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 Image
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 ImageImage
Read 8 tweets
Check out our paper today at #CVPR2020 🎉🎉🎉…

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.
Read 10 tweets
Introducing RepNet, a model that counts repetitions in videos of *any* action

w @yusufaytar, @JonathanTompson, @psermanet and Andrew Zisserman


#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.
Read 9 tweets
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
Some preferred papers so far 👇
1. Dynamic Graph Message Passing Networks…
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…
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
Read 10 tweets
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!

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!

Read 7 tweets
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
2. Learning Formation of Physically-Based Face Attributes

Authors: Ruilong Li, Karl Bladin, Yajie Zhao, Chinmay Chinara, Owen Ingraham, Pengda Xiang, Xinglei Ren, et al. @HaoLi81

Photorealistic humans are here! Fitting code for any 3D mesh is coming soon too.

#CVPR2020 Day 1
Read 7 tweets
Introducing new #cvpr2020 work with S. Gidaris and team on a new self-supervised task: Learning Representations by Predicting Bags of Visual Words 1/ Image
@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/ ImageImage
@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/
Read 5 tweets

Related hashtags

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!