• Publications
  • Influence
Deformable Convolutional Networks
TLDR
This work introduces two new modules to enhance the transformation modeling capability of CNNs, namely, deformable convolution and deformable RoI pooling, based on the idea of augmenting the spatial sampling locations in the modules with additional offsets and learning the offsets from the target tasks, without additional supervision. Expand
Face Alignment by Explicit Shape Regression
TLDR
A very efficient, highly accurate, “Explicit Shape Regression” approach for face alignment that significantly outperforms the state-of-the-art in terms of both accuracy and efficiency. Expand
Saliency Optimization from Robust Background Detection
TLDR
This work proposes a robust background measure, called boundary connectivity, which characterizes the spatial layout of image regions with respect to image boundaries and is much more robust and presents unique benefits that are absent in previous saliency measures. Expand
Simple Baselines for Human Pose Estimation and Tracking
TLDR
This work provides simple and effective baseline methods for pose estimation that are helpful for inspiring and evaluating new ideas for the field and achieved on challenging benchmarks. Expand
Face Alignment at 3000 FPS via Regressing Local Binary Features
TLDR
This paper presents a highly efficient, very accurate regression approach for face alignment that achieves the state-of-the-art results when tested on the current most challenging benchmarks. Expand
Geodesic Saliency Using Background Priors
TLDR
Evaluation on two databases validates that geodesic saliency achieves superior results and outperforms previous approaches by a large margin, in both accuracy and speed (2 ms per image), illustrating that appropriate prior exploitation is helpful for the ill-posed saliency detection problem. Expand
Cascaded hand pose regression
TLDR
3D pose-indexed features that generalize the previous 2D parameterized features and achieve better invariance to 3D transformations and a principled hierarchical regression that is adapted to the articulated object structure are introduced. Expand
Deep Feature Flow for Video Recognition
TLDR
Deep feature flow is presented, a fast and accurate framework for video recognition that runs the expensive convolutional sub-network only on sparse key frames and propagates their deep feature maps to other frames via a flow field and achieves significant speedup as flow computation is relatively fast. Expand
Single Path One-Shot Neural Architecture Search with Uniform Sampling
TLDR
A Single Path One-Shot model is proposed to construct a simplified supernet, where all architectures are single paths so that weight co-adaption problem is alleviated. Expand
Flow-Guided Feature Aggregation for Video Object Detection
TLDR
This work presents flow-guided feature aggregation, an accurate and end-to-end learning framework for video object detection that improves the per-frame features by aggregation of nearby features along the motion paths, and thus improves the video recognition accuracy. Expand
...
1
2
3
4
5
...