽车普及程度不断 ，综合实力显著增强。随着汽车普及程度不断 提 高，我国已快速进入汽车社会。当前新一轮科技 高，我国已快速进入汽车社会。当前新一轮科技 高，我国已快速进入汽车社会。当前新一轮科技 高，我国已快速进入汽车社会。当前新一轮科技 革命和产业变 革蓬勃兴起 ，智 能汽车已成为产业发展的战略方向。，智 能汽车已成为产业发展的战略方向。，智 能汽车已成为产业发展的战略方向。能汽车不仅是解决社会面临的交通安全、道路拥堵源消 能汽车不仅是解决社会面临的交通安全、道路拥堵源消 能汽车不仅是解决社会面临的交通安全、道路拥堵源消 耗、环境污染 等问题 的重要手段，更是深化供给侧结构性改革、 实施创新驱动发展战略、 建成 现代化强国的重要支撑，对不断满 现代化强国的重要支撑，对不断满 足人民日益增长的美好生活需要具有十分重意义。为加快 足人民日益增长的美好生活需要具有十分重意义。

SLAM DNN CNN 目标检测与目标识别 视频目标分割 图像分割 自然语言处理 自动驾驶

1.NeuroPilot 可实现的手机AI 应用 2.手机AI的挑战 3.NeuroPilot如何克服这些挑战 4.功耗功耗

1. 如何打造可大规模量产的自主代客泊车系统 2. 纵目科技 3. 智东西

We present a new compact but dense representation of scene geometry which is conditioned on the intensity data from a single image and generated from a code consisting of a small number of parameters. We are inspired by work both on learned depth from images, and auto-encoders. Our approach is suitable for use in a keyframe-based monocular dense SLAM system: While each keyframe with a code can produce a depth map, the code can be optimised efficiently jointly with pose variables and together with the codes of overlapping keyframes to attain global consistency. Condi- tioning the depth map on the image allows the code to only represent aspects of the local geometry which cannot di- rectly be predicted from the image. We explain how to learn our code representation, and demonstrate its advantageous properties in monocular SLAM.

Zero-shot artistic style transfer is an important image synthesis problem aiming at transferring arbitrary style into content images. However, the trade-off between the gener- alization and efficiency in existing methods impedes a high quality zero-shot style transfer in real-time. In this pa- per, we resolve this dilemma and propose an efficient yet effective Avatar-Net that enables visually plausible multi- scale transfer for arbitrary style. The key ingredient of our method is a style decorator that makes up the content fea- tures by semantically aligned style features from an arbi- trary style image, which does not only holistically match their feature distributions but also preserve detailed style patterns in the decorated features. By embedding this mod- ule into an image reconstruction network that fuses multi- scale style abstractions, the Avatar-Net renders multi-scale stylization for any style image in one feed-forward pass. We demonstrate the state-of-the-art effectiveness and effi- ciency of the proposed method in generating high-quality stylized images, with a series of successive applications in- clude multiple style integration, video stylization and etc.

This paper addresses the problem of video object segmentation, where the initial object mask is given in the first frame of an input video. We propose a novel spatiotemporal Markov Random Field (MRF) model defined over pixels to handle this problem. Unlike conventional MRF models, the spatial dependencies among pixels in our model are encoded by a Convolutional Neural Network (CNN). Specifically, for a given object, the probability of a labeling to a set of spatially neighboring pixels can be predicted by a CNN trained for this specific object. As a result, higher-order, richer dependencies among pixels in the set can be implicitly modeled by the CNN. With temporal dependencies established by optical flow, the resulting MRF model combines both spatial and temporal cues for tackling video object segmentation. However, performing inference in the MRF model is very difficult due to the very highorder dependencies. To this end, we propose a novel CNNembedded algorithm to perform approximate inference in the MRF. This algorithm proceeds by alternating between a temporal fusion step and a feed-forward CNN step. When initialized with an appearance-based one-shot segmentation CNN, our model outperforms the winning entries of the DAVIS 2017 Challenge, without resorting to model ensembling or any dedicated detectors.

Observing that Semantic features learned in an image classification task and Appearance features learned in a similarity matching task complement each other, we build a twofold Siamese network, named SA-Siam, for real-time object tracking. SA-Siam is composed of a semantic branch and an appearance branch. Each branch is a similarity- learning Siamese network. An important design choice in SA-Siam is to separately train the two branches to keep the heterogeneity of the two types of features. In addi- tion, we propose a channel attention mechanism for the semantic branch. Channel-wise weights are computed ac- cording to the channel activations around the target posi- tion. While the inherited architecture from SiamFC [3] al- lows our tracker to operate beyond real-time, the twofold design and the attention mechanism significantly improve the tracking performance. The proposed SA-Siam outper- forms all other real-time trackers by a large margin on OTB-2013/50/100 benchmarks. 1. Introduction

Neural networks have recently become good at engaging in dialog. However, current approaches are based solely on verbal text, lacking the richness of a real face-to-face conversation. We propose a neural conversation model that aims to read and generate facial gestures alongside with text. This allows our model to adapt its response based on the “mood” of the conversation. In particular, we introduce an RNN encoder-decoder that exploits the movement of facial muscles, as well as the verbal conversation. The decoder consists of two layers, where the lower layer aims at generating the verbal response and coarse facial expressions, while the second layer fills in the subtle gestures, making the generated output more smooth and natural. We train our neural network by having it “watch” 250 movies. We showcase our joint face-text model in generating more natural conversations through automatic metrics and a human study. We demonstrate an example application with a face-to-face chatting avatar.

We present a fast inverse-graphics framework for instance-level 3D scene understanding. We train a deep convolutional network that learns to map image regions to the full 3D shape and pose of all object instances in the image. Our method produces a compact 3D representation of the scene, which can be readily used for applications like autonomous driving. Many traditional 2D vision outputs, like instance segmentations and depth-maps, can be obtained by simply rendering our output 3D scene model. We exploit class-specific shape priors by learning a low dimensional shape-space from collections of CAD models. We present novel representations of shape and pose, that strive towards better 3D equivariance and generalization. In order to exploit rich supervisory signals in the form of 2D annotations like segmentation, we propose a differentiable Render-and-Compare loss that allows 3D shape and pose to be learned with 2D supervision. We evaluate our method on the challenging real-world datasets of Pascal3D+ and KITTI, where we achieve state-of-the-art results.

Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is naturally dense (e.g., photos), many other data sources are inherently sparse. Examples include 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard “dense” implementations of convolutional networks are very inefficient when applied on such sparse data. We introduce new sparse convolutional operations that are designed to process spatially-sparse data more efficiently, and use them to develop spatially-sparse convolutional networks. We demonstrate the strong performance of the resulting models, called submanifold sparse convolutional networks (SSCNs), on two tasks involving semantic segmentation of 3D point clouds. In particular, our models outperform all prior state-of-the-art on the test set of a recent semantic segmentation competition

We propose a scalable, efficient and accurate approach to retrieve 3D models for objects in the wild. Our contri- bution is twofold. We first present a 3D pose estimation approach for object categories which significantly outper- forms the state-of-the-art on Pascal3D+. Second, we use the estimated pose as a prior to retrieve 3D models which accurately represent the geometry of objects in RGB im- ages. For this purpose, we render depth images from 3D models under our predicted pose and match learned im- age descriptors of RGB images against those of rendered depth images using a CNN-based multi-view metric learn- ing approach. In this way, we are the first to report quanti- tative results for 3D model retrieval on Pascal3D+, where our method chooses the same models as human annota- tors for 50% of the validation images on average. In ad- dition, we show that our method, which was trained purely on Pascal3D+, retrieves rich and accurate 3D models from ShapeNet given RGB images of objects in the wild.

智能网联汽车评价体系介绍 自动驾驶 智能网联汽车 评价体系 人工之鞥

20170926-国家智能网联汽车（上海）试点示范区.pdf 自动驾驶 人工智能

20171024第19届亚太汽车工程年会 自动驾驶 车联网 V2X 人工智能 深度学习 新能源

开放合作，构建自动驾驶新生态 Opening and Cooperation to build up a New Eco-system of Autonomous Driving

VALSE大会现场PPT 深度学习 计算机视觉 图像处理 人工智能 自动驾驶 自然语言处理 SLAM

CVPR-2018论文合集--SLAM DNN CNN 目标检测与目标识别 视频目标分割 图像分割 自然语言处理 自动驾驶

CVPR-2018论文合集--SLAM DNN CNN 目标检测与目标识别 视频目标分割 图像分割 自然语言处理 自动驾驶

CVPR-2018论文合集--SLAM DNN CNN 目标检测与目标识别 视频目标分割 图像分割 自然语言处理 自动驾驶

智能驾驶进程与毫米波雷达技术动态 自动驾驶感知与传感器技术 毫米波障碍物与行人检测

第六次ADAS国标制定系列工作会议-第一次会议-2018.1-杭州

智东西-自动驾驶系列课第5课课件-激光雷达在辅助驾驶和无人驾驶中的应用-镭神智能董事长胡小波

智东西-自动驾驶系列课第6课课件-新造车务实派如何落地自动驾驶-小鹏汽车肖志光-

智东西-自动驾驶系列课第7课课件-基于激光雷达的地图创建与定位-速腾聚创创始人邱纯鑫

智东西公开课-自动驾驶系列课课件-李文俊-禾多科技-0522 自动驾驶、代客泊车、深度学习、公开课

自动驾驶的感知定位与高精地图解决方案-DeepMotion联合创始人-蔡锐 深度学习、SLAM、激光雷达、高精度地图