628 citations · 2.1k across the 30 of their papers we have counts for
38 papers
Self-supervised Hypergraphs for Learning Multiple World Interpretations
Alina Marcu, Mihai Pirvu, Dragos Costea +5
We present a method for learning multiple scene representations given a small labeled set, by exploiting the relationships between such representations in the form of a multi-task…
HSPACE: Synthetic Parametric Humans Animated in Complex Environments
Eduard Gabriel Bazavan, Andrei Zanfir, Mihai Zanfir +3
Advances in the state of the art for 3d human sensing are currently limited by the lack of visual datasets with 3d ground truth, including multiple people, in motion, operating in…
Discrete Representations Strengthen Vision Transformer Robustness
Chengzhi Mao, Lu Jiang, Mostafa Dehghani +3
Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition. While recent studies suggest that ViTs are more robust than their convolutional cou…
THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers
Mihai Zanfir, Andrei Zanfir, Eduard Gabriel Bazavan +3
We present THUNDR, a transformer-based deep neural network methodology to reconstruct the 3d pose and shape of people, given monocular RGB images. Key to our methodology is an inte…
Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus
Marius Leordeanu, Mihai Pirvu, Dragos Costea +3
We address the challenging problem of semi-supervised learning in the context of multiple visual interpretations of the world by finding consensus in a graph of neural networks. Ea…
The End-of-End-to-End: A Video Understanding Pentathlon Challenge (2020)
Samuel Albanie, Yang Liu, Arsha Nagrani +18
We present a new video understanding pentathlon challenge, an open competition held in conjunction with the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020.…
Neural Descent for Visual 3D Human Pose and Shape
Andrei Zanfir, Eduard Gabriel Bazavan, Mihai Zanfir +3
We present deep neural network methodology to reconstruct the 3d pose and shape of people, given an input RGB image. We rely on a recently introduced, expressivefull body statistic…
Learning Video Representations from Textual Web Supervision
Jonathan C. Stroud, Zhichao Lu, Chen Sun +4
Videos on the Internet are paired with pieces of text, such as titles and descriptions. This text typically describes the most important content in the video, such as the objects i…
Speech2Action: Cross-modal Supervision for Action Recognition
Arsha Nagrani, Chen Sun, David Ross +3
Is it possible to guess human action from dialogue alone? In this work we investigate the link between spoken words and actions in movies. We note that movie screenplays describe a…
Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows
Andrei Zanfir, Eduard Gabriel Bazavan, Hongyi Xu +3
Monocular 3D human pose and shape estimation is challenging due to the many degrees of freedom of the human body and thedifficulty to acquire training data for large-scale supervis…
Selfie Drone Stick: A Natural Interface for Quadcopter Photography
Saif Alabachi, Gita Sukthankar, Rahul Sukthankar
A physical selfie stick extends the user's reach, enabling the acquisition of personal photos that include more of the background scene. Similarly, a quadcopter can capture photos…
An Efficient 3D CNN for Action/Object Segmentation in Video
Rui Hou, Chen Chen, Rahul Sukthankar +1
Convolutional Neural Network (CNN) based image segmentation has made great progress in recent years. However, video object segmentation remains a challenging task due to its high c…
Relational Action Forecasting
Chen Sun, Abhinav Shrivastava, Carl Vondrick +3
This paper focuses on multi-person action forecasting in videos. More precisely, given a history of H previous frames, the goal is to detect actors and to predict their future acti…
Customizing Object Detectors for Indoor Robots
Saif Alabachi, Gita Sukthankar, Rahul Sukthankar
Object detection models based on convolutional neural networks (CNNs) demonstrate impressive performance when trained on large-scale labeled datasets. While a generic object detect…
D3D: Distilled 3D Networks for Video Action Recognition
Jonathan C. Stroud, David A. Ross, Chen Sun +2
State-of-the-art methods for video action recognition commonly use an ensemble of two networks: the spatial stream, which takes RGB frames as input, and the temporal stream, which…
Modulated Policy Hierarchies
Alexander Pashevich, Danijar Hafner, James Davidson +2
Solving tasks with sparse rewards is a main challenge in reinforcement learning. While hierarchical controllers are an intuitive approach to this problem, current methods often req…
Actor-Centric Relation Network
Chen Sun, Abhinav Shrivastava, Carl Vondrick +3
Current state-of-the-art approaches for spatio-temporal action localization rely on detections at the frame level and model temporal context with 3D ConvNets. Here, we go one step…
Rethinking the Faster R-CNN Architecture for Temporal Action Localization
Yu-Wei Chao, Sudheendra Vijayanarasimhan, Bryan Seybold +3
We propose TAL-Net, an improved approach to temporal action localization in video that is inspired by the Faster R-CNN object detection framework. TAL-Net addresses three key short…
Object category learning and retrieval with weak supervision
Steven Hickson, Anelia Angelova, Irfan Essa +1
We consider the problem of retrieving objects from image data and learning to classify them into meaningful semantic categories with minimal supervision. To that end, we propose a…
WebVision Challenge: Visual Learning and Understanding With Web Data
Wen Li, Limin Wang, Wei Li +5
We present the 2017 WebVision Challenge, a public image recognition challenge designed for deep learning based on web images without instance-level human annotation. Following the…
Motion Prediction Under Multimodality with Conditional Stochastic Networks
Katerina Fragkiadaki, Jonathan Huang, Alex Alemi +3
Given a visual history, multiple future outcomes for a video scene are equally probable, in other words, the distribution of future outcomes has multiple modes. Multimodality is no…
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
Chunhui Gu, Chen Sun, David A. Ross +9
This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions (AVA). The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video…
SfM-Net: Learning of Structure and Motion from Video
Sudheendra Vijayanarasimhan, Susanna Ricco, Cordelia Schmid +2
We propose SfM-Net, a geometry-aware neural network for motion estimation in videos that decomposes frame-to-frame pixel motion in terms of scene and object depth, camera motion an…
Robust Adversarial Reinforcement Learning
Lerrel Pinto, James Davidson, Rahul Sukthankar +1
Deep neural networks coupled with fast simulation and improved computation have led to recent successes in the field of reinforcement learning (RL). However, most current RL-based…