贝叶斯在计算机视觉中的应用,贝叶斯方法及其在场景理解中的应用

NIPS 2013:

Approximate Bayesian Image Interpretation using Generative

Probabilistic Graphics Programs

ICCV 2013:

Bayesian 3D tracking from monocular video

Understanding High-Level Semantics by Modeling Traffic

Patterns

Latent Data Association: Bayesian Model Selection for

Multi-target Tracking

CVPR 2013:

3D Pictorial Structures for Multiple View Articulated Pose

Estimation

3D-Based Reasoning with Blocks, Support, and Stability

A Joint Model for 2D and 3D Pose Estimation from a Single

Image

A Statistical Model for Recreational Trails in Aerial

Images

Action Recognition by Hierarchical Sequence

Summarization

Bayesian Grammar Learning for Inverse Procedural

Modeling

Hallucinated Humans as the Hidden Context for Labeling 3D

Scenes

Image Understanding from Experts’ Eyes by Modeling Perceptual

Skill of Diagnostic Reasoning Processes

Lost! Leveraging the Crowd for Probabilistic Visual

Self-Localization

Manhattan Junction Catalogue for Spatial Reasoning of Indoor

Scene

Motion Estimation for Self-Driving Cars With a Generalized

Camera

Physically Plausible 3D Scene Tracking-The Single Actor

Hypothesis

Scene Parsing by Integrating Function, Geometry and Appearance

Models

Tracking People and Their Objects

Understanding Bayesian rooms using composite 3D object

models

TPAMI 2013:

Monocular Visual Scene Understanding - Understanding

Multi-Object Traffic Scenes

CVPR 2014:

A Probabilistic Framework for Multitarget Tracking with Mutual

Occlusions

Are Cars Just 3D Boxes – Jointly Estimating the 3D Shape of

Multiple Objects

Ground Plane Estimation using a Hidden Markov Model

TPAMI 2014:

3D Traffic Scene Understanding from Movable Platforms

ECCV 2014:

Tracking Interacting Objects

Optimally Using Integer Programming

Probabilistic Temporal Head Pose

Estimation Using a Hierarchical Graphical Model

Visual Tracking by Sampling

Tree-Structured Graphical Models

Online Graph-Based Tracking

Context-based Pedestrian Path

Prediction

Bayesian Nonparametric Intrinsic

Image Decomposition

最近在用Bayes方法做场景理解，下面附上这门课的课程报告：