362 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Honda (United States)US9 papers
- University of California, BerkeleyUS4 papers
- Purdue University West LafayetteUS3 papers
- University of Maryland, College ParkUS3 papers
- Atlanta Technical CollegeUS1 paper
- Boston UniversityUS1 paper
- Carnegie Mellon UniversityUS1 paper
- Georgia Institute of TechnologyUS1 paper
- Honda (Japan)JP1 paper
- IBM Research - Thomas J. Watson Research CenterUS1 paper
- IBM (United States)US1 paper
- Indiana UniversityUS1 paper
8 papers · 1 filter
Recognition and 3D Localization of Pedestrian Actions from Monocular Video
Jun Hayakawa, Behzad Dariush
Understanding and predicting pedestrian behavior is an important and challenging area of research for realizing safe and effective navigation strategies in automated and advanced d…
Who Make Drivers Stop? Towards Driver-centric Risk Assessment: Risk Object Identification via Causal Inference
Chengxi Li, Stanley H. Chan, Yi-Ting Chen
A significant amount of people die in road accidents due to driver errors. To reduce fatalities, developing intelligent driving systems assisting drivers to identify potential risk…
Learning 3D-aware Egocentric Spatial-Temporal Interaction via Graph Convolutional Networks
Chengxi Li, Yue Meng, Stanley H. Chan +1
To enable intelligent automated driving systems, a promising strategy is to understand how human drives and interacts with road users in complicated driving situations. In this pap…
Context Aware Road-user Importance Estimation (iCARE)
Alireza Rahimpour, Sujitha Martin, Ashish Tawari +1
Road-users are a critical part of decision-making for both self-driving cars and driver assistance systems. Some road-users, however, are more important for decision-making than ot…
Temporal Recurrent Networks for Online Action Detection
Mingze Xu, Mingfei Gao, Yi-Ting Chen +2
Most work on temporal action detection is formulated as an offline problem, in which the start and end times of actions are determined after the entire video is fully observed. How…
Two Stream Self-Supervised Learning for Action Recognition
Ahmed Taha, Moustafa Meshry, Xitong Yang +2
We present a self-supervised approach using spatio-temporal signals between video frames for action recognition. A two-stream architecture is leveraged to tangle spatial and tempor…
Local Descriptors Optimized for Average Precision
Kun He, Yan Lu, Stan Sclaroff
Extraction of local feature descriptors is a vital stage in the solution pipelines for numerous computer vision tasks. Learning-based approaches improve performance in certain task…
Learning to Cluster for Proposal-Free Instance Segmentation
Yen-Chang Hsu, Zheng Xu, Zsolt Kira +1
This work proposed a novel learning objective to train a deep neural network to perform end-to-end image pixel clustering. We applied the approach to instance segmentation, which i…