03 2020 档案
摘要：Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation 2020-03-30 19:02:01 Paper: https://arxiv.org/abs/2003.0
阅读全文
摘要：How NAS was improved. From days to hours in search time 2020-03-29 21:18:08 Source: https://medium.com/peltarion/how-nas-was-improved-from-days-to-hou
阅读全文
摘要：Recent Advances in Vision and Language PreTrained Models (VL-PTMs) Maintained by WANG Yue (yuewang@cse.cuhk.edu.hk). Last update on 2020/03/26. Source
阅读全文
该文被密码保护。
该文被密码保护。
摘要：Know Your Surroundings: Exploiting Scene Information for Object Tracking 2020-03-25 17:52:24 Paper: https://arxiv.org/abs/2003.11014 Code: 尚无 1. Backg
阅读全文
摘要：Video Object Grounding using Semantic Roles in Language Description 2020-03-25 17:44:59 Paper：https://arxiv.org/pdf/2003.10606.pdf Code: https://githu
阅读全文
摘要：MAST: A Memory-Augmented Self-Supervised Tracker 2020-03-24 20:12:56 Paper: https://arxiv.org/pdf/2002.07793 Code: https://github.com/zlai0/MAST 1. Ba
阅读全文
该文被密码保护。
摘要：Attention is All you need 2020-03-22 00:29:11 Paper: https://papers.nips.cc/paper/7181-attention-is-all-you-need.pdf Doc: https://huggingface.co/trans
阅读全文
该文被密码保护。
摘要：Dynamic Zoom-in Network for Fast Object Detection in Large Images 2020-03-17 21:45:24 Paper: CVPR-2018 1. Background and Motivation: 如图 1 所示， 本文提出一种 c
阅读全文
该文被密码保护。
摘要：A Survey of Long-Term Context in Transformers 2020-03-17 10:08:32 Source: https://www.pragmatic.ml/a-survey-of-methods-for-incorporating-long-term-con
阅读全文
该文被密码保护。
摘要：ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks 2020-03-12 23:10:53 Paper: NeurIPS 2019 Code: https:/
阅读全文
摘要：SPARK: Spatial-aware Online Incremental Attack Against Visual Tracking 2020-03-09 23:47:26 Paper: https://arxiv.org/pdf/1910.08681.pdf 1. Background a
阅读全文
摘要：Generating Adversarial Examples with Adversarial Networks 2020-03-08 22:40:38 Paper: IJCAI-2018 Code: https://github.com/mathcbc/advGAN_pytorch 1. Bac
阅读全文
摘要：Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video 2020-03-08 14:29:35 Paper: https://arxiv.org/pdf/1906.02549.pdf Code: https://
阅读全文
摘要：Approaching literature review for academic purposes: The Literature Review Checklist Debora F.B. LeiteI II III http://orcid.org/0000-0001-8839-3934 Ma
阅读全文
该文被密码保护。
摘要：Visual Semantic Reasoning for Image-Text Matching 2020-03-06 15:17:02 Paper: https://arxiv.org/pdf/1909.02701.pdf Code: https://github.com/KunpengLi19
阅读全文
摘要：Stacked Cross Attention for Image-Text Matching 2020-03-06 15:13:08 Paper: https://arxiv.org/pdf/1803.08024.pdf Code: https://github.com/kuanghuei/SCA
阅读全文
摘要：Non-local Neural Networks 2020-03-05 20:24:39 Paper: CVPR_2018 Code: https://github.com/facebookresearch/video-nonlocal-net (Caffe2 version) https://g
阅读全文
摘要：BERT-related Papers 2020-03-03 16:36:12 This is a list of BERT-related papers. Any feedback is welcome. Source: https://github.com/tomohideshibata/BER
阅读全文
摘要：BERT在多模态领域中的应用 Source: Link BERT (Bidrectional Encoder Representations from Transformers) 自提出后，凭借着 Transformer 强大的特征学习能力以及通过掩码语言模型实现的双向编码，其大幅地提高了各项 NL
阅读全文
该文被密码保护。
该文被密码保护。
摘要：Learning When and Where to Zoom with Deep Reinforcement Learning 2020-03-03 14:47:08 Paper: https://arxiv.org/pdf/2003.00425.pdf Related work: "Effici
阅读全文
该文被密码保护。
摘要：Illustrating the Reformer 2020-03-02 13:39:12 Source: https://towardsdatascience.com/illustrating-the-reformer-393575ac6ba0 See also: Translation in �
阅读全文
