今日CS.CV計算機視覺論文速覽
Thu, 22 Nov 2018
Totally 47 papers

Daily Computer Vision Papers

[1] Title: HAQ: Hardware-Aware Automated Quantization
Authors:Kuan Wang, Zhijian Liu, Yujun Lin, Ji Lin, Song Han
[2] Title: Rethinking ImageNet Pre-training
Authors:Kaiming He, Ross Girshick, Piotr Dollár

[3] Title: fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
Authors:Jure Zbontar, Florian Knoll, Anuroop Sriram, Matthew J. Muckley, Mary Bruno, Aaron Defazio, Marc Parente, Krzysztof J. Geras, Joe Katsnelson, Hersh Chandarana, Zizhao Zhang, Michal Drozdzal, Adriana Romero, Michael Rabbat, Pascal Vincent, James Pinkerton, Duo Wang, Nafissa Yakubova, Erich Owens, C. Lawrence Zitnick, Michael P. Recht, Daniel K. Sodickson, Yvonne W. Lui
[4] Title: Recognizing Disguised Faces in the Wild
Authors:Maneet Singh, Richa Singh, Mayank Vatsa, Nalini Ratha, Rama Chellappa
[5] Title: Early Fusion for Goal Directed Robotic Vision
Authors:Aaron Walsman, Yonatan Bisk, Saadia Gabriel, Dipendra Misra, Yoav Artzi, Yejin Choi, Dieter Fox
[6] Title: Trajectory PHD and CPHD filters
Authors:Ángel F. García-Fernández, Lennart Svensson
[7] Title: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection
Authors:Khoi-Nguyen C. Mac, Dhiraj Joshi, Raymond A. Yeh, Jinjun Xiong, Rogerio R. Feris, Minh N. Do
[8] Title: Dynamic-Net: Tuning the Objective Without Re-training
Authors:Alon Shoshan, Roey Mechrez, Lihi Zelnik-Manor
[9] Title: Chan-Vese Reformulation for Selective Image Segmentation
Authors:Michael Roberts, Jack Spencer
[10] Title: Gated Context Aggregation Network for Image Dehazing and Deraining
Authors:Dongdong Chen, Mingming He, Qingnan Fan, Jing Liao, Liheng Zhang, Dongdong Hou, Lu Yuan, Gang Hua
[11] Title: Semantic Stereo for Incidental Satellite Images
Authors:Marc Bosch, Kevin Foster, Gordon Christie, Sean Wang, Gregory D Hager, Myron Brown
[12] Title: SpotTune: Transfer Learning through Adaptive Fine-tuning
Authors:Yunhui Guo, Honghui Shi, Abhishek Kumar, Kristen Grauman, Tajana Rosing, Rogerio Feris
[13] Title: AttentionMask: Attentive, Efficient Object Proposal Generation Focusing on Small Objects
Authors:Christian Wilms, Simone Frintrop
[14] Title: Graph Refinement based Tree Extraction using Mean-Field Networks and Graph Neural Networks
Authors:Raghavendra Selvan, Thomas Kipf, Max Welling, Jesper H Pedersen, Jens Petersen, Marleen de Bruijne
[15] Title: Computational Decomposition of Style for Controllable and Enhanced Style Transfer
Authors:Minchao Li, Shikui Tu, Lei Xu
[16] Title: Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detection
Authors:Paul F. Jaeger, Simon A. A. Kohl, Sebastian Bickelhaupt, Fabian Isensee, Tristan Anselm Kuder, Heinz-Peter Schlemmer, Klaus H. Maier-Hein
[17] Title: PersEmoN: A Deep Network for Joint Analysis of Apparent Personality, Emotion and Their Relationship
Authors:Le Zhang, Songyou Peng, Stefan Winkler
[18] Title: A Fingerprint Indexing Method Based on Minutia Descriptor and Clustering
Authors:Gwang-Il Ri, Chol-Gyun Ri, Su-Rim Ji
[19] Title: Synetgy: Algorithm-hardware Co-design for ConvNet Accelerators on Embedded FPGAs
Authors:Yifan Yang, Qijing Huang, Bichen Wu, Tianjun Zhang, Liang Ma, Giulio Gambardella, Michaela Blott, Luciano Lavagno, Kees Vissers, John Wawrzynek, Kurt Keutzer
[20] Title: A Deep Tree-Structured Fusion Model for Single Image Deraining
Authors:Xueyang Fu, Qi Qi, Yue Huang, Xinghao Ding, Feng Wu, John Paisley
[21] Title: Angular Triplet-Center Loss for Multi-view 3D Shape Retrieval
Authors:Zhaoqun Li, Cheng Xu, Biao Leng
[22] Title: Neural Networks with Activation Networks
Authors:Jinhyeok Jang, Jaehong Kim, Jaeyeon Lee, Seungjoon Yang
[23] Title: A Novel Integrated Framework for Learning both Text Detection and Recognition
Authors:Wanchen Sui, Qing Zhang, Jun Yang, Wei Chu
[24] Title: Scene Text Detection with Supervised Pyramid Context Network
Authors:Enze Xie, Yuhang Zang, Shuai Shao, Gang Yu, Cong Yao, Guangyao Li
[25] Title: M2E-Try On Net: Fashion from Model to Everyone
Authors:Zhonghua Wu, Guosheng Lin, Qingyi Tao, Jianfei Cai
[26] Title: Learning to Attend Relevant Regions in Videos from Eye Fixations
Authors:Thanh T. Nguyen, Dung Nguyen, Sung Ju Hwang
[27] Title: Measuring Depression Symptom Severity from Spoken Language and 3D Facial Expressions
Authors:Albert Haque, Michelle Guo, Adam S Miner, Li Fei-Fei
[28] Title: Graph-Adaptive Pruning for Efficient Inference of Convolutional Neural Networks
Authors:Mengdi Wang, Qing Zhang, Jun Yang, Xiaoyuan Cui, Wei Lin
[29] Title: Real-Time 6D Object Pose Estimation on CPU
Authors:Yoshinori Konishi, Kosuke Hattori, Manabu Hashimoto
[30] Title: Progressive Feature Alignment for Unsupervised Domain Adaptation
Authors:Chaoqi Chen, Weiping Xie, Tingyang Xu, Wenbing Huang, Yu Rong, Xinghao Ding, Yue Huang, Junzhou Huang
[31] Title: Unsupervised Single Image Deraining with Self-supervised Constraints
Authors:Xin Jin, Zhibo Chen, Jianxin Lin, Zhikai Chen, Wei Zhou
[32] Title: Priming Deep Neural Networks with Synthetic Faces for Enhanced Performance
Authors:Adam Kortylewski, Andreas Schneider, Thomas Gerig, Clemens Blumer, Bernhard Egger, Corius Reyneke, Andreas Morel-Forster, Thomas Vetter
[33] Title: Feature Selection Convolutional Neural Networks for Visual Tracking
Authors:Zhiyan Cui, Na Lu
[34] Title: Adaptive Re-ranking of Deep Feature for Person Re-identification
Authors:Yong Liu, Lin Shang, Andy Song
[35] Title: Adjustable Real-time Style Transfer
Authors:Mohammad Babaeizadeh, Golnaz Ghiasi
[36] Title: Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision
Authors:Wanxin Tian, Zixuan Wang, Haifeng Shen, Weihong Deng, Binghui Chen, Xiubao Zhang
[37] Title: Seeing in the dark with recurrent convolutional neural networks
Authors:Till S. Hartmann
[38] Title: Finding a Needle in the Haystack: Attention-Based Classification of High Resolution Microscopy Images
Authors:Naofumi Tomita, Behnaz Abdollahi, Jason Wei, Bing Ren, Arief Suriawinata, Saeed Hassanpour
[39] Title: A Proposal-Based Solution to Spatio-Temporal Action Detection in Untrimmed Videos
Authors:Joshua Gleason, Rajeev Ranjan, Steven Schwarcz, Carlos D. Castillo, Jun-Chen Cheng, Rama Chellappa
[40] Title: Are pre-trained CNNs good feature extractors for anomaly detection in surveillance videos?
Authors:Tiago S. Nazare, Rodrigo F. de Mello, Moacir A. Ponti
[41] Title: Adversarial Removal of Gender from Deep Image Representations
Authors:Tianlu Wang, Jieyu Zhao, Kai-Wei Chang, Mark Yatskar, Vicente Ordonez
[42] Title: MimicGAN: Corruption-Mimicking for Blind Image Recovery & Adversarial Defense
Authors:Rushil Anirudh, Jayaraman J. Thiagarajan, Bhavya Kailkhura, Timo Bremer
[43] Title: VQA with no questions-answers training
Authors:Ben-Zion Vatashsky, Shimon Ullman
[44] Title: Double Refinement Network for Efficient Indoor Monocular Depth Estimation
Authors:Nikita Durasov, Mikhail Romanov, Valeriya Bubnova, Anton Konushin
[45] Title: Artificial Color Constancy via GoogLeNet with Angular Loss Function
Authors:Oleksii Sidorov
[46] Title: Intermediate Level Adversarial Attack for Enhanced Transferability
Authors:Qian Huang, Zeqi Gu, Isay Katsman, Horace He, Pian Pawakapan, Zhiqiu Lin, Serge Belongie, Ser-Nam Lim
[47] Title: Boosting in Image Quality Assessment
Authors:Dogancan Temel, Ghassan AlRegib

Papers from arxiv.org

---

Interesting:

• ImageNet 預訓練新思考
  

• 將模特的衣服試裝到任何人身上_M2E-Try On Net (from:NTU&Nvidia)

• 對風格影象特徵的解構組合–FFT DCT PCA ICA—實現可控的風格遷移 （from sjtu）
  

• CPU上23fps的位姿估計方法，結合了multimodal PCOF, 平衡位姿搜尋樹和記憶體優化策略，直接通過RGB-D計算方向直方圖來計算特徵(from 歐姆龍)。
  

• 利用Angular Triplet-Center Loss損失函式改進三維檢索, (from 北航)
  

• 利用門限內容增強網路實現去霧去雨,並結合了邊緣的低階資訊實現平滑擴散卷積，平滑輸出。(from 中科大)
  

• 光照顏色不變性的CNN演算法,提出了角度損失函式 $angular_loss = 1−cos\epsilon$
  
  資料集：SFU Grayball,e ColorChecker Reprocessed , code

• 利用兩個精煉網路實現更精細的單目深度估計
  

• 基於深度樹結構融合模型去雨滴 (from 廈門大學)
  合成數據來自：JORDER [36], DDN [10] and DID [38]
  

• 單張影象去雨滴,包含了背景、雨滴引導
  
  合成下雨影象資料集:Rain800, Rain12, Rain100L and Rain100H
  參考論文：https://arxiv.org/pdf/1802.07412.pdf

核磁共振開源資料集fastMRI:http://fastmri.med.nyu.edu/