Predict human activities in videos
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
To facilitate the training, the network is learned with an auxiliary task of predicting future location in which the activity will happen.
Ranked #1 on Trajectory Forecasting on ActEV
This work introduces a method to tune a sequence-based generative model for molecular de novo design that through augmented episodic likelihood can learn to generate structures with certain specified desirable properties.
Bayesian Matrix Factorization (BMF) is a powerful technique for recommender systems because it produces good results and is relatively robust against overfitting.
We propose Macau, a powerful and flexible Bayesian factorization method for heterogeneous data.
Uncharacteristic of state-of-the-art approaches, our representations and models generalize to completely different datasets, collected across several cities, and also across countries where people drive on opposite sides of the road (left-handed vs right-handed driving).
No spatial coherence is forced on the glimpse locations, which gives the module liberty to explore different points at each frame and better optimize the process of scrutinizing visual information.
Ranked #6 on Skeleton Based Action Recognition on N-UCLA
The derived uncertainty-based ranking loss is found to significantly boost model performance by improving the quality of relational features.
These data were trained on a deep learning model which was also integrated with the Attention mechanism to facilitate training and interpreting.
Ranked #1 on Drug Discovery on egfr-inh
We present a PrBPM technique that transforms the next most likely activities into the next best actions regarding a given KPI.
Visualizing graph embeddings annotated with predictions of potentially suicidal individuals shows the integrated model could classify such individuals even if they are positioned far from the support group.