This work proposes to combine neural networks with the compositional hierarchy of human
bodies for efficient and complete human parsing. We formulate the approach as a neural …

Action recognition and pose estimation from video are closely related tasks for
understanding human motion, most methods, however, learn separate models and combine …

Modeling the human structure is central for human parsing that extracts pixel-wise semantic
information from images. We start with analyzing three types of inference processes over the …

Computer vision systems in real-world applications need to be robust to partial occlusion
while also being explainable. In this work, we show that black-box deep convolutional …

This paper presents a hierarchical composition approach for multi-view object tracking. The
key idea is to adaptively exploit multiple cues in both 2D and 3D, eg, ground occupancy …

Using techniques derived from the syntactic methods for visual pattern recognition is not
new and was much explored in the area called syntactical or structural pattern recognition …

We perform fast vehicle detection from traffic surveillance cameras. A novel deep learning
framework, namely Evolving Boxes, is developed that proposes and refines the object boxes …

We present an object detection system based on the Fisher vector (FV) image
representation computed over SIFT and color descriptors. For computational and storage …

This paper aims to illustrate the concept-emerging phenomenon in a trained DNN.
Specifically, we find that the inference score of a DNN can be disentangled into the effects of …

Sampling, generation, and evaluation of scenarios are essential steps for intelligent testing
of autonomous vehicles. Since uncertainty in driving behavior always leads to different …