Discover and read the best of Twitter Threads about #CVPR2020
Most recents (7)
Last day of the main conference at #CVPR2020, and here are my non-scientifically chosen top five papers @CVPR for the last day. Visit them in the next 10(?) hours! (1/6)
1. High-Dimensional Convolutional Networks for Geometric Pattern Recognition
Authors: Christopher Choy, Junha Lee, René Ranftl, Jaesik Park, Vladlen Koltun
Correspondences in 2D/3D forms geometric structures in higher dim, let's segment those with ND convnets!
#CVPR2020
Authors: Christopher Choy, Junha Lee, René Ranftl, Jaesik Park, Vladlen Koltun
Correspondences in 2D/3D forms geometric structures in higher dim, let's segment those with ND convnets!
#CVPR2020
2. PointGMM: A Neural GMM Network for Point Clouds
Authors: Amir Hertz, Rana Hanocka, Raja Giryes, Daniel Cohen-Or
Constructing a hierarchical GMM by attentional split, and using the encoding for shape interpolation and generation.
#CVPR2020
Authors: Amir Hertz, Rana Hanocka, Raja Giryes, Daniel Cohen-Or
Constructing a hierarchical GMM by attentional split, and using the encoding for shape interpolation and generation.
#CVPR2020
Check out our paper today at #CVPR2020 🎉🎉🎉
cvpr20.com/event/context-…
Context R-CNN: Long Term Temporal Context for Per Camera Object Detection
Come ask questions at the live Q&As!
First session: June 18, 3-5 PM PDT
Second session: June 19, 3-5 AM PDT
Our @CVPR spotlight vid:
cvpr20.com/event/context-…
Context R-CNN: Long Term Temporal Context for Per Camera Object Detection
Come ask questions at the live Q&As!
First session: June 18, 3-5 PM PDT
Second session: June 19, 3-5 AM PDT
Our @CVPR spotlight vid:
In static cameras (like #cameratraps), relevant context for identifying objects can be spread out across long time horizons. For example, these two images come from the same camera and are uncannily similar, but they were taken a month apart! Turns out animals are pretty habitual
We propose a simple and flexible method for aggregating context from up to a month of data, using attention! We first build an (unsupervised) “memory bank” for each location. We add context for each object by finding features in the memory bank that help us identify that object.
Introducing RepNet, a model that counts repetitions in videos of *any* action
w @yusufaytar, @JonathanTompson, @psermanet and Andrew Zisserman
Paper: openaccess.thecvf.com/content_CVPR_2…
Project: sites.google.com/repnet
Video:
#CVPR2020 #computervision #deeplearning
w @yusufaytar, @JonathanTompson, @psermanet and Andrew Zisserman
Paper: openaccess.thecvf.com/content_CVPR_2…
Project: sites.google.com/repnet
Video:
#CVPR2020 #computervision #deeplearning
Here's an overview of RepNet's architecture.
An integral part of RepNet is the temporal self-similarity matrix (TSM) which not only makes it easy to count repetitions but also drives generalization to actions and domains not seen during training.
3 days participate in #CVPR2020 conference. excited about a lot of interesting subjects covered in computer vision: Adversarial Learning, Effective training and inference, representation learning...
Will do a write-up later.
#CVPR20 #computervision
Will do a write-up later.
#CVPR20 #computervision
Some preferred papers so far 👇
1. Dynamic Graph Message Passing Networks arxiv.org/pdf/1908.06955…
It addresses the modelling long-range dependencies problem by using feature map as a feature vector nodes and dynamically sample the neighborhood of a node from the feature graph.
1. Dynamic Graph Message Passing Networks arxiv.org/pdf/1908.06955…
It addresses the modelling long-range dependencies problem by using feature map as a feature vector nodes and dynamically sample the neighborhood of a node from the feature graph.
2. Semantic Pyramid for Image Generation arxiv.org/pdf/2003.06221…
A generative image model that can leverage the feature space from different semantic levels learned by a pretrained classification network. many generative applications to play with
A generative image model that can leverage the feature space from different semantic levels learned by a pretrained classification network. many generative applications to play with
For the night session attendees of #CVPR2020, here is my completely non-scientifically chosen top five papers @cvpr for the second day. Visit them in the next 8 hours! (1/6)
1. DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes
Authors: Jonas Schult, Francis Engelmann, Theodora Kontogianni, Bastian Leibe
Conv->(euclidean+geodesic) convs
Pooling->mesh simplification
6% mIoU increase and a nice paper!
#CVPR2020
Authors: Jonas Schult, Francis Engelmann, Theodora Kontogianni, Bastian Leibe
Conv->(euclidean+geodesic) convs
Pooling->mesh simplification
6% mIoU increase and a nice paper!
#CVPR2020
2. Unsupervised Learning of Intrinsic Structural Representation Points
Authors: Nenglun Chen, Lingjie Liu, Zhiming Cui, Runnan Chen, Duygu Ceylan, Changhe Tu, Wenping Wang
Like categorical SIFT points in point clouds, for matching, recon, interpolation and more!
#CVPR2020
Authors: Nenglun Chen, Lingjie Liu, Zhiming Cui, Runnan Chen, Duygu Ceylan, Changhe Tu, Wenping Wang
Like categorical SIFT points in point clouds, for matching, recon, interpolation and more!
#CVPR2020
For the night session attendees of #CVPR2020, here is my completely non-scientifically chosen top five papers @cvpr first day. Visit them in the next 8 hours! (1/6)
1. Perspective Plane Program Induction From a Single Image
Authors: Yikai Li, Jiayuan Mao, Xiuming Zhang, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu @MIT_CSAIL
Domain agnostic image-based proceduralization with single terminal and grid-based rules.
#CVPR2020 Day 1
Authors: Yikai Li, Jiayuan Mao, Xiuming Zhang, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu @MIT_CSAIL
Domain agnostic image-based proceduralization with single terminal and grid-based rules.
#CVPR2020 Day 1
Introducing new #cvpr2020 work with S. Gidaris and team on a new self-supervised task: Learning Representations by Predicting Bags of Visual Words arxiv.org/abs/2002.12247 1/
@quobbe Inspired by NLP approaches, our method builds upon features from a self-supervised CNN (e.g. RotNet), which are used for computing a codebook of visual words and image-level Bag-of-Words (BoW) representations 2/
@quobbe Then, as a self-supervised task, we train another CNN to predict the BoW representation of an image given as input a perturbed version of that image. This forces the CNN to learn perturbation and context invariant features useful for downstream image-understanding tasks 3/
