Causal Reasoning in CV计算机视觉中因果推理的应用,可以从两个方面来归纳数据、任务和方法:常识因果和事件因果。常识因果的研究关键词是relation,通常用graph来建模,也会利用到知识等先验作为指导。事件因果的研究关键词是independent,通常要求算法独立出研究对象,保留其对结果的影响,去除其他因素(包括confounder和meditator)。
Chi Zhang, Baoxiong Jia, Mark Edmonds, Song-Chun Zhu, Yixin Zhu
We present a new dataset for Abstract Causal REasoning, aiming to measure and improve causal induction in visual reasoning systems
Cited by0BibtexViews22
0
0
Tayfun Ates, Muhammed Samil Atesoglu, Cagatay Yigit, Ilker Kesen, Mert Kobas,Erkut Erdem,Aykut Erdem, Tilbe Goksun, Deniz Yuret
We present CRAFT, a new benchmark to challenge intuitive physics capabilities of the current machine learning algorithms
Cited by0BibtexViews7
0
0
Choi Chiho, Patil Abhishek,Malla Srikanth
We presented a Deep RObust Goal-Oriented trajectory prediction Network, DROGON, which aims to understand a causal relationship between intention and behavior of human drivers
Cited by0BibtexViews10
0
0
Vasili Ramanishka,Yi-Ting Chen, Teruhisa Misu,Kate Saenko
CVPR, (2018): 7699-7707
We introduce the Honda Research Institute Driving Dataset, which aims to stimulate the community to propose novel algorithms to capture the driver behavior
Cited by94BibtexViews77DOI
0
0
arXiv: Learning, (2018)
By optimizing an agent to perform a task that depended on causal structure, the agent learned implicit strategies to use the available data for causal reasoning, including drawing inferences from passive observation, actively intervening, and making counterfactual predictions
Cited by0BibtexViews129
0
0
LREC, (2018)
We introduce the task of visual commonsense causal reasoning with Visual Choice of Plausible Alternatives evaluation dataset
Cited by0BibtexViews15
0
0
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp.48-56, (2017)
We introduced a probability model for the sequential Causal And-Or Graph, enabling joint inference of hidden fluents and actions from video
Cited by5BibtexViews9DOI
0
0
Computing Handbook, 3rd ed. (1), pp.44: 1-24, (2014)
The disturbances U1;:::; Un are mutually independent, that is, P = Y P. These two conditions, called Markovian, are the basis of the independencies embodied in Bayesian networks and they enable us to compute causal e ects directly from the cfoi,nodrittihoenadlisptrriobbuatbioilni...
Cited by112BibtexViews127DOI
0
0
Computer Vision and Image Understanding, no. 2 (2005): 259-290
Knowledge of the homographies induced by the same 3D plane across the whole sequence permits the direct recovery of the camera projection matrices and of the Euclidean camera 3D motion, which is later refined through a local resectioning process
Cited by40BibtexViews11DOI
0
0
(2000)
Consider that it has further been discovered that it's not just the children's and the parents' birth dates that are correlated with the children's careers. No matter how many more complex covariation patterns we discover, most well-educated people would dismiss these findings be...
Cited by175BibtexViews14
0
0
Current biology : CB, no. 12 (2000): 723-726
In Experiment 1, S.A. received a number of tests, including a causal knowledge test, the picture arrangement test from the Wechsler adult intelligence scale, and a theory of mind’ task consisting of ‘changed container’ false-belief measures
Cited by89BibtexViews13DOI
0
0
ECCV (2), pp.657-673, (1998)
We have described an approach based on appearance based models for robust lip tracking and feature extraction
Cited by52BibtexViews8DOI
0
0