Using goal-driven deep learning models to understand sensory cortex
Fueled by innovation in the computer vision and artificial intelligence communities, recent
developments in computational neuroscience have used goal-driven hierarchical …
developments in computational neuroscience have used goal-driven hierarchical …
Detect what you can: Detecting and representing objects using holistic models and body parts
Detecting objects becomes difficult when we need to deal with large shape deformation,
occlusion and low resolution. We propose a novel approach to i) handle large deformations …
occlusion and low resolution. We propose a novel approach to i) handle large deformations …
Object as hotspots: An anchor-free 3d object detection approach via firing of hotspots
Accurate 3D object detection in LiDAR based point clouds suffers from the challenges of
data sparsity and irregularities. Existing methods strive to organize the points regularly, eg …
data sparsity and irregularities. Existing methods strive to organize the points regularly, eg …
A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs
INTRODUCTION Compositionality, generalization, and learning from a few examples are
among the hallmarks of human intelligence. CAPTCHAs (Completely Automated Public …
among the hallmarks of human intelligence. CAPTCHAs (Completely Automated Public …
Robust object detection under occlusion with context-aware compositionalnets
Detecting partially occluded objects is a difficult task. Our experimental results show that
deep learning approaches, such as Faster R-CNN, are not robust at object detection under …
deep learning approaches, such as Faster R-CNN, are not robust at object detection under …
A probabilistic model for component-based shape synthesis
We present an approach to synthesizing shapes from complex domains, by identifying new
plausible combinations of components from existing shapes. Our primary contribution is a …
plausible combinations of components from existing shapes. Our primary contribution is a …
Automatic generation of software behavioral models
Dynamic analysis of software systems produces behavioral models that are useful for
analysis, verification and testing. The main techniques for extracting models of functional …
analysis, verification and testing. The main techniques for extracting models of functional …
Compositional convolutional neural networks: A robust and interpretable model for object recognition under occlusion
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 …
while also being explainable. In this work, we show that black-box deep convolutional …
Compositional convolutional neural networks: A deep architecture with innate robustness to partial occlusion
Recent work has shown that deep convolutional neural networks (DCNNs) do not
generalize well under partial occlusion. Inspired by the success of compositional models at …
generalize well under partial occlusion. Inspired by the success of compositional models at …
Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos
Analyzing videos of human activities involves not only recognizing actions (typically based
on their appearances), but also determining the story/plot of the video. The storyline of a …
on their appearances), but also determining the story/plot of the video. The storyline of a …