Titlebook: Intelligence Science and Big Data Engineering. Visual Data Engineering; 9th International Co Zhen Cui,Jinshan Pan,Jian Yang Conference proc

劇本

同義聯(lián)想法

Robust Object Tracking Based on Multi-granularity Sparse Representation,with different sizes. At last, in order to reduce tracking model’s drift phenomenon due to model update, an adaptive update mechanism is designed by combining occlusion ratio and incremental HOG feature. Both qualitative and quantitative evaluations have been conducted on OTB-2013 datasets to demons

spinal-stenosis

Real-Time Visual Object Tracking Based on Reinforcement Learning with Twin Delayed Deep Deterministodel by using two Critic networks to jointly predict the bounding box confidence, and to obtain the smaller predicted value as the label to update the network parameters, thereby rendering the Critic network to avoid excessive estimation bias, accelerate the convergence of the loss function, and obt

潛移默化

Efficiently Handling Scale Variation for Pedestrian Detection, and only introduces very few additional parameters. We have conducted experiments on the CityPersons, Caltech and ETH datasets and achieved significant improvements to the baseline method, especially on the small scale subset. In particular, on the CityPersons and ETH datasets, our method surpasses

Foolproof

CAMP

莎草

Soft Transferring and Progressive Learning for Human Action Recognition,to learn from the supervisors, which have been trained on large-scale datasets. We fine-tune supervision model and train our new model on UCF101 and HMDB51 datasets, experiment results demonstrate the feasibility of soft transferring method, extend transfer learning to a broader sense, and show the

MOAN

斷斷續(xù)續(xù)

熔巖