2018   • 2017 and before   •

Group Seminar

Date & Time Speakers Topic & Slides

Thursday, 17 May 2018, 19:30

Defa Zhu(朱德发) GAN-2

Wednesday, 16 May 2018, 19:00

Weibo Zhang(张卫博) 华大基因库

Wednesday, 16 May 2018, 19:00

Fan Tang(唐凡) google I/O 2018

Sunday, 13 May 2018, 19:30

Ruihe Qian(钱瑞和) 1.MoNet: Deep Motion Exploitation for Video Object Segmentation
2.Human Pose Estimation with Parsing Induced Learner

Saturday, 9 May 2018, 19:00

Han Yu(庾涵) 颜水成——人工智能杂谈

Saturday, 9 May 2018, 19:00

Runhe Yang(杨润河) 吴文俊院士生平与吴文俊人工智能奖

Saturday, 9 May 2018, 19:00

Fan Tang(唐凡) 优必选机器人

Saturday, 9 May 2018, 19:00

Xiaofan Cai(蔡晓帆) Semantic Instance Segmentation with a Discriminative Loss Function

Saturday, 5 May 2018, 14:00

Tianrui Hui(惠天瑞) deeplab v3+

Saturday, 5 May 2018, 14:00

Chen Gao(高晨) Image Inpainting for Irregular Holes Using Partial Convolutions

Saturday, 5 May 2018, 14:00

Ruihe Qian(钱瑞和) 1.Efficient Video Object Segmentation via Network Modulation
2.Dynamic Video Segmentation Network

Thursday, 5 May 2018, 19:00

Defa Zhu(朱德发) GAN-1

Wednesday, 2 May 2018, 19:00

Defa Zhu(朱德发) 1.Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
2.MUNIT: Multimodal UNsupervised Image-to-image TranslationPlug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space

Wednesday, 2 May 2018, 19:00

Lejian Ren(任乐健) 如何做一个“实用”的图像数据集

Wednesday, 2 May 2018, 19:00

Weibo Zhang(张卫博) video++

Wednesday, 2 May 2018, 19:00

Fan Tang(唐凡) 小朋汽车+BAT在ai领域的战略布局

Wednesday, 25 April 2018, 19:00

Guanghui Ren(任广辉) 1.Who Let The Dogs Out? Modeling Dog Behavior From Visual Data
2.endtoend flow correlation tracking with spatial-temporal Attention

Wednesday, 25 April 2018, 19:00

Fan Tang(唐凡) EPIC-Kitchens

Wednesday, 25 April 2018, 19:00

Han Yu(庾涵) Video Based Reconstruction of 3D People Models

Wednesday, 18 April 2018, 19:00

Tianrui Hui(惠天瑞) Multi-scale Deep Learning Architectures for Person Re-identification
Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval
Demystifying Neural Style Transfer

Wednesday, 18 April 2018, 19:00

Yue Liao(廖越) Richer Convolutional Features for Edge Detection

Wednesday, 18 April 2018, 19:00

Ruihe Qian(钱瑞和) An Analysis of Scale Invariance in Object Detection – SNIP

Saturday, 14 April 2018, 14:00

Ruihe Qian(钱瑞和) 1.Video Scene Parsing with Predictive Feature Learning
2.Fast and Accurate Online Video Object Segmentation via Tracking Parts
3.Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses

Saturday, 14 April 2018, 14:00

Shaofei Huang(黄少飞) 1. AttnGAN: Fine-grained text to image generation with attentional generative adversarial networks
2. 美妆商品图像识别大赛简介

Saturday, 14 April 2018, 14:00

Yue Liao(廖越) Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships

Saturday, 14 April 2018, 14:00

Fan Tang(唐凡) 从摩拜出售看共享经济

Saturday, 14 April 2018, 14:00

Guanghui Ren(任广辉) Low-Latency Video Semantic Segmentation

Wednesday, 11 April 2018, 19:00

Weibo Zhang(张卫博) 深度学习助力前端

Wednesday, 11 April 2018, 19:00

Chen Gao(高晨) Globally and Locally Consistent Image Completion

Wednesday, 11 April 2018, 19:00

Guanghui Ren(任广辉) Clockwork Convnets for Video Semantic Segmentation

Wednesday, 11 April 2018, 19:00

Tianrui Hui(惠天瑞) Generative Image Inpainting with Contextual Attention

Sunday, 8 April 2018, 19:00

Shaofei Huang(黄少飞) Caption 评价标准(机器翻译评价标准)

Sunday, 8 April 2018, 19:00

Lejian Ren(任乐健) Neural Motifs: Scene Graph Parsing with Global Context

Sunday, 8 April 2018, 19:00

Tianrui Hui(惠天瑞) Disentangled Person Image Generation

Wednesday, 4 April 2018, 19:00

Fan Tang(唐凡) uber无人驾驶事件

Wednesday, 4 April 2018, 19:00

Shaofei Huang(黄少飞) 本征图像

Wednesday, 4 April 2018, 19:00

Xiaofan Cai(蔡晓帆) Learning Spatiotemporal Features with 3D Convolutional Networks

Wednesday, 4 April 2018, 19:00

Renda Bao(包仁达) 1.Multi-Content GAN for Few-Shot Font Style Transfer
2.DeblurGAN Blind Motion Deblurring Using Conditional Adversarial Networks

Saturday, 31 March 2018, 14:00

Chen Gao(高晨) Context Encoding for Semantic Segmentation

Saturday, 31 March 2018, 14:00

Guanghui Ren(任广辉) 1.Deep Feature Flow for Video Recognition
2.Flow-Guided Feature Aggregation for Video Object Detection

Saturday, 31 March 2018, 14:00

Lejian Ren(任乐健) Generating Triples with Adversarial Networks for Scene Graph Construction

Wednesday, 28 March 2018, 19:00

WeiBo Zhang(张卫博) 了解火币网

Wednesday, 28 March 2018, 19:00

Lejian Ren(任乐健) Stereoscopic Neural Style Transfer

Wednesday, 28 March 2018, 19:00

Tianrui Hui(惠天瑞) PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model

Wednesday, 28 March 2018, 19:00

Shaofei Huang(黄少飞) 生成对抗网络评价标准

Saturday, 17 March 2018, 14:00

Shaofei Huang(黄少飞) 1.mobile real-time video segmentation
2.RTSEG:real-time semantic segmentation comparative study

Saturday, 17 March 2018, 14:00

Lejian Ren(任乐健) Visual Translation Embedding Network for Visual Relation Detection

Wednesday, 14 March 2018, 19:00

WeiBo Zhang(张卫博) 扫地机器人

Wednesday, 14 March 2018, 19:00

Guanghui Ren(任广辉) 1. Path Aggregation Network for Instance Segmentation br>2. Relation Networks for Object Detection

Wednesday, 14 March 2018, 19:00

Tianrui Hui(惠天瑞) Progressive Cognitive Human Parsing

Wednesday, 14 March 2018, 19:00

Renda Bao(包仁达) Face Mask Extraction in Video Sequence

Wednesday, 14 March 2018, 19:00

Fan Tang(唐凡) 智能养猪

Saturday, 11 March 2018, 14:00

Xiaofan Cai(蔡晓帆) SpaceX

Saturday, 11 March 2018, 14:00

SanBi Luo(罗三笔) 抖音

Saturday, 11 March 2018, 14:00

Guanghui Ren(任广辉) Semantic Object Parsing with Graph LSTM

Saturday, 11 March 2018, 14:00

Guanghui Ren(任广辉) Semantic Object Parsing with Graph LSTM

Saturday, 11 March 2018, 14:00

Ruihe Qian(钱瑞和) DA-GAN

Saturday, 11 March 2018, 14:00

Defa Zhu(朱德发) cGANs with Projection Discriminator

Saturday, 11 March 2018, 14:00

Yue Liao(廖越) Scene Graph Generation by Iterative Message Passing

Saturday, 3 March 2018, 14:00

Xiaofan Cai(蔡晓帆) Mix-and-Match Tuning for Self-Supervised Semantic Segmentation

Saturday, 3 March 2018, 14:00

Shaofei Huang(黄少飞) Fluorescence microscopy image segmentation using convolutional neural network with generative adversarial networks

Saturday, 3 March 2018, 14:00

Tianrui Hui(惠天瑞) An Iterative Spanning Forest Framework for Superpixel Segmentation

Saturday, 3 March 2018, 14:00

Chen Gao(高晨) DEEP LOGISMOS: DEEP LEARNING GRAPH-BASED 3D SEGMENTATION OF PANCREATIC TUMORS ON CT SCANS

Saturday, 3 February 2018, 14:00

Chen Gao(高晨) Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

Saturday, 3 February 2018, 14:00

Xiaofan Cai(蔡晓帆) Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis

Saturday, 3 February 2018, 14:00

Tianrui Hui(惠天瑞) Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption

Saturday, 3 February 2018, 14:00

Yue Liao(廖越) Pixels to Graphs by Associative Embedding

Saturday, 3 February 2018, 14:00

Defa Zhu(朱德发) Decoupled Learning for Conditional Adversarial Networks

Wednesday, 31 January 2018, 19:00

Xiaofan Cai(蔡晓帆) StuffNet: Using ‘Stuff’ to Improve Object Detection

Wednesday, 31 January 2018, 19:00

Han Yu(庾涵) 1.What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
2.VR介绍

Wednesday, 31 January 2018, 19:00

Lejian Ren(任乐健) Learning Face Age Progression: A Pyramid Architecture of GANs

Wednesday, 31 January 2018, 19:00

Ruihe Qian(钱瑞和) Unsupervised Visual Attribute Transfer with Reconfigurable Generative Adversarial Networks

Saturday, 27 January 2018, 14:00

Xiaofan Cai(蔡晓帆) Toward Multimodal Image-to-Image Translation

Saturday, 27 January 2018, 14:00

Chen Gao(高晨) Deformable GANs for Pose-based Human Image Generation

Saturday, 27 January 2018, 14:00

Shaofei Huang(黄少飞) Semi-supervised FusedGAN for Conditional Image Generation

Saturday, 27 January 2018, 14:00

Tianrui Hui(惠天瑞) 颜水成:像素级标注数据集将引领计算机视觉下一个时代

Wednesday, 24 January 2018, 19:00

Xiaofan Cai(蔡晓帆) Amazon Go

Wednesday, 24 January 2018, 19:00

Shaofei Huang(黄少飞) 图像质量评价标准

Wednesday, 24 January 2018, 19:00

Tianrui Hui(惠天瑞) Unsupervised Real-to-Virtual Domain Unification for End-to-End Highway Driving

Wednesday, 24 January 2018, 19:00

Han Yu(庾涵) Fast Patch-based Style Transfer of Arbitrary Style

Wednesday, 17 January 2018, 19:00

Runhe Tang(杨润河) Large Kernel Matters --- Improve Semantic Segmenttation by Global Convolutional Network.

Wednesday, 17 January 2018, 19:00

Ruihe Qian(钱瑞和) Region-based Quality Estimation Network for Large-scale Person Re-identification

Wednesday, 17 January 2018, 19:00

Chen Gao(高晨) Panoptic Segmentation and COCO-Stuff: Thing and Stuff Classes in Context

Wednesday, 17 January 2018, 19:00

Shaofei Huang(黄少飞) 人脸图像保护和网纹人脸识别

Saturday, 13 January 2018, 14:00

Renda Bao(包仁达) A survey of makeup

Saturday, 13 January 2018, 14:00

Shaofei Huang(黄少飞) Shadow Detection With Conditional Generative Adversarial Networks

Saturday, 13 January 2018, 14:00

Defa Zhu(朱德发) High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

Saturday, 13 January 2018, 14:00

Xiaofan Cai(蔡晓帆) 1.One-Shot Video Object Segmentation
2.DAVIS

Wednesday, 10 January 2018, 19:00

Ruihe Qian(钱瑞和) Evaluation of Segmentation Quality via Adaptive Composition of Reference Segmentations

Wednesday, 10 January 2018, 19:00

Lejian Ren(任乐健) Anti-Makeup: Learning A Bi-Level Adversarial Network for Makeup-Invariant Face Verification

Wednesday, 10 January 2018, 19:00

Chen Gao(高晨) SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes

Wednesday, 10 January 2018, 19:00

Weibo Zhang(张卫博) 1.Learning to Detect Human-Object Interactions
2.Detecting and Recognizing Human-Object Interactions

Saturday, 6 January 2018, 14:00

Yue Liao(廖越) Illuminating Pedestrians via Simultaneous Detection

Saturday, 6 January 2018, 14:00

Guanghui Ren(任广辉) Structure-measure: A New Way to Evaluate Foreground Maps

Saturday, 6 January 2018, 14:00

Defa Zhu(朱德发) Sparse Smart Contours to Represent and Edit Images

Saturday, 6 January 2018, 14:00

Renda Bao(包仁达) Deeply Supervised Salient Object Detection with Short Connections

Wednesday, 3 January 2018, 19:00

Xiaofan Cai(蔡晓帆) Spatial As Deep: Spatial CNN for Traffic Scene Understanding

Wednesday, 3 January 2018, 19:00

Lejian Ren(任乐健) Data Distillation: Towards Omni-Supervised Learning

Wednesday, 3 January 2018, 19:00

Han Yu(庾涵) 1.Unsupervised Learning of Stereo Matching
2.微软做了什么
3.Context-Aware Saliency Detection