2.4k citations · 8.4k across the 129 of their papers we have counts for
12 papers · 1 filter
Feedback Networks
Amir R. Zamir, Te-Lin Wu, Lin Sun +3
Currently, the most successful learning models in computer vision are based on learning successive representations followed by a decision layer. This is usually actualized through…
Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition
Timur Bagautdinov, Alexandre Alahi, François Fleuret +2
We present a unified framework for understanding human social behaviors in raw image sequences. Our model jointly detects multiple individuals, infers their social actions, and est…
Human Centred Object Co-Segmentation
Chenxia Wu, Jiemi Zhang, Ashutosh Saxena +1
Co-segmentation is the automatic extraction of the common semantic regions given a set of images. Different from previous approaches mainly based on object visuals, in this paper,…
Universal Correspondence Network
Christopher B. Choy, JunYoung Gwak, Silvio Savarese +1
We present a deep learning framework for accurate visual correspondences and demonstrate its effectiveness for both geometric and semantic matching, spanning across rigid motions t…
Unsupervised Semantic Action Discovery from Video Collections
Ozan Sener, Amir Roshan Zamir, Chenxia Wu +2
Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objectiv…
3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
Christopher B. Choy, Danfei Xu, JunYoung Gwak +2
Inspired by the recent success of methods that employ shape priors to achieve robust 3D reconstructions, we propose a novel recurrent neural network architecture that we call the 3…
Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection
Yu Xiang, Wongun Choi, Yuanqing Lin +1
In CNN-based object detection methods, region proposal becomes a bottleneck when objects exhibit significant scale variation, occlusion or truncation. In addition, these methods ma…
Learning to Track at 100 FPS with Deep Regression Networks
David Held, Sebastian Thrun, Silvio Savarese
Machine learning techniques are often used in computer vision due to their ability to leverage large amounts of training data to improve performance. Unfortunately, most generic ob…
Unsupervised Transductive Domain Adaptation
Ozan Sener, Hyun Oh Song, Ashutosh Saxena +1
Supervised learning with large scale labeled datasets and deep layered models has made a paradigm shift in diverse areas in learning and recognition. However, this approach still s…
Watch-n-Patch: Unsupervised Learning of Actions and Relations
Chenxia Wu, Jiemi Zhang, Ozan Sener +3
There is a large variation in the activities that humans perform in their everyday lives. We consider modeling these composite human activities which comprises multiple basic level…
Knowledge Transfer for Scene-specific Motion Prediction
Lamberto Ballan, Francesco Castaldo, Alexandre Alahi +2
When given a single frame of the video, humans can not only interpret the content of the scene, but also they are able to forecast the near future. This ability is mostly driven by…
Forecasting Social Navigation in Crowded Complex Scenes
Alexandre Robicquet, Alexandre Alahi, Amir Sadeghian +4
When humans navigate a crowed space such as a university campus or the sidewalks of a busy street, they follow common sense rules based on social etiquette. In this paper, we argue…