Search Results for author:
Found 12 papers, 2 papers with code
Multiview Transformers for Video Recognition
Video understanding requires reasoning at multiple spatiotemporal resolutions -- from short fine-grained motions to events taking place over longer durations.
Ranked #1 on
Action Classification
on Kinetics-400
(using extra training data)
Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts
To address this issue, we introduce a new method for pre-training video action recognition models using queried web videos.
Exploring Sub-Pseudo Labels for Learning from Weakly-Labeled Web Videos
To address this issue, we introduce a new method for pre-training video action recognition models using queried web videos.
Spatial-Temporal Alignment Network for Action Recognition and Detection
The experimental results show that the STAN model can consistently improve the state of the arts in both action detection and action recognition tasks.
PERF-Net: Pose Empowered RGB-Flow Net
In recent years, many works in the video action recognition literature have shown that two stream models (combining spatial and temporal input streams) are necessary for achieving state of the art performance.
Ranked #3 on
Action Recognition
on UCF101
AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification
The discovered attention cells can be seamlessly inserted into existing backbone networks, e. g., I3D or S3D, and improve video classification accuracy by more than 2% on both Kinetics-600 and MiT datasets.
An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints
In this paper, we study how to design a genetic programming approach for optimizing the structure of a CNN for a given task under limited computational resources yet without imposing strong restrictions on the search space.
Efficient Video Object Segmentation via Network Modulation
Video object segmentation targets at segmenting a specific object throughout a video sequence, given only an annotated first frame.
Global Supervised Descent Method
It is generally accepted that second order descent methods are the most robust, fast, and reliable approaches for nonlinear optimization of a general smooth function.
Supervised Descent Method for Solving Nonlinear Least Squares Problems in Computer Vision
Using generic descent maps, we derive a practical algorithm - Supervised Descent Method (SDM) - for minimizing Nonlinear Least Squares (NLS) problems.
Supervised Descent Method and Its Applications to Face Alignment
It is generally accepted that 2 nd order descent methods are the most robust, fast and reliable approaches for nonlinear optimization of a general smooth function.
Ranked #21 on
Face Alignment
on WFLW
Bayesian Optimal Active Search and Surveying
In the second, active surveying, our goal is to actively query points to ultimately predict the proportion of a given class.
