paper-with-me

Papers

Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition

2015-11-13 · CVPR 2016 6 · Zhiwei Deng, Arash Vahdat, Hexiang Hu, Greg Mori

Rich semantic relations are important in a variety of visual recognition problems. As a concrete example, group activity recognition involves the interactions and relative spatial relations of a set of people in a scene. State of the art recognition methods center on deep learning approaches for training highly effective, complex classifiers for interpreting images. However, bridging the relatively low-level concepts output by these methods to interpret higher-level compositional scenes remains a challenge. Graphical models are a standard tool for this task. In this paper, we propose a method to integrate graphical models and deep neural networks into a joint framework. Instead of using a traditional inference method, we use a sequential inference modeled by a recurrent neural network. Beyond this, the appropriate structure for inference can be learned by imposing gates on edges between nodes. Empirical results on group activity recognition demonstrate the potential of this model to handle highly structured learning tasks.

📄 PDF Abstract BibTeX arXiv:1511.04196

Code (0)

등록된 구현이 없습니다.

Tasks

Activity RecognitionGroup Activity Recognition

Similar Papers 제목 키워드 기반

Recurrent Inference Machines for Solving Inverse Problems

2017-06-13 · Patrick Putzky, Max Welling

Much of the recent research on solving iterative inference problems focuses on moving away from hand-chosen inference algorithms and towards learned inference. In the latter, the inference process is unrolled in time and…

DenoisingImage DenoisingImage RestorationSuper-Resolution

Deep Gate Recurrent Neural Network

2016-04-11 · Yuan Gao, Dorota Glowacka

This paper introduces two recurrent neural network structures called Simple Gated Unit (SGU) and Deep Simple Gated Unit (DSGU), which are general structures for learning long term dependencies. Compared to traditional Lo…

Effective Mean-Field Inference Method for Nonnegative Boltzmann Machines

2016-03-08 · Muneki Yasuda

Nonnegative Boltzmann machines (NNBMs) are recurrent probabilistic neural network models that can describe multi-modal nonnegative data. NNBMs form rectified Gaussian distributions that appear in biological neural networ…

Re-understanding Finite-State Representations of Recurrent Policy Networks

2020-06-06 · Mohamad H. Danesh, Anurag Koul, Alan Fern, Saeed Khorram

We introduce an approach for understanding control policies represented as recurrent neural networks. Recent work has approached this problem by transforming such recurrent policy networks into finite-state machines (FSM…

Atari Games

Feedforward Initialization for Fast Inference of Deep Generative Networks is biologically plausible

2016-06-06 · Yoshua Bengio, Benjamin Scellier, Olexa Bilaniuk, Joao Sacramento 외

We consider deep multi-layered generative models such as Boltzmann machines or Hopfield nets in which computation (which implements inference) is both recurrent and stochastic, but where the recurrence is not to model se…